Hugging Face's logo

Shreesh-Coder
/
interntViT-raw-finetune-Amazon

TensorBoard
Safetensors
internvl_chat
custom_code
Model card Files Metrics Community
Shreesh-Coder commited on
Commit
288325c
•
1 Parent(s): 4fe0a5d

Initial commit of the model

Browse files
Files changed (45) hide show
  1. added_tokens.json +11 -0
  2. all_results.json +8 -0
  3. checkpoint-400/added_tokens.json +11 -0
  4. checkpoint-400/config.json +201 -0
  5. checkpoint-400/generation_config.json +8 -0
  6. checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  7. checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  8. checkpoint-400/global_step400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  9. checkpoint-400/global_step400/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  10. checkpoint-400/global_step400/mp_rank_00_model_states.pt +3 -0
  11. checkpoint-400/latest +1 -0
  12. checkpoint-400/model-00001-of-00004.safetensors +3 -0
  13. checkpoint-400/model-00002-of-00004.safetensors +3 -0
  14. checkpoint-400/model-00003-of-00004.safetensors +3 -0
  15. checkpoint-400/model-00004-of-00004.safetensors +3 -0
  16. checkpoint-400/model.safetensors.index.json +900 -0
  17. checkpoint-400/rng_state_0.pth +3 -0
  18. checkpoint-400/rng_state_1.pth +3 -0
  19. checkpoint-400/rng_state_2.pth +3 -0
  20. checkpoint-400/rng_state_3.pth +3 -0
  21. checkpoint-400/special_tokens_map.json +47 -0
  22. checkpoint-400/tokenization_internlm2.py +235 -0
  23. checkpoint-400/tokenizer.model +3 -0
  24. checkpoint-400/tokenizer_config.json +179 -0
  25. checkpoint-400/trainer_state.json +2421 -0
  26. checkpoint-400/training_args.bin +3 -0
  27. checkpoint-400/zero_to_fp32.py +604 -0
  28. config.json +201 -0
  29. generation_config.json +8 -0
  30. model-00001-of-00004.safetensors +3 -0
  31. model-00002-of-00004.safetensors +3 -0
  32. model-00003-of-00004.safetensors +3 -0
  33. model-00004-of-00004.safetensors +3 -0
  34. model.safetensors.index.json +900 -0
  35. runs/Sep15_15-26-42_1fe2e16e3880/events.out.tfevents.1726414020.1fe2e16e3880 +3 -0
  36. runs/Sep15_15-32-38_1fe2e16e3880/events.out.tfevents.1726414376.1fe2e16e3880 +3 -0
  37. runs/Sep15_15-34-50_1fe2e16e3880/events.out.tfevents.1726414508.1fe2e16e3880 +3 -0
  38. special_tokens_map.json +47 -0
  39. tokenization_internlm2.py +235 -0
  40. tokenizer.model +3 -0
  41. tokenizer_config.json +179 -0
  42. train_results.json +8 -0
  43. trainer_state.json +2838 -0
  44. training_args.bin +3 -0
  45. training_log.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</img>": 92545,
4
+ "</quad>": 92548,
5
+ "</ref>": 92550,
6
+ "<IMG_CONTEXT>": 92546,
7
+ "<box>": 92551,
8
+ "<img>": 92544,
9
+ "<quad>": 92547,
10
+ "<ref>": 92549
11
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99,
3
+ "train_loss": 0.3061195729762061,
4
+ "train_runtime": 5033.3609,
5
+ "train_samples": 9996,
6
+ "train_samples_per_second": 5.958,
7
+ "train_steps_per_second": 0.093
8
+ }
checkpoint-400/added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</img>": 92545,
4
+ "</quad>": 92548,
5
+ "</ref>": 92550,
6
+ "<IMG_CONTEXT>": 92546,
7
+ "<box>": 92551,
8
+ "<img>": 92544,
9
+ "<quad>": 92547,
10
+ "<ref>": 92549
11
+ }
checkpoint-400/config.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/workspace/pretrained/InternVL2-8B",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "llm_config": {
16
+ "_name_or_path": "internlm/internlm2_5-7b-chat",
17
+ "add_cross_attention": false,
18
+ "architectures": [
19
+ "InternLM2ForCausalLM"
20
+ ],
21
+ "attn_implementation": "flash_attention_2",
22
+ "auto_map": {
23
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
24
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
25
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
26
+ },
27
+ "bad_words_ids": null,
28
+ "begin_suppress_tokens": null,
29
+ "bias": false,
30
+ "bos_token_id": 1,
31
+ "chunk_size_feed_forward": 0,
32
+ "cross_attention_hidden_size": null,
33
+ "decoder_start_token_id": null,
34
+ "diversity_penalty": 0.0,
35
+ "do_sample": false,
36
+ "early_stopping": false,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": 2,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "hidden_act": "silu",
44
+ "hidden_size": 4096,
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 14336,
51
+ "is_decoder": false,
52
+ "is_encoder_decoder": false,
53
+ "label2id": {
54
+ "LABEL_0": 0,
55
+ "LABEL_1": 1
56
+ },
57
+ "length_penalty": 1.0,
58
+ "max_length": 20,
59
+ "max_position_embeddings": 32768,
60
+ "min_length": 0,
61
+ "model_type": "internlm2",
62
+ "no_repeat_ngram_size": 0,
63
+ "num_attention_heads": 32,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_hidden_layers": 32,
67
+ "num_key_value_heads": 8,
68
+ "num_return_sequences": 1,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_scores": false,
72
+ "pad_token_id": 2,
73
+ "prefix": null,
74
+ "pretraining_tp": 1,
75
+ "problem_type": null,
76
+ "pruned_heads": {},
77
+ "remove_invalid_values": false,
78
+ "repetition_penalty": 1.0,
79
+ "return_dict": true,
80
+ "return_dict_in_generate": false,
81
+ "rms_norm_eps": 1e-05,
82
+ "rope_scaling": {
83
+ "factor": 2.0,
84
+ "type": "dynamic"
85
+ },
86
+ "rope_theta": 1000000,
87
+ "sep_token_id": null,
88
+ "suppress_tokens": null,
89
+ "task_specific_params": null,
90
+ "temperature": 1.0,
91
+ "tf_legacy_loss": false,
92
+ "tie_encoder_decoder": false,
93
+ "tie_word_embeddings": false,
94
+ "tokenizer_class": null,
95
+ "top_k": 50,
96
+ "top_p": 1.0,
97
+ "torch_dtype": "bfloat16",
98
+ "torchscript": false,
99
+ "transformers_version": "4.37.2",
100
+ "typical_p": 1.0,
101
+ "use_bfloat16": true,
102
+ "use_cache": false,
103
+ "vocab_size": 92553
104
+ },
105
+ "max_dynamic_patch": 6,
106
+ "min_dynamic_patch": 1,
107
+ "model_type": "internvl_chat",
108
+ "pad2square": false,
109
+ "ps_version": "v2",
110
+ "select_layer": -1,
111
+ "template": "internlm2-chat",
112
+ "torch_dtype": "bfloat16",
113
+ "transformers_version": null,
114
+ "use_backbone_lora": 0,
115
+ "use_llm_lora": 16,
116
+ "use_thumbnail": true,
117
+ "vision_config": {
118
+ "_name_or_path": "",
119
+ "add_cross_attention": false,
120
+ "architectures": [
121
+ "InternVisionModel"
122
+ ],
123
+ "attention_dropout": 0.0,
124
+ "bad_words_ids": null,
125
+ "begin_suppress_tokens": null,
126
+ "bos_token_id": null,
127
+ "chunk_size_feed_forward": 0,
128
+ "cross_attention_hidden_size": null,
129
+ "decoder_start_token_id": null,
130
+ "diversity_penalty": 0.0,
131
+ "do_sample": false,
132
+ "drop_path_rate": 0.0,
133
+ "dropout": 0.0,
134
+ "early_stopping": false,
135
+ "encoder_no_repeat_ngram_size": 0,
136
+ "eos_token_id": null,
137
+ "exponential_decay_length_penalty": null,
138
+ "finetuning_task": null,
139
+ "forced_bos_token_id": null,
140
+ "forced_eos_token_id": null,
141
+ "hidden_act": "gelu",
142
+ "hidden_size": 1024,
143
+ "id2label": {
144
+ "0": "LABEL_0",
145
+ "1": "LABEL_1"
146
+ },
147
+ "image_size": 448,
148
+ "initializer_factor": 1.0,
149
+ "initializer_range": 0.02,
150
+ "intermediate_size": 4096,
151
+ "is_decoder": false,
152
+ "is_encoder_decoder": false,
153
+ "label2id": {
154
+ "LABEL_0": 0,
155
+ "LABEL_1": 1
156
+ },
157
+ "layer_norm_eps": 1e-06,
158
+ "length_penalty": 1.0,
159
+ "max_length": 20,
160
+ "min_length": 0,
161
+ "model_type": "intern_vit_6b",
162
+ "no_repeat_ngram_size": 0,
163
+ "norm_type": "layer_norm",
164
+ "num_attention_heads": 16,
165
+ "num_beam_groups": 1,
166
+ "num_beams": 1,
167
+ "num_channels": 3,
168
+ "num_hidden_layers": 24,
169
+ "num_return_sequences": 1,
170
+ "output_attentions": false,
171
+ "output_hidden_states": false,
172
+ "output_scores": false,
173
+ "pad_token_id": null,
174
+ "patch_size": 14,
175
+ "prefix": null,
176
+ "problem_type": null,
177
+ "pruned_heads": {},
178
+ "qk_normalization": false,
179
+ "qkv_bias": true,
180
+ "remove_invalid_values": false,
181
+ "repetition_penalty": 1.0,
182
+ "return_dict": true,
183
+ "return_dict_in_generate": false,
184
+ "sep_token_id": null,
185
+ "suppress_tokens": null,
186
+ "task_specific_params": null,
187
+ "temperature": 1.0,
188
+ "tf_legacy_loss": false,
189
+ "tie_encoder_decoder": false,
190
+ "tie_word_embeddings": true,
191
+ "tokenizer_class": null,
192
+ "top_k": 50,
193
+ "top_p": 1.0,
194
+ "torch_dtype": "bfloat16",
195
+ "torchscript": false,
196
+ "transformers_version": "4.37.2",
197
+ "typical_p": 1.0,
198
+ "use_bfloat16": true,
199
+ "use_flash_attn": true
200
+ }
201
+ }
checkpoint-400/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 92542,
5
+ 92543
6
+ ],
7
+ "transformers_version": "4.37.2"
8
+ }
checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7392530fd3a7a55eb7b6f730515e1aa558de544e1f59052c4ccc9f7e07610df1
3
+ size 113259408
checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93acdf40c79970926726f5231d9d48c5bd2f92e0c2d6680846f787d94901bb23
3
+ size 113259472
checkpoint-400/global_step400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc3dafb395aebc04e059cab5ba9ba97e7c3024ccd8d378bae71f16fb06d511f1
3
+ size 113259536
checkpoint-400/global_step400/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff080eeb81b130783d76cdeba02a791c17432fb93ff1b9dfe72b7724e34c476
3
+ size 113259536
checkpoint-400/global_step400/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee1d3239d12595f891a2aea19410528b70aa342e448c8c3633bbd540adcd1135
3
+ size 16226755142
checkpoint-400/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step400
checkpoint-400/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08004a9eee5f9e25e73a272951298aea0e541dbf571d2308aa34c670c7e2f429
3
+ size 4959423416
checkpoint-400/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d71916eac60be672d8c2a98add2e33827ba52f4818531709137ce2b647ce3ed1
3
+ size 4942476624
checkpoint-400/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d622098094b0be9f4aa5fab7df89bdab8633df688cb13b730f8dcb84900efc0c
3
+ size 4942476664
checkpoint-400/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59aa4893389a55c11081900afd1ee17532bcaa4bf3962c004958ada23aa90bec
3
+ size 1381978232
checkpoint-400/model.safetensors.index.json ADDED
@@ -0,0 +1,900 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16226228224
4
+ },
5
+ "weight_map": {
6
+ "language_model.base_model.model.model.layers.0.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.base_model.model.model.layers.0.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.base_model.model.model.layers.0.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.base_model.model.model.layers.0.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.base_model.model.model.layers.0.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.base_model.model.model.layers.0.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.base_model.model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.base_model.model.model.layers.0.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.base_model.model.model.layers.0.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.base_model.model.model.layers.0.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.base_model.model.model.layers.0.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.base_model.model.model.layers.0.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.base_model.model.model.layers.0.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.base_model.model.model.layers.0.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.base_model.model.model.layers.0.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.base_model.model.model.layers.0.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.base_model.model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.base_model.model.model.layers.1.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.base_model.model.model.layers.1.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.base_model.model.model.layers.1.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.base_model.model.model.layers.1.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.base_model.model.model.layers.1.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.base_model.model.model.layers.1.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
29
+ "language_model.base_model.model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
30
+ "language_model.base_model.model.model.layers.1.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
31
+ "language_model.base_model.model.model.layers.1.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
32
+ "language_model.base_model.model.model.layers.1.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
33
+ "language_model.base_model.model.model.layers.1.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
34
+ "language_model.base_model.model.model.layers.1.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
35
+ "language_model.base_model.model.model.layers.1.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
36
+ "language_model.base_model.model.model.layers.1.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
37
+ "language_model.base_model.model.model.layers.1.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
38
+ "language_model.base_model.model.model.layers.1.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
39
+ "language_model.base_model.model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
40
+ "language_model.base_model.model.model.layers.10.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.base_model.model.model.layers.10.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.base_model.model.model.layers.10.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.base_model.model.model.layers.10.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.base_model.model.model.layers.10.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.base_model.model.model.layers.10.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.base_model.model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.base_model.model.model.layers.10.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.base_model.model.model.layers.10.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.base_model.model.model.layers.10.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.base_model.model.model.layers.10.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.base_model.model.model.layers.10.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.base_model.model.model.layers.10.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.base_model.model.model.layers.10.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.base_model.model.model.layers.10.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.base_model.model.model.layers.10.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.base_model.model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.base_model.model.model.layers.11.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.base_model.model.model.layers.11.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.base_model.model.model.layers.11.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.base_model.model.model.layers.11.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.base_model.model.model.layers.11.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.base_model.model.model.layers.11.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.base_model.model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.base_model.model.model.layers.11.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.base_model.model.model.layers.11.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.base_model.model.model.layers.11.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.base_model.model.model.layers.11.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.base_model.model.model.layers.11.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.base_model.model.model.layers.11.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.base_model.model.model.layers.11.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.base_model.model.model.layers.11.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.base_model.model.model.layers.11.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.base_model.model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.base_model.model.model.layers.12.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.base_model.model.model.layers.12.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.base_model.model.model.layers.12.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.base_model.model.model.layers.12.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.base_model.model.model.layers.12.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.base_model.model.model.layers.12.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.base_model.model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.base_model.model.model.layers.12.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.base_model.model.model.layers.12.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.base_model.model.model.layers.12.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.base_model.model.model.layers.12.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.base_model.model.model.layers.12.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.base_model.model.model.layers.12.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.base_model.model.model.layers.12.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.base_model.model.model.layers.12.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.base_model.model.model.layers.12.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.base_model.model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.base_model.model.model.layers.13.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.base_model.model.model.layers.13.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.base_model.model.model.layers.13.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.base_model.model.model.layers.13.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.base_model.model.model.layers.13.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.base_model.model.model.layers.13.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.base_model.model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.base_model.model.model.layers.13.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.base_model.model.model.layers.13.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.base_model.model.model.layers.13.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.base_model.model.model.layers.13.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.base_model.model.model.layers.13.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.base_model.model.model.layers.13.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.base_model.model.model.layers.13.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.base_model.model.model.layers.13.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.base_model.model.model.layers.13.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.base_model.model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.base_model.model.model.layers.14.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.base_model.model.model.layers.14.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.base_model.model.model.layers.14.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.base_model.model.model.layers.14.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.base_model.model.model.layers.14.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.base_model.model.model.layers.14.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.base_model.model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.base_model.model.model.layers.14.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.base_model.model.model.layers.14.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.base_model.model.model.layers.14.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
118
+ "language_model.base_model.model.model.layers.14.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
119
+ "language_model.base_model.model.model.layers.14.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
120
+ "language_model.base_model.model.model.layers.14.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
121
+ "language_model.base_model.model.model.layers.14.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
122
+ "language_model.base_model.model.model.layers.14.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
123
+ "language_model.base_model.model.model.layers.14.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
124
+ "language_model.base_model.model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
125
+ "language_model.base_model.model.model.layers.15.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
126
+ "language_model.base_model.model.model.layers.15.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
127
+ "language_model.base_model.model.model.layers.15.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
128
+ "language_model.base_model.model.model.layers.15.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
129
+ "language_model.base_model.model.model.layers.15.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
130
+ "language_model.base_model.model.model.layers.15.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
131
+ "language_model.base_model.model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
132
+ "language_model.base_model.model.model.layers.15.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
133
+ "language_model.base_model.model.model.layers.15.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
134
+ "language_model.base_model.model.model.layers.15.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
135
+ "language_model.base_model.model.model.layers.15.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
136
+ "language_model.base_model.model.model.layers.15.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
137
+ "language_model.base_model.model.model.layers.15.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
138
+ "language_model.base_model.model.model.layers.15.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
139
+ "language_model.base_model.model.model.layers.15.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
140
+ "language_model.base_model.model.model.layers.15.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
141
+ "language_model.base_model.model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
142
+ "language_model.base_model.model.model.layers.16.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
143
+ "language_model.base_model.model.model.layers.16.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
144
+ "language_model.base_model.model.model.layers.16.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
145
+ "language_model.base_model.model.model.layers.16.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
146
+ "language_model.base_model.model.model.layers.16.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
147
+ "language_model.base_model.model.model.layers.16.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
148
+ "language_model.base_model.model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
149
+ "language_model.base_model.model.model.layers.16.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
150
+ "language_model.base_model.model.model.layers.16.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
151
+ "language_model.base_model.model.model.layers.16.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
152
+ "language_model.base_model.model.model.layers.16.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
153
+ "language_model.base_model.model.model.layers.16.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
154
+ "language_model.base_model.model.model.layers.16.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
155
+ "language_model.base_model.model.model.layers.16.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
156
+ "language_model.base_model.model.model.layers.16.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
157
+ "language_model.base_model.model.model.layers.16.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
158
+ "language_model.base_model.model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
159
+ "language_model.base_model.model.model.layers.17.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
160
+ "language_model.base_model.model.model.layers.17.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
161
+ "language_model.base_model.model.model.layers.17.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
162
+ "language_model.base_model.model.model.layers.17.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
163
+ "language_model.base_model.model.model.layers.17.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
164
+ "language_model.base_model.model.model.layers.17.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
165
+ "language_model.base_model.model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
166
+ "language_model.base_model.model.model.layers.17.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
167
+ "language_model.base_model.model.model.layers.17.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
168
+ "language_model.base_model.model.model.layers.17.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
169
+ "language_model.base_model.model.model.layers.17.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
170
+ "language_model.base_model.model.model.layers.17.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
171
+ "language_model.base_model.model.model.layers.17.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
172
+ "language_model.base_model.model.model.layers.17.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
173
+ "language_model.base_model.model.model.layers.17.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
174
+ "language_model.base_model.model.model.layers.17.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
175
+ "language_model.base_model.model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
176
+ "language_model.base_model.model.model.layers.18.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
177
+ "language_model.base_model.model.model.layers.18.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
178
+ "language_model.base_model.model.model.layers.18.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
179
+ "language_model.base_model.model.model.layers.18.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
180
+ "language_model.base_model.model.model.layers.18.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
181
+ "language_model.base_model.model.model.layers.18.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
182
+ "language_model.base_model.model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
183
+ "language_model.base_model.model.model.layers.18.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
184
+ "language_model.base_model.model.model.layers.18.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
185
+ "language_model.base_model.model.model.layers.18.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
186
+ "language_model.base_model.model.model.layers.18.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
187
+ "language_model.base_model.model.model.layers.18.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
188
+ "language_model.base_model.model.model.layers.18.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
189
+ "language_model.base_model.model.model.layers.18.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
190
+ "language_model.base_model.model.model.layers.18.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
191
+ "language_model.base_model.model.model.layers.18.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
192
+ "language_model.base_model.model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
193
+ "language_model.base_model.model.model.layers.19.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
194
+ "language_model.base_model.model.model.layers.19.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
195
+ "language_model.base_model.model.model.layers.19.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
196
+ "language_model.base_model.model.model.layers.19.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
197
+ "language_model.base_model.model.model.layers.19.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
198
+ "language_model.base_model.model.model.layers.19.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
199
+ "language_model.base_model.model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.base_model.model.model.layers.19.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
201
+ "language_model.base_model.model.model.layers.19.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
202
+ "language_model.base_model.model.model.layers.19.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
203
+ "language_model.base_model.model.model.layers.19.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.base_model.model.model.layers.19.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.base_model.model.model.layers.19.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.base_model.model.model.layers.19.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.base_model.model.model.layers.19.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.base_model.model.model.layers.19.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.base_model.model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.base_model.model.model.layers.2.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
211
+ "language_model.base_model.model.model.layers.2.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.base_model.model.model.layers.2.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
213
+ "language_model.base_model.model.model.layers.2.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.base_model.model.model.layers.2.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
215
+ "language_model.base_model.model.model.layers.2.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.base_model.model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.base_model.model.model.layers.2.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.base_model.model.model.layers.2.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
219
+ "language_model.base_model.model.model.layers.2.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
220
+ "language_model.base_model.model.model.layers.2.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
221
+ "language_model.base_model.model.model.layers.2.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
222
+ "language_model.base_model.model.model.layers.2.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
223
+ "language_model.base_model.model.model.layers.2.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
224
+ "language_model.base_model.model.model.layers.2.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
225
+ "language_model.base_model.model.model.layers.2.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
226
+ "language_model.base_model.model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
227
+ "language_model.base_model.model.model.layers.20.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.base_model.model.model.layers.20.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.base_model.model.model.layers.20.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.base_model.model.model.layers.20.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.base_model.model.model.layers.20.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.base_model.model.model.layers.20.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.base_model.model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.base_model.model.model.layers.20.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
235
+ "language_model.base_model.model.model.layers.20.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
236
+ "language_model.base_model.model.model.layers.20.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.base_model.model.model.layers.20.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.base_model.model.model.layers.20.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.base_model.model.model.layers.20.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.base_model.model.model.layers.20.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.base_model.model.model.layers.20.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.base_model.model.model.layers.20.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.base_model.model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.base_model.model.model.layers.21.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
245
+ "language_model.base_model.model.model.layers.21.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
246
+ "language_model.base_model.model.model.layers.21.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
247
+ "language_model.base_model.model.model.layers.21.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
248
+ "language_model.base_model.model.model.layers.21.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
249
+ "language_model.base_model.model.model.layers.21.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
250
+ "language_model.base_model.model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
251
+ "language_model.base_model.model.model.layers.21.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
252
+ "language_model.base_model.model.model.layers.21.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
253
+ "language_model.base_model.model.model.layers.21.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
254
+ "language_model.base_model.model.model.layers.21.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
255
+ "language_model.base_model.model.model.layers.21.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
256
+ "language_model.base_model.model.model.layers.21.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
257
+ "language_model.base_model.model.model.layers.21.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
258
+ "language_model.base_model.model.model.layers.21.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
259
+ "language_model.base_model.model.model.layers.21.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
260
+ "language_model.base_model.model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
261
+ "language_model.base_model.model.model.layers.22.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
262
+ "language_model.base_model.model.model.layers.22.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
263
+ "language_model.base_model.model.model.layers.22.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
264
+ "language_model.base_model.model.model.layers.22.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
265
+ "language_model.base_model.model.model.layers.22.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
266
+ "language_model.base_model.model.model.layers.22.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
267
+ "language_model.base_model.model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
268
+ "language_model.base_model.model.model.layers.22.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
269
+ "language_model.base_model.model.model.layers.22.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
270
+ "language_model.base_model.model.model.layers.22.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
271
+ "language_model.base_model.model.model.layers.22.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
272
+ "language_model.base_model.model.model.layers.22.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
273
+ "language_model.base_model.model.model.layers.22.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
274
+ "language_model.base_model.model.model.layers.22.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
275
+ "language_model.base_model.model.model.layers.22.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
276
+ "language_model.base_model.model.model.layers.22.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
277
+ "language_model.base_model.model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
278
+ "language_model.base_model.model.model.layers.23.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
279
+ "language_model.base_model.model.model.layers.23.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
280
+ "language_model.base_model.model.model.layers.23.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
281
+ "language_model.base_model.model.model.layers.23.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
282
+ "language_model.base_model.model.model.layers.23.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
283
+ "language_model.base_model.model.model.layers.23.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
284
+ "language_model.base_model.model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
285
+ "language_model.base_model.model.model.layers.23.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
286
+ "language_model.base_model.model.model.layers.23.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
287
+ "language_model.base_model.model.model.layers.23.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
288
+ "language_model.base_model.model.model.layers.23.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
289
+ "language_model.base_model.model.model.layers.23.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
290
+ "language_model.base_model.model.model.layers.23.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
291
+ "language_model.base_model.model.model.layers.23.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
292
+ "language_model.base_model.model.model.layers.23.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
293
+ "language_model.base_model.model.model.layers.23.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
294
+ "language_model.base_model.model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
295
+ "language_model.base_model.model.model.layers.24.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
296
+ "language_model.base_model.model.model.layers.24.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
297
+ "language_model.base_model.model.model.layers.24.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
298
+ "language_model.base_model.model.model.layers.24.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
299
+ "language_model.base_model.model.model.layers.24.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
300
+ "language_model.base_model.model.model.layers.24.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
301
+ "language_model.base_model.model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
302
+ "language_model.base_model.model.model.layers.24.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
303
+ "language_model.base_model.model.model.layers.24.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
304
+ "language_model.base_model.model.model.layers.24.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
305
+ "language_model.base_model.model.model.layers.24.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
306
+ "language_model.base_model.model.model.layers.24.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
307
+ "language_model.base_model.model.model.layers.24.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
308
+ "language_model.base_model.model.model.layers.24.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
309
+ "language_model.base_model.model.model.layers.24.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
310
+ "language_model.base_model.model.model.layers.24.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
311
+ "language_model.base_model.model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
312
+ "language_model.base_model.model.model.layers.25.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
313
+ "language_model.base_model.model.model.layers.25.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
314
+ "language_model.base_model.model.model.layers.25.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
315
+ "language_model.base_model.model.model.layers.25.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
316
+ "language_model.base_model.model.model.layers.25.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
317
+ "language_model.base_model.model.model.layers.25.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
318
+ "language_model.base_model.model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
319
+ "language_model.base_model.model.model.layers.25.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
320
+ "language_model.base_model.model.model.layers.25.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
321
+ "language_model.base_model.model.model.layers.25.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
322
+ "language_model.base_model.model.model.layers.25.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
323
+ "language_model.base_model.model.model.layers.25.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
324
+ "language_model.base_model.model.model.layers.25.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
325
+ "language_model.base_model.model.model.layers.25.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
326
+ "language_model.base_model.model.model.layers.25.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
327
+ "language_model.base_model.model.model.layers.25.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
328
+ "language_model.base_model.model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
329
+ "language_model.base_model.model.model.layers.26.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
330
+ "language_model.base_model.model.model.layers.26.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
331
+ "language_model.base_model.model.model.layers.26.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
332
+ "language_model.base_model.model.model.layers.26.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
333
+ "language_model.base_model.model.model.layers.26.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
334
+ "language_model.base_model.model.model.layers.26.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
335
+ "language_model.base_model.model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
336
+ "language_model.base_model.model.model.layers.26.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
337
+ "language_model.base_model.model.model.layers.26.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
338
+ "language_model.base_model.model.model.layers.26.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
339
+ "language_model.base_model.model.model.layers.26.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
340
+ "language_model.base_model.model.model.layers.26.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
341
+ "language_model.base_model.model.model.layers.26.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
342
+ "language_model.base_model.model.model.layers.26.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
343
+ "language_model.base_model.model.model.layers.26.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
344
+ "language_model.base_model.model.model.layers.26.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
345
+ "language_model.base_model.model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
346
+ "language_model.base_model.model.model.layers.27.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
347
+ "language_model.base_model.model.model.layers.27.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
348
+ "language_model.base_model.model.model.layers.27.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
349
+ "language_model.base_model.model.model.layers.27.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
350
+ "language_model.base_model.model.model.layers.27.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
351
+ "language_model.base_model.model.model.layers.27.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
352
+ "language_model.base_model.model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
353
+ "language_model.base_model.model.model.layers.27.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
354
+ "language_model.base_model.model.model.layers.27.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
355
+ "language_model.base_model.model.model.layers.27.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
356
+ "language_model.base_model.model.model.layers.27.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
357
+ "language_model.base_model.model.model.layers.27.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
358
+ "language_model.base_model.model.model.layers.27.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
359
+ "language_model.base_model.model.model.layers.27.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
360
+ "language_model.base_model.model.model.layers.27.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
361
+ "language_model.base_model.model.model.layers.27.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
362
+ "language_model.base_model.model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
363
+ "language_model.base_model.model.model.layers.28.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
364
+ "language_model.base_model.model.model.layers.28.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
365
+ "language_model.base_model.model.model.layers.28.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
366
+ "language_model.base_model.model.model.layers.28.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
367
+ "language_model.base_model.model.model.layers.28.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
368
+ "language_model.base_model.model.model.layers.28.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
369
+ "language_model.base_model.model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
370
+ "language_model.base_model.model.model.layers.28.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
371
+ "language_model.base_model.model.model.layers.28.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
372
+ "language_model.base_model.model.model.layers.28.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
373
+ "language_model.base_model.model.model.layers.28.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
374
+ "language_model.base_model.model.model.layers.28.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
375
+ "language_model.base_model.model.model.layers.28.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
376
+ "language_model.base_model.model.model.layers.28.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
377
+ "language_model.base_model.model.model.layers.28.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
378
+ "language_model.base_model.model.model.layers.28.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
379
+ "language_model.base_model.model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
380
+ "language_model.base_model.model.model.layers.29.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
381
+ "language_model.base_model.model.model.layers.29.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
382
+ "language_model.base_model.model.model.layers.29.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
383
+ "language_model.base_model.model.model.layers.29.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
384
+ "language_model.base_model.model.model.layers.29.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
385
+ "language_model.base_model.model.model.layers.29.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
386
+ "language_model.base_model.model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
387
+ "language_model.base_model.model.model.layers.29.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
388
+ "language_model.base_model.model.model.layers.29.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
389
+ "language_model.base_model.model.model.layers.29.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
390
+ "language_model.base_model.model.model.layers.29.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
391
+ "language_model.base_model.model.model.layers.29.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
392
+ "language_model.base_model.model.model.layers.29.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
393
+ "language_model.base_model.model.model.layers.29.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
394
+ "language_model.base_model.model.model.layers.29.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
395
+ "language_model.base_model.model.model.layers.29.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
396
+ "language_model.base_model.model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
397
+ "language_model.base_model.model.model.layers.3.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
398
+ "language_model.base_model.model.model.layers.3.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
399
+ "language_model.base_model.model.model.layers.3.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
400
+ "language_model.base_model.model.model.layers.3.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
401
+ "language_model.base_model.model.model.layers.3.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
402
+ "language_model.base_model.model.model.layers.3.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
403
+ "language_model.base_model.model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
404
+ "language_model.base_model.model.model.layers.3.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
405
+ "language_model.base_model.model.model.layers.3.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
406
+ "language_model.base_model.model.model.layers.3.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
407
+ "language_model.base_model.model.model.layers.3.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
408
+ "language_model.base_model.model.model.layers.3.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
409
+ "language_model.base_model.model.model.layers.3.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
410
+ "language_model.base_model.model.model.layers.3.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
411
+ "language_model.base_model.model.model.layers.3.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
412
+ "language_model.base_model.model.model.layers.3.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
413
+ "language_model.base_model.model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
414
+ "language_model.base_model.model.model.layers.30.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
415
+ "language_model.base_model.model.model.layers.30.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
416
+ "language_model.base_model.model.model.layers.30.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
417
+ "language_model.base_model.model.model.layers.30.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
418
+ "language_model.base_model.model.model.layers.30.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
419
+ "language_model.base_model.model.model.layers.30.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
420
+ "language_model.base_model.model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
421
+ "language_model.base_model.model.model.layers.30.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
422
+ "language_model.base_model.model.model.layers.30.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
423
+ "language_model.base_model.model.model.layers.30.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
424
+ "language_model.base_model.model.model.layers.30.feed_forward.w2.base_layer.weight": "model-00004-of-00004.safetensors",
425
+ "language_model.base_model.model.model.layers.30.feed_forward.w2.lora_A.default.weight": "model-00004-of-00004.safetensors",
426
+ "language_model.base_model.model.model.layers.30.feed_forward.w2.lora_B.default.weight": "model-00004-of-00004.safetensors",
427
+ "language_model.base_model.model.model.layers.30.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
428
+ "language_model.base_model.model.model.layers.30.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
429
+ "language_model.base_model.model.model.layers.30.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
430
+ "language_model.base_model.model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
431
+ "language_model.base_model.model.model.layers.31.attention.wo.base_layer.weight": "model-00004-of-00004.safetensors",
432
+ "language_model.base_model.model.model.layers.31.attention.wo.lora_A.default.weight": "model-00004-of-00004.safetensors",
433
+ "language_model.base_model.model.model.layers.31.attention.wo.lora_B.default.weight": "model-00004-of-00004.safetensors",
434
+ "language_model.base_model.model.model.layers.31.attention.wqkv.base_layer.weight": "model-00004-of-00004.safetensors",
435
+ "language_model.base_model.model.model.layers.31.attention.wqkv.lora_A.default.weight": "model-00004-of-00004.safetensors",
436
+ "language_model.base_model.model.model.layers.31.attention.wqkv.lora_B.default.weight": "model-00004-of-00004.safetensors",
437
+ "language_model.base_model.model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
438
+ "language_model.base_model.model.model.layers.31.feed_forward.w1.base_layer.weight": "model-00004-of-00004.safetensors",
439
+ "language_model.base_model.model.model.layers.31.feed_forward.w1.lora_A.default.weight": "model-00004-of-00004.safetensors",
440
+ "language_model.base_model.model.model.layers.31.feed_forward.w1.lora_B.default.weight": "model-00004-of-00004.safetensors",
441
+ "language_model.base_model.model.model.layers.31.feed_forward.w2.base_layer.weight": "model-00004-of-00004.safetensors",
442
+ "language_model.base_model.model.model.layers.31.feed_forward.w2.lora_A.default.weight": "model-00004-of-00004.safetensors",
443
+ "language_model.base_model.model.model.layers.31.feed_forward.w2.lora_B.default.weight": "model-00004-of-00004.safetensors",
444
+ "language_model.base_model.model.model.layers.31.feed_forward.w3.base_layer.weight": "model-00004-of-00004.safetensors",
445
+ "language_model.base_model.model.model.layers.31.feed_forward.w3.lora_A.default.weight": "model-00004-of-00004.safetensors",
446
+ "language_model.base_model.model.model.layers.31.feed_forward.w3.lora_B.default.weight": "model-00004-of-00004.safetensors",
447
+ "language_model.base_model.model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
448
+ "language_model.base_model.model.model.layers.4.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
449
+ "language_model.base_model.model.model.layers.4.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
450
+ "language_model.base_model.model.model.layers.4.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
451
+ "language_model.base_model.model.model.layers.4.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
452
+ "language_model.base_model.model.model.layers.4.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
453
+ "language_model.base_model.model.model.layers.4.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
454
+ "language_model.base_model.model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
455
+ "language_model.base_model.model.model.layers.4.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
456
+ "language_model.base_model.model.model.layers.4.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
457
+ "language_model.base_model.model.model.layers.4.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
458
+ "language_model.base_model.model.model.layers.4.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
459
+ "language_model.base_model.model.model.layers.4.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
460
+ "language_model.base_model.model.model.layers.4.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
461
+ "language_model.base_model.model.model.layers.4.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
462
+ "language_model.base_model.model.model.layers.4.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
463
+ "language_model.base_model.model.model.layers.4.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
464
+ "language_model.base_model.model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
465
+ "language_model.base_model.model.model.layers.5.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
466
+ "language_model.base_model.model.model.layers.5.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
467
+ "language_model.base_model.model.model.layers.5.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
468
+ "language_model.base_model.model.model.layers.5.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
469
+ "language_model.base_model.model.model.layers.5.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
470
+ "language_model.base_model.model.model.layers.5.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
471
+ "language_model.base_model.model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
472
+ "language_model.base_model.model.model.layers.5.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
473
+ "language_model.base_model.model.model.layers.5.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
474
+ "language_model.base_model.model.model.layers.5.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
475
+ "language_model.base_model.model.model.layers.5.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
476
+ "language_model.base_model.model.model.layers.5.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
477
+ "language_model.base_model.model.model.layers.5.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
478
+ "language_model.base_model.model.model.layers.5.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
479
+ "language_model.base_model.model.model.layers.5.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
480
+ "language_model.base_model.model.model.layers.5.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
481
+ "language_model.base_model.model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
482
+ "language_model.base_model.model.model.layers.6.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
483
+ "language_model.base_model.model.model.layers.6.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
484
+ "language_model.base_model.model.model.layers.6.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
485
+ "language_model.base_model.model.model.layers.6.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
486
+ "language_model.base_model.model.model.layers.6.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
487
+ "language_model.base_model.model.model.layers.6.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
488
+ "language_model.base_model.model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
489
+ "language_model.base_model.model.model.layers.6.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
490
+ "language_model.base_model.model.model.layers.6.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
491
+ "language_model.base_model.model.model.layers.6.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
492
+ "language_model.base_model.model.model.layers.6.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
493
+ "language_model.base_model.model.model.layers.6.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
494
+ "language_model.base_model.model.model.layers.6.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
495
+ "language_model.base_model.model.model.layers.6.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
496
+ "language_model.base_model.model.model.layers.6.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
497
+ "language_model.base_model.model.model.layers.6.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
498
+ "language_model.base_model.model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
499
+ "language_model.base_model.model.model.layers.7.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
500
+ "language_model.base_model.model.model.layers.7.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
501
+ "language_model.base_model.model.model.layers.7.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
502
+ "language_model.base_model.model.model.layers.7.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
503
+ "language_model.base_model.model.model.layers.7.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
504
+ "language_model.base_model.model.model.layers.7.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
505
+ "language_model.base_model.model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
506
+ "language_model.base_model.model.model.layers.7.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
507
+ "language_model.base_model.model.model.layers.7.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
508
+ "language_model.base_model.model.model.layers.7.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
509
+ "language_model.base_model.model.model.layers.7.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
510
+ "language_model.base_model.model.model.layers.7.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
511
+ "language_model.base_model.model.model.layers.7.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
512
+ "language_model.base_model.model.model.layers.7.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
513
+ "language_model.base_model.model.model.layers.7.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
514
+ "language_model.base_model.model.model.layers.7.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
515
+ "language_model.base_model.model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
516
+ "language_model.base_model.model.model.layers.8.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
517
+ "language_model.base_model.model.model.layers.8.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
518
+ "language_model.base_model.model.model.layers.8.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
519
+ "language_model.base_model.model.model.layers.8.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
520
+ "language_model.base_model.model.model.layers.8.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
521
+ "language_model.base_model.model.model.layers.8.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
522
+ "language_model.base_model.model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
523
+ "language_model.base_model.model.model.layers.8.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
524
+ "language_model.base_model.model.model.layers.8.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
525
+ "language_model.base_model.model.model.layers.8.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
526
+ "language_model.base_model.model.model.layers.8.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
527
+ "language_model.base_model.model.model.layers.8.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
528
+ "language_model.base_model.model.model.layers.8.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
529
+ "language_model.base_model.model.model.layers.8.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
530
+ "language_model.base_model.model.model.layers.8.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
531
+ "language_model.base_model.model.model.layers.8.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
532
+ "language_model.base_model.model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
533
+ "language_model.base_model.model.model.layers.9.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
534
+ "language_model.base_model.model.model.layers.9.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
535
+ "language_model.base_model.model.model.layers.9.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
536
+ "language_model.base_model.model.model.layers.9.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
537
+ "language_model.base_model.model.model.layers.9.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
538
+ "language_model.base_model.model.model.layers.9.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
539
+ "language_model.base_model.model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
540
+ "language_model.base_model.model.model.layers.9.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
541
+ "language_model.base_model.model.model.layers.9.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
542
+ "language_model.base_model.model.model.layers.9.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
543
+ "language_model.base_model.model.model.layers.9.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
544
+ "language_model.base_model.model.model.layers.9.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
545
+ "language_model.base_model.model.model.layers.9.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
546
+ "language_model.base_model.model.model.layers.9.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
547
+ "language_model.base_model.model.model.layers.9.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
548
+ "language_model.base_model.model.model.layers.9.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
549
+ "language_model.base_model.model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
550
+ "language_model.base_model.model.model.norm.weight": "model-00004-of-00004.safetensors",
551
+ "language_model.base_model.model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
552
+ "language_model.base_model.model.output.weight": "model-00004-of-00004.safetensors",
553
+ "mlp1.0.bias": "model-00004-of-00004.safetensors",
554
+ "mlp1.0.weight": "model-00004-of-00004.safetensors",
555
+ "mlp1.1.bias": "model-00004-of-00004.safetensors",
556
+ "mlp1.1.weight": "model-00004-of-00004.safetensors",
557
+ "mlp1.3.bias": "model-00004-of-00004.safetensors",
558
+ "mlp1.3.weight": "model-00004-of-00004.safetensors",
559
+ "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
560
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
561
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
562
+ "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
563
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
564
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
565
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
568
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
569
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
570
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
571
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
576
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
578
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
579
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
580
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
581
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
582
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
583
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
584
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
585
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
586
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
587
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
588
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
589
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
590
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
591
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
592
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
593
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
594
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
595
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
596
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
597
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
598
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
599
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
600
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
602
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
603
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
604
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
605
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
606
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
607
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
608
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
609
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
610
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
611
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
612
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
613
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
614
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
615
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
616
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
617
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
618
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
619
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
620
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
621
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
622
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
623
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
624
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
625
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
626
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
627
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
628
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
629
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
630
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
631
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
632
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
633
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
636
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
637
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
638
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
639
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
640
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
641
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
642
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
643
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
644
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
645
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
646
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
647
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
648
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
649
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
650
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
651
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
652
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
653
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
654
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
655
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
656
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
657
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
658
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
659
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
660
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
661
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
662
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
663
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
664
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
665
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
666
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
667
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
668
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
669
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
670
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
671
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
672
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
673
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
674
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
675
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
676
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
677
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
678
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
679
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
680
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
681
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
682
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
683
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
684
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
685
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
686
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
687
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
688
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
689
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
690
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
691
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
692
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
693
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
694
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
695
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
696
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
697
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
698
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
699
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
700
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
701
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
702
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
703
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
704
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
705
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
706
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
707
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
708
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
709
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
710
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
711
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
712
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
713
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
714
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
715
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
716
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
717
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
718
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
719
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
720
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
721
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
722
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
723
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
724
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
725
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
726
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
727
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
728
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
729
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
730
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
731
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
732
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
733
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
734
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
735
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
736
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
737
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
738
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
739
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
740
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
741
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
742
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
743
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
744
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
745
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
746
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
747
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
748
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
749
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
750
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
751
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
752
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
753
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
754
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
755
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
756
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
757
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
758
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
759
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
760
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
761
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
762
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
763
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
764
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
765
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
766
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
767
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
768
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
769
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
770
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
771
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
772
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
773
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
774
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
775
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
776
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
777
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
778
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
779
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
780
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
781
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
782
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
783
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
784
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
785
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
786
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
787
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
788
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
789
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
790
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
791
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
792
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
793
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
794
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
795
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
796
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
797
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
798
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
799
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
800
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
801
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
802
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
803
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
804
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
805
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
806
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
807
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
808
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
809
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
810
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
811
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
812
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
813
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
814
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
815
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
816
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
817
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
818
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
819
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
820
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
821
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
822
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
823
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
824
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
825
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
826
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
827
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
828
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
829
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
830
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
831
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
832
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
833
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
834
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
835
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
836
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
837
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
838
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
839
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
840
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
841
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
842
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
843
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
844
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
845
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
846
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
847
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
848
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
849
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
850
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
851
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
852
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
853
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
854
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
855
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
856
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
857
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
858
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
859
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
860
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
861
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
862
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
863
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
864
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
865
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
866
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
867
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
868
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
869
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
870
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
871
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
872
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
873
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
874
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
875
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
876
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
877
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
878
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
879
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
880
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
881
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
882
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
883
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
884
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
885
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
886
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
887
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
888
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
889
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
890
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
891
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
892
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
893
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
894
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
895
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
896
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
897
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
898
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
899
+ }
900
+ }
checkpoint-400/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f7803cb74ce5380a3afff7891224a55cafb01319d7dd193b97237837493f19c
3
+ size 15024
checkpoint-400/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fb1d4cd211938878e877983a58367c1196aef89c30118f72ff04876e8a35966
3
+ size 15024
checkpoint-400/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43f863bc3c7bc6fb004e922eb49ab21fc01b93854023c1dbe34e415669407807
3
+ size 15024
checkpoint-400/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c7a68b19971e7ddf280d3b42ba642be5107abd47f6bd17dd734bd7259b383e
3
+ size 15024
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<img>",
10
+ "</img>",
11
+ "<IMG_CONTEXT>",
12
+ "<quad>",
13
+ "</quad>",
14
+ "<ref>",
15
+ "</ref>",
16
+ "<box>",
17
+ "</box>"
18
+ ],
19
+ "bos_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "eos_token": {
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "unk_token": {
41
+ "content": "<unk>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ }
47
+ }
checkpoint-400/tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
checkpoint-400/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ }
147
+ },
148
+ "additional_special_tokens": [
149
+ "<|im_start|>",
150
+ "<|im_end|>",
151
+ "<|action_start|>",
152
+ "<|action_end|>",
153
+ "<|interpreter|>",
154
+ "<|plugin|>",
155
+ "<img>",
156
+ "</img>",
157
+ "<IMG_CONTEXT>",
158
+ "<quad>",
159
+ "</quad>",
160
+ "<ref>",
161
+ "</ref>",
162
+ "<box>",
163
+ "</box>"
164
+ ],
165
+ "auto_map": {
166
+ "AutoTokenizer": [
167
+ "tokenization_internlm2.InternLM2Tokenizer",
168
+ null
169
+ ]
170
+ },
171
+ "bos_token": "<s>",
172
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
173
+ "clean_up_tokenization_spaces": false,
174
+ "eos_token": "</s>",
175
+ "model_max_length": 4096,
176
+ "pad_token": "</s>",
177
+ "tokenizer_class": "InternLM2Tokenizer",
178
+ "unk_token": "<unk>"
179
+ }
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,2421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.5559105431309903,
5
+ "eval_steps": 500,
6
+ "global_step": 400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2.666666666666667e-06,
14
+ "loss": 3.7352,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 5.333333333333334e-06,
20
+ "loss": 3.7667,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 8.000000000000001e-06,
26
+ "loss": 3.7797,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.03,
31
+ "learning_rate": 1.0666666666666667e-05,
32
+ "loss": 3.6592,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 1.3333333333333333e-05,
38
+ "loss": 3.6968,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 1.6000000000000003e-05,
44
+ "loss": 3.7754,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 1.866666666666667e-05,
50
+ "loss": 3.4281,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 2.1333333333333335e-05,
56
+ "loss": 3.6136,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.06,
61
+ "learning_rate": 2.4e-05,
62
+ "loss": 3.0098,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 2.6666666666666667e-05,
68
+ "loss": 2.7693,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 2.9333333333333333e-05,
74
+ "loss": 2.2559,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.08,
79
+ "learning_rate": 3.2000000000000005e-05,
80
+ "loss": 2.1567,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "learning_rate": 3.466666666666667e-05,
86
+ "loss": 1.7343,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.09,
91
+ "learning_rate": 3.733333333333334e-05,
92
+ "loss": 1.677,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.1,
97
+ "learning_rate": 4e-05,
98
+ "loss": 1.2854,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.1,
103
+ "learning_rate": 3.999951904814875e-05,
104
+ "loss": 1.1381,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.11,
109
+ "learning_rate": 3.999807621572648e-05,
110
+ "loss": 0.7843,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.12,
115
+ "learning_rate": 3.999567157212646e-05,
116
+ "loss": 0.7415,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.12,
121
+ "learning_rate": 3.999230523300049e-05,
122
+ "loss": 0.6684,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.13,
127
+ "learning_rate": 3.998797736025326e-05,
128
+ "loss": 0.4267,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.13,
133
+ "learning_rate": 3.9982688162034624e-05,
134
+ "loss": 0.5993,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.14,
139
+ "learning_rate": 3.997643789272954e-05,
140
+ "loss": 0.555,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.15,
145
+ "learning_rate": 3.996922685294587e-05,
146
+ "loss": 0.5142,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.15,
151
+ "learning_rate": 3.9961055389499904e-05,
152
+ "loss": 0.3841,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.16,
157
+ "learning_rate": 3.9951923895399696e-05,
158
+ "loss": 0.3057,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.17,
163
+ "learning_rate": 3.9941832809826136e-05,
164
+ "loss": 0.4327,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.17,
169
+ "learning_rate": 3.993078261811186e-05,
170
+ "loss": 0.3207,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.18,
175
+ "learning_rate": 3.991877385171789e-05,
176
+ "loss": 0.454,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.19,
181
+ "learning_rate": 3.990580708820805e-05,
182
+ "loss": 0.2997,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.19,
187
+ "learning_rate": 3.9891882951221246e-05,
188
+ "loss": 0.3583,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.2,
193
+ "learning_rate": 3.9877002110441424e-05,
194
+ "loss": 0.2823,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.2,
199
+ "learning_rate": 3.986116528156537e-05,
200
+ "loss": 0.2659,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.21,
205
+ "learning_rate": 3.9844373226268305e-05,
206
+ "loss": 0.3158,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.22,
211
+ "learning_rate": 3.982662675216723e-05,
212
+ "loss": 0.2704,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.22,
217
+ "learning_rate": 3.9807926712782115e-05,
218
+ "loss": 0.3642,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.23,
223
+ "learning_rate": 3.978827400749481e-05,
224
+ "loss": 0.3058,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.24,
229
+ "learning_rate": 3.976766958150581e-05,
230
+ "loss": 0.3343,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.24,
235
+ "learning_rate": 3.97461144257888e-05,
236
+ "loss": 0.2987,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.25,
241
+ "learning_rate": 3.972360957704298e-05,
242
+ "loss": 0.2469,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.26,
247
+ "learning_rate": 3.970015611764323e-05,
248
+ "loss": 0.359,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.26,
253
+ "learning_rate": 3.9675755175588006e-05,
254
+ "loss": 0.2903,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.27,
259
+ "learning_rate": 3.9650407924445147e-05,
260
+ "loss": 0.3881,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.27,
265
+ "learning_rate": 3.9624115583295375e-05,
266
+ "loss": 0.2877,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.28,
271
+ "learning_rate": 3.959687941667372e-05,
272
+ "loss": 0.2628,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.29,
277
+ "learning_rate": 3.9568700734508645e-05,
278
+ "loss": 0.2789,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.29,
283
+ "learning_rate": 3.9539580892059086e-05,
284
+ "loss": 0.2164,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.3,
289
+ "learning_rate": 3.950952128984927e-05,
290
+ "loss": 0.217,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.31,
295
+ "learning_rate": 3.9478523373601325e-05,
296
+ "loss": 0.2196,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.31,
301
+ "learning_rate": 3.944658863416575e-05,
302
+ "loss": 0.3036,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.32,
307
+ "learning_rate": 3.941371860744978e-05,
308
+ "loss": 0.2398,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.33,
313
+ "learning_rate": 3.937991487434342e-05,
314
+ "loss": 0.2441,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.33,
319
+ "learning_rate": 3.934517906064348e-05,
320
+ "loss": 0.2922,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.34,
325
+ "learning_rate": 3.930951283697534e-05,
326
+ "loss": 0.3127,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.35,
331
+ "learning_rate": 3.927291791871264e-05,
332
+ "loss": 0.2994,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.35,
337
+ "learning_rate": 3.923539606589473e-05,
338
+ "loss": 0.2534,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.36,
343
+ "learning_rate": 3.919694908314209e-05,
344
+ "loss": 0.2855,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.36,
349
+ "learning_rate": 3.9157578819569455e-05,
350
+ "loss": 0.2889,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.37,
355
+ "learning_rate": 3.9117287168696956e-05,
356
+ "loss": 0.3228,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.38,
361
+ "learning_rate": 3.907607606835899e-05,
362
+ "loss": 0.2197,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.38,
367
+ "learning_rate": 3.903394750061106e-05,
368
+ "loss": 0.3422,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.39,
373
+ "learning_rate": 3.899090349163444e-05,
374
+ "loss": 0.2788,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.4,
379
+ "learning_rate": 3.8946946111638696e-05,
380
+ "loss": 0.3245,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.4,
385
+ "learning_rate": 3.8902077474762155e-05,
386
+ "loss": 0.336,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.41,
391
+ "learning_rate": 3.8856299738970225e-05,
392
+ "loss": 0.2951,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.42,
397
+ "learning_rate": 3.880961510595158e-05,
398
+ "loss": 0.3156,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.42,
403
+ "learning_rate": 3.876202582101229e-05,
404
+ "loss": 0.2534,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.43,
409
+ "learning_rate": 3.8713534172967815e-05,
410
+ "loss": 0.2775,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.43,
415
+ "learning_rate": 3.866414249403295e-05,
416
+ "loss": 0.3381,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.44,
421
+ "learning_rate": 3.861385315970964e-05,
422
+ "loss": 0.2593,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.45,
427
+ "learning_rate": 3.856266858867273e-05,
428
+ "loss": 0.166,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.45,
433
+ "learning_rate": 3.851059124265363e-05,
434
+ "loss": 0.3453,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.46,
439
+ "learning_rate": 3.8457623626321944e-05,
440
+ "loss": 0.2238,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.47,
445
+ "learning_rate": 3.840376828716499e-05,
446
+ "loss": 0.2773,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.47,
451
+ "learning_rate": 3.834902781536527e-05,
452
+ "loss": 0.2777,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.48,
457
+ "learning_rate": 3.8293404843675904e-05,
458
+ "loss": 0.3032,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.49,
463
+ "learning_rate": 3.8236902047294015e-05,
464
+ "loss": 0.2138,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.49,
469
+ "learning_rate": 3.817952214373206e-05,
470
+ "loss": 0.2605,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.5,
475
+ "learning_rate": 3.812126789268712e-05,
476
+ "loss": 0.3205,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.5,
481
+ "learning_rate": 3.806214209590819e-05,
482
+ "loss": 0.27,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.51,
487
+ "learning_rate": 3.80021475970614e-05,
488
+ "loss": 0.2882,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.52,
493
+ "learning_rate": 3.7941287281593284e-05,
494
+ "loss": 0.3081,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.52,
499
+ "learning_rate": 3.787956407659198e-05,
500
+ "loss": 0.3268,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.53,
505
+ "learning_rate": 3.781698095064647e-05,
506
+ "loss": 0.2018,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.54,
511
+ "learning_rate": 3.775354091370376e-05,
512
+ "loss": 0.2624,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.54,
517
+ "learning_rate": 3.7689247016924186e-05,
518
+ "loss": 0.2042,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.55,
523
+ "learning_rate": 3.7624102352534615e-05,
524
+ "loss": 0.3193,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.56,
529
+ "learning_rate": 3.755811005367974e-05,
530
+ "loss": 0.2487,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.56,
535
+ "learning_rate": 3.7491273294271386e-05,
536
+ "loss": 0.1408,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.57,
541
+ "learning_rate": 3.742359528883588e-05,
542
+ "loss": 0.276,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.58,
547
+ "learning_rate": 3.735507929235941e-05,
548
+ "loss": 0.2293,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.58,
553
+ "learning_rate": 3.7285728600131535e-05,
554
+ "loss": 0.2223,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.59,
559
+ "learning_rate": 3.7215546547586596e-05,
560
+ "loss": 0.3011,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.59,
565
+ "learning_rate": 3.7144536510143436e-05,
566
+ "loss": 0.2439,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.6,
571
+ "learning_rate": 3.707270190304294e-05,
572
+ "loss": 0.2061,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.61,
577
+ "learning_rate": 3.7000046181183834e-05,
578
+ "loss": 0.1888,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.61,
583
+ "learning_rate": 3.692657283895651e-05,
584
+ "loss": 0.2698,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.62,
589
+ "learning_rate": 3.6852285410074974e-05,
590
+ "loss": 0.1813,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.63,
595
+ "learning_rate": 3.6777187467406857e-05,
596
+ "loss": 0.3824,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.63,
601
+ "learning_rate": 3.6701282622801626e-05,
602
+ "loss": 0.2891,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.64,
607
+ "learning_rate": 3.662457452691682e-05,
608
+ "loss": 0.1906,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.65,
613
+ "learning_rate": 3.6547066869042524e-05,
614
+ "loss": 0.2127,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.65,
619
+ "learning_rate": 3.6468763376923886e-05,
620
+ "loss": 0.3177,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.66,
625
+ "learning_rate": 3.638966781658187e-05,
626
+ "loss": 0.1738,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.66,
631
+ "learning_rate": 3.630978399213206e-05,
632
+ "loss": 0.1801,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.67,
637
+ "learning_rate": 3.622911574560181e-05,
638
+ "loss": 0.2335,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.68,
643
+ "learning_rate": 3.6147666956745364e-05,
644
+ "loss": 0.2521,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.68,
649
+ "learning_rate": 3.60654415428573e-05,
650
+ "loss": 0.204,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.69,
655
+ "learning_rate": 3.598244345858412e-05,
656
+ "loss": 0.2199,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.7,
661
+ "learning_rate": 3.589867669573404e-05,
662
+ "loss": 0.322,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.7,
667
+ "learning_rate": 3.5814145283085055e-05,
668
+ "loss": 0.2733,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.71,
673
+ "learning_rate": 3.5728853286191075e-05,
674
+ "loss": 0.3102,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.72,
679
+ "learning_rate": 3.56428048071865e-05,
680
+ "loss": 0.2365,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.72,
685
+ "learning_rate": 3.555600398458885e-05,
686
+ "loss": 0.1718,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.73,
691
+ "learning_rate": 3.546845499309976e-05,
692
+ "loss": 0.198,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.73,
697
+ "learning_rate": 3.538016204340418e-05,
698
+ "loss": 0.2557,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.74,
703
+ "learning_rate": 3.529112938196787e-05,
704
+ "loss": 0.1825,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.75,
709
+ "learning_rate": 3.5201361290833165e-05,
710
+ "loss": 0.3099,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.75,
715
+ "learning_rate": 3.511086208741303e-05,
716
+ "loss": 0.3273,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.76,
721
+ "learning_rate": 3.501963612428341e-05,
722
+ "loss": 0.4337,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.77,
727
+ "learning_rate": 3.492768778897388e-05,
728
+ "loss": 0.2754,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.77,
733
+ "learning_rate": 3.483502150375665e-05,
734
+ "loss": 0.2226,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.78,
739
+ "learning_rate": 3.474164172543386e-05,
740
+ "loss": 0.2698,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.79,
745
+ "learning_rate": 3.464755294512325e-05,
746
+ "loss": 0.2,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.79,
751
+ "learning_rate": 3.455275968804212e-05,
752
+ "loss": 0.1865,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.8,
757
+ "learning_rate": 3.445726651328971e-05,
758
+ "loss": 0.2586,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.81,
763
+ "learning_rate": 3.4361078013627945e-05,
764
+ "loss": 0.3064,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.81,
769
+ "learning_rate": 3.426419881526052e-05,
770
+ "loss": 0.21,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.82,
775
+ "learning_rate": 3.4166633577610425e-05,
776
+ "loss": 0.1701,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.82,
781
+ "learning_rate": 3.4068386993095806e-05,
782
+ "loss": 0.2909,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.83,
787
+ "learning_rate": 3.396946378690435e-05,
788
+ "loss": 0.2558,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.84,
793
+ "learning_rate": 3.386986871676597e-05,
794
+ "loss": 0.1833,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.84,
799
+ "learning_rate": 3.3769606572724e-05,
800
+ "loss": 0.184,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.85,
805
+ "learning_rate": 3.366868217690482e-05,
806
+ "loss": 0.2481,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.86,
811
+ "learning_rate": 3.3567100383285925e-05,
812
+ "loss": 0.1628,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.86,
817
+ "learning_rate": 3.346486607746249e-05,
818
+ "loss": 0.1711,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.87,
823
+ "learning_rate": 3.336198417641238e-05,
824
+ "loss": 0.2293,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.88,
829
+ "learning_rate": 3.325845962825966e-05,
830
+ "loss": 0.2515,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.88,
835
+ "learning_rate": 3.315429741203666e-05,
836
+ "loss": 0.1741,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.89,
841
+ "learning_rate": 3.304950253744443e-05,
842
+ "loss": 0.1595,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.89,
847
+ "learning_rate": 3.294408004461188e-05,
848
+ "loss": 0.1889,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.9,
853
+ "learning_rate": 3.283803500385332e-05,
854
+ "loss": 0.2864,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.91,
859
+ "learning_rate": 3.27313725154246e-05,
860
+ "loss": 0.1941,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.91,
865
+ "learning_rate": 3.2624097709277855e-05,
866
+ "loss": 0.2526,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.92,
871
+ "learning_rate": 3.251621574481475e-05,
872
+ "loss": 0.1784,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.93,
877
+ "learning_rate": 3.240773181063834e-05,
878
+ "loss": 0.3217,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.93,
883
+ "learning_rate": 3.229865112430352e-05,
884
+ "loss": 0.2438,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.94,
889
+ "learning_rate": 3.218897893206608e-05,
890
+ "loss": 0.2797,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.95,
895
+ "learning_rate": 3.2078720508630427e-05,
896
+ "loss": 0.2358,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.95,
901
+ "learning_rate": 3.196788115689584e-05,
902
+ "loss": 0.2403,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.96,
907
+ "learning_rate": 3.185646620770146e-05,
908
+ "loss": 0.2295,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.96,
913
+ "learning_rate": 3.1744481019569885e-05,
914
+ "loss": 0.2063,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.97,
919
+ "learning_rate": 3.163193097844949e-05,
920
+ "loss": 0.2654,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.98,
925
+ "learning_rate": 3.1518821497455326e-05,
926
+ "loss": 0.2071,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.98,
931
+ "learning_rate": 3.1405158016608806e-05,
932
+ "loss": 0.2035,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.99,
937
+ "learning_rate": 3.129094600257611e-05,
938
+ "loss": 0.2398,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 1.0,
943
+ "learning_rate": 3.1176190948405194e-05,
944
+ "loss": 0.1623,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 1.0,
949
+ "learning_rate": 3.106089837326161e-05,
950
+ "loss": 0.2313,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 1.01,
955
+ "learning_rate": 3.094507382216312e-05,
956
+ "loss": 0.2687,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 1.02,
961
+ "learning_rate": 3.082872286571295e-05,
962
+ "loss": 0.246,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 1.02,
967
+ "learning_rate": 3.0711851099831885e-05,
968
+ "loss": 0.191,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 1.03,
973
+ "learning_rate": 3.059446414548915e-05,
974
+ "loss": 0.1543,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 1.04,
979
+ "learning_rate": 3.047656764843203e-05,
980
+ "loss": 0.1978,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 1.04,
985
+ "learning_rate": 3.0358167278914387e-05,
986
+ "loss": 0.2698,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 1.05,
991
+ "learning_rate": 3.023926873142391e-05,
992
+ "loss": 0.2351,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 1.05,
997
+ "learning_rate": 3.011987772440825e-05,
998
+ "loss": 0.1925,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 1.06,
1003
+ "learning_rate": 3.0000000000000004e-05,
1004
+ "loss": 0.2246,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 1.07,
1009
+ "learning_rate": 2.9879641323740505e-05,
1010
+ "loss": 0.2093,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 1.07,
1015
+ "learning_rate": 2.9758807484302566e-05,
1016
+ "loss": 0.2332,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 1.08,
1021
+ "learning_rate": 2.963750429321208e-05,
1022
+ "loss": 0.1983,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 1.09,
1027
+ "learning_rate": 2.9515737584568463e-05,
1028
+ "loss": 0.2707,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 1.09,
1033
+ "learning_rate": 2.939351321476412e-05,
1034
+ "loss": 0.2485,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 1.1,
1039
+ "learning_rate": 2.927083706220274e-05,
1040
+ "loss": 0.1947,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 1.11,
1045
+ "learning_rate": 2.9147715027016593e-05,
1046
+ "loss": 0.1949,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 1.11,
1051
+ "learning_rate": 2.902415303078275e-05,
1052
+ "loss": 0.1907,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.12,
1057
+ "learning_rate": 2.8900157016238296e-05,
1058
+ "loss": 0.1801,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.12,
1063
+ "learning_rate": 2.8775732946994508e-05,
1064
+ "loss": 0.2489,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.13,
1069
+ "learning_rate": 2.8650886807250024e-05,
1070
+ "loss": 0.1969,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.14,
1075
+ "learning_rate": 2.8525624601503055e-05,
1076
+ "loss": 0.1724,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.14,
1081
+ "learning_rate": 2.8399952354262566e-05,
1082
+ "loss": 0.1797,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.15,
1087
+ "learning_rate": 2.8273876109758568e-05,
1088
+ "loss": 0.1341,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.16,
1093
+ "learning_rate": 2.8147401931651363e-05,
1094
+ "loss": 0.2223,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.16,
1099
+ "learning_rate": 2.802053590273997e-05,
1100
+ "loss": 0.2221,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.17,
1105
+ "learning_rate": 2.789328412466953e-05,
1106
+ "loss": 0.2019,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.18,
1111
+ "learning_rate": 2.7765652717637873e-05,
1112
+ "loss": 0.1336,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.18,
1117
+ "learning_rate": 2.763764782010116e-05,
1118
+ "loss": 0.2361,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.19,
1123
+ "learning_rate": 2.7509275588478606e-05,
1124
+ "loss": 0.2023,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.19,
1129
+ "learning_rate": 2.738054219685647e-05,
1130
+ "loss": 0.2428,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.2,
1135
+ "learning_rate": 2.725145383669106e-05,
1136
+ "loss": 0.2394,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.21,
1141
+ "learning_rate": 2.712201671651094e-05,
1142
+ "loss": 0.1464,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.21,
1147
+ "learning_rate": 2.699223706161839e-05,
1148
+ "loss": 0.2485,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.22,
1153
+ "learning_rate": 2.6862121113789917e-05,
1154
+ "loss": 0.3039,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.23,
1159
+ "learning_rate": 2.673167513097613e-05,
1160
+ "loss": 0.1387,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.23,
1165
+ "learning_rate": 2.6600905387000716e-05,
1166
+ "loss": 0.2657,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.24,
1171
+ "learning_rate": 2.6469818171258723e-05,
1172
+ "loss": 0.176,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.25,
1177
+ "learning_rate": 2.633841978841406e-05,
1178
+ "loss": 0.1876,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.25,
1183
+ "learning_rate": 2.620671655809627e-05,
1184
+ "loss": 0.1726,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.26,
1189
+ "learning_rate": 2.60747148145966e-05,
1190
+ "loss": 0.2352,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.27,
1195
+ "learning_rate": 2.594242090656335e-05,
1196
+ "loss": 0.254,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.27,
1201
+ "learning_rate": 2.5809841196696504e-05,
1202
+ "loss": 0.2125,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.28,
1207
+ "learning_rate": 2.5676982061441763e-05,
1208
+ "loss": 0.2049,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 1.28,
1213
+ "learning_rate": 2.5543849890683813e-05,
1214
+ "loss": 0.1865,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 1.29,
1219
+ "learning_rate": 2.5410451087439075e-05,
1220
+ "loss": 0.2203,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 1.3,
1225
+ "learning_rate": 2.5276792067547672e-05,
1226
+ "loss": 0.2002,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 1.3,
1231
+ "learning_rate": 2.514287925936492e-05,
1232
+ "loss": 0.1524,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 1.31,
1237
+ "learning_rate": 2.500871910345212e-05,
1238
+ "loss": 0.2059,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 1.32,
1243
+ "learning_rate": 2.4874318052266794e-05,
1244
+ "loss": 0.1885,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 1.32,
1249
+ "learning_rate": 2.473968256985238e-05,
1250
+ "loss": 0.1837,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 1.33,
1255
+ "learning_rate": 2.460481913152734e-05,
1256
+ "loss": 0.1938,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 1.34,
1261
+ "learning_rate": 2.4469734223573703e-05,
1262
+ "loss": 0.1497,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 1.34,
1267
+ "learning_rate": 2.4334434342925133e-05,
1268
+ "loss": 0.2644,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 1.35,
1273
+ "learning_rate": 2.4198925996854422e-05,
1274
+ "loss": 0.1937,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 1.35,
1279
+ "learning_rate": 2.4063215702660564e-05,
1280
+ "loss": 0.2791,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 1.36,
1285
+ "learning_rate": 2.392730998735529e-05,
1286
+ "loss": 0.24,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 1.37,
1291
+ "learning_rate": 2.379121538734912e-05,
1292
+ "loss": 0.1574,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 1.37,
1297
+ "learning_rate": 2.3654938448137062e-05,
1298
+ "loss": 0.1896,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 1.38,
1303
+ "learning_rate": 2.351848572398371e-05,
1304
+ "loss": 0.1865,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 1.39,
1309
+ "learning_rate": 2.338186377760811e-05,
1310
+ "loss": 0.1336,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 1.39,
1315
+ "learning_rate": 2.3245079179868054e-05,
1316
+ "loss": 0.2047,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 1.4,
1321
+ "learning_rate": 2.31081385094441e-05,
1322
+ "loss": 0.31,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 1.41,
1327
+ "learning_rate": 2.297104835252314e-05,
1328
+ "loss": 0.2096,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 1.41,
1333
+ "learning_rate": 2.283381530248165e-05,
1334
+ "loss": 0.2593,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 1.42,
1339
+ "learning_rate": 2.2696445959568577e-05,
1340
+ "loss": 0.1585,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 1.42,
1345
+ "learning_rate": 2.2558946930587907e-05,
1346
+ "loss": 0.1781,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 1.43,
1351
+ "learning_rate": 2.2421324828580877e-05,
1352
+ "loss": 0.1462,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 1.44,
1357
+ "learning_rate": 2.2283586272507975e-05,
1358
+ "loss": 0.1687,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 1.44,
1363
+ "learning_rate": 2.214573788693054e-05,
1364
+ "loss": 0.1716,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 1.45,
1369
+ "learning_rate": 2.2007786301692205e-05,
1370
+ "loss": 0.2694,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 1.46,
1375
+ "learning_rate": 2.18697381516e-05,
1376
+ "loss": 0.1615,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 1.46,
1381
+ "learning_rate": 2.1731600076105264e-05,
1382
+ "loss": 0.1891,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 1.47,
1387
+ "learning_rate": 2.159337871898431e-05,
1388
+ "loss": 0.1321,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 1.48,
1393
+ "learning_rate": 2.145508072801888e-05,
1394
+ "loss": 0.1706,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 1.48,
1399
+ "learning_rate": 2.131671275467647e-05,
1400
+ "loss": 0.2391,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 1.49,
1405
+ "learning_rate": 2.1178281453790358e-05,
1406
+ "loss": 0.1462,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 1.5,
1411
+ "learning_rate": 2.1039793483239607e-05,
1412
+ "loss": 0.1928,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 1.5,
1417
+ "learning_rate": 2.090125550362879e-05,
1418
+ "loss": 0.3621,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 1.51,
1423
+ "learning_rate": 2.0762674177967676e-05,
1424
+ "loss": 0.1987,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 1.51,
1429
+ "learning_rate": 2.0624056171350785e-05,
1430
+ "loss": 0.2071,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 1.52,
1435
+ "learning_rate": 2.0485408150636804e-05,
1436
+ "loss": 0.1817,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 1.53,
1441
+ "learning_rate": 2.0346736784127955e-05,
1442
+ "loss": 0.1615,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 1.53,
1447
+ "learning_rate": 2.0208048741249288e-05,
1448
+ "loss": 0.1521,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 1.54,
1453
+ "learning_rate": 2.006935069222789e-05,
1454
+ "loss": 0.156,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 1.55,
1459
+ "learning_rate": 1.9930649307772114e-05,
1460
+ "loss": 0.2438,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 1.55,
1465
+ "learning_rate": 1.979195125875072e-05,
1466
+ "loss": 0.2432,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.56,
1471
+ "learning_rate": 1.9653263215872048e-05,
1472
+ "loss": 0.1292,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.57,
1477
+ "learning_rate": 1.9514591849363203e-05,
1478
+ "loss": 0.2293,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.57,
1483
+ "learning_rate": 1.9375943828649215e-05,
1484
+ "loss": 0.1932,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.58,
1489
+ "learning_rate": 1.923732582203233e-05,
1490
+ "loss": 0.1508,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.58,
1495
+ "learning_rate": 1.909874449637122e-05,
1496
+ "loss": 0.2317,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.59,
1501
+ "learning_rate": 1.8960206516760396e-05,
1502
+ "loss": 0.218,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.6,
1507
+ "learning_rate": 1.8821718546209646e-05,
1508
+ "loss": 0.1777,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.6,
1513
+ "learning_rate": 1.8683287245323536e-05,
1514
+ "loss": 0.1577,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.61,
1519
+ "learning_rate": 1.8544919271981125e-05,
1520
+ "loss": 0.2977,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.62,
1525
+ "learning_rate": 1.84066212810157e-05,
1526
+ "loss": 0.2277,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.62,
1531
+ "learning_rate": 1.8268399923894736e-05,
1532
+ "loss": 0.1574,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.63,
1537
+ "learning_rate": 1.8130261848399996e-05,
1538
+ "loss": 0.3187,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.64,
1543
+ "learning_rate": 1.7992213698307795e-05,
1544
+ "loss": 0.1758,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.64,
1549
+ "learning_rate": 1.7854262113069468e-05,
1550
+ "loss": 0.2118,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.65,
1555
+ "learning_rate": 1.7716413727492035e-05,
1556
+ "loss": 0.1539,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.65,
1561
+ "learning_rate": 1.757867517141913e-05,
1562
+ "loss": 0.1885,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.66,
1567
+ "learning_rate": 1.7441053069412103e-05,
1568
+ "loss": 0.1915,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.67,
1573
+ "learning_rate": 1.7303554040431426e-05,
1574
+ "loss": 0.1716,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.67,
1579
+ "learning_rate": 1.7166184697518352e-05,
1580
+ "loss": 0.2217,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.68,
1585
+ "learning_rate": 1.7028951647476862e-05,
1586
+ "loss": 0.3266,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.69,
1591
+ "learning_rate": 1.6891861490555906e-05,
1592
+ "loss": 0.2631,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.69,
1597
+ "learning_rate": 1.6754920820131946e-05,
1598
+ "loss": 0.2481,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.7,
1603
+ "learning_rate": 1.6618136222391893e-05,
1604
+ "loss": 0.2521,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.71,
1609
+ "learning_rate": 1.6481514276016297e-05,
1610
+ "loss": 0.2022,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.71,
1615
+ "learning_rate": 1.634506155186295e-05,
1616
+ "loss": 0.2055,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.72,
1621
+ "learning_rate": 1.6208784612650883e-05,
1622
+ "loss": 0.2257,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.73,
1627
+ "learning_rate": 1.6072690012644717e-05,
1628
+ "loss": 0.2634,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.73,
1633
+ "learning_rate": 1.593678429733944e-05,
1634
+ "loss": 0.2195,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.74,
1639
+ "learning_rate": 1.5801074003145585e-05,
1640
+ "loss": 0.2063,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.74,
1645
+ "learning_rate": 1.5665565657074874e-05,
1646
+ "loss": 0.2601,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.75,
1651
+ "learning_rate": 1.5530265776426294e-05,
1652
+ "loss": 0.1633,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.76,
1657
+ "learning_rate": 1.5395180868472662e-05,
1658
+ "loss": 0.2333,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.76,
1663
+ "learning_rate": 1.5260317430147627e-05,
1664
+ "loss": 0.149,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.77,
1669
+ "learning_rate": 1.512568194773322e-05,
1670
+ "loss": 0.2587,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.78,
1675
+ "learning_rate": 1.4991280896547893e-05,
1676
+ "loss": 0.1951,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.78,
1681
+ "learning_rate": 1.4857120740635084e-05,
1682
+ "loss": 0.2757,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.79,
1687
+ "learning_rate": 1.472320793245233e-05,
1688
+ "loss": 0.2321,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.8,
1693
+ "learning_rate": 1.4589548912560932e-05,
1694
+ "loss": 0.2177,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.8,
1699
+ "learning_rate": 1.4456150109316192e-05,
1700
+ "loss": 0.1363,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.81,
1705
+ "learning_rate": 1.4323017938558245e-05,
1706
+ "loss": 0.1428,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.81,
1711
+ "learning_rate": 1.4190158803303498e-05,
1712
+ "loss": 0.2112,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.82,
1717
+ "learning_rate": 1.4057579093436653e-05,
1718
+ "loss": 0.2269,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.83,
1723
+ "learning_rate": 1.3925285185403406e-05,
1724
+ "loss": 0.1712,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.83,
1729
+ "learning_rate": 1.3793283441903737e-05,
1730
+ "loss": 0.1182,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.84,
1735
+ "learning_rate": 1.3661580211585947e-05,
1736
+ "loss": 0.1667,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.85,
1741
+ "learning_rate": 1.3530181828741285e-05,
1742
+ "loss": 0.2887,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.85,
1747
+ "learning_rate": 1.3399094612999291e-05,
1748
+ "loss": 0.1624,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.86,
1753
+ "learning_rate": 1.3268324869023878e-05,
1754
+ "loss": 0.2356,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.87,
1759
+ "learning_rate": 1.313787888621009e-05,
1760
+ "loss": 0.2557,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.87,
1765
+ "learning_rate": 1.3007762938381619e-05,
1766
+ "loss": 0.2203,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.88,
1771
+ "learning_rate": 1.2877983283489062e-05,
1772
+ "loss": 0.3142,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.88,
1777
+ "learning_rate": 1.2748546163308947e-05,
1778
+ "loss": 0.16,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.89,
1783
+ "learning_rate": 1.261945780314354e-05,
1784
+ "loss": 0.1647,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.9,
1789
+ "learning_rate": 1.2490724411521406e-05,
1790
+ "loss": 0.2373,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.9,
1795
+ "learning_rate": 1.2362352179898855e-05,
1796
+ "loss": 0.1701,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.91,
1801
+ "learning_rate": 1.2234347282362129e-05,
1802
+ "loss": 0.1522,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.92,
1807
+ "learning_rate": 1.2106715875330475e-05,
1808
+ "loss": 0.1613,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 1.92,
1813
+ "learning_rate": 1.1979464097260039e-05,
1814
+ "loss": 0.1883,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 1.93,
1819
+ "learning_rate": 1.1852598068348642e-05,
1820
+ "loss": 0.2338,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 1.94,
1825
+ "learning_rate": 1.1726123890241439e-05,
1826
+ "loss": 0.2248,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 1.94,
1831
+ "learning_rate": 1.1600047645737433e-05,
1832
+ "loss": 0.1811,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 1.95,
1837
+ "learning_rate": 1.1474375398496948e-05,
1838
+ "loss": 0.1893,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 1.96,
1843
+ "learning_rate": 1.1349113192749986e-05,
1844
+ "loss": 0.203,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 1.96,
1849
+ "learning_rate": 1.1224267053005504e-05,
1850
+ "loss": 0.1425,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 1.97,
1855
+ "learning_rate": 1.1099842983761712e-05,
1856
+ "loss": 0.1337,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 1.97,
1861
+ "learning_rate": 1.0975846969217258e-05,
1862
+ "loss": 0.1684,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 1.98,
1867
+ "learning_rate": 1.0852284972983415e-05,
1868
+ "loss": 0.165,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 1.99,
1873
+ "learning_rate": 1.0729162937797257e-05,
1874
+ "loss": 0.2462,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 1.99,
1879
+ "learning_rate": 1.0606486785235879e-05,
1880
+ "loss": 0.2298,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 2.0,
1885
+ "learning_rate": 1.0484262415431536e-05,
1886
+ "loss": 0.2047,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 2.01,
1891
+ "learning_rate": 1.0362495706787923e-05,
1892
+ "loss": 0.2365,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 2.01,
1897
+ "learning_rate": 1.0241192515697432e-05,
1898
+ "loss": 0.1738,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 2.02,
1903
+ "learning_rate": 1.0120358676259508e-05,
1904
+ "loss": 0.2467,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 2.03,
1909
+ "learning_rate": 1.0000000000000006e-05,
1910
+ "loss": 0.1459,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 2.03,
1915
+ "learning_rate": 9.880122275591752e-06,
1916
+ "loss": 0.1594,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 2.04,
1921
+ "learning_rate": 9.760731268576095e-06,
1922
+ "loss": 0.1145,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 2.04,
1927
+ "learning_rate": 9.64183272108562e-06,
1928
+ "loss": 0.1485,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 2.05,
1933
+ "learning_rate": 9.523432351567979e-06,
1934
+ "loss": 0.0932,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 2.06,
1939
+ "learning_rate": 9.405535854510863e-06,
1940
+ "loss": 0.1819,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 2.06,
1945
+ "learning_rate": 9.288148900168122e-06,
1946
+ "loss": 0.1534,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 2.07,
1951
+ "learning_rate": 9.171277134287057e-06,
1952
+ "loss": 0.1875,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 2.08,
1957
+ "learning_rate": 9.054926177836878e-06,
1958
+ "loss": 0.1416,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 2.08,
1963
+ "learning_rate": 8.939101626738395e-06,
1964
+ "loss": 0.1717,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 2.09,
1969
+ "learning_rate": 8.823809051594816e-06,
1970
+ "loss": 0.1975,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 2.1,
1975
+ "learning_rate": 8.70905399742389e-06,
1976
+ "loss": 0.1706,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 2.1,
1981
+ "learning_rate": 8.594841983391196e-06,
1982
+ "loss": 0.1869,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 2.11,
1987
+ "learning_rate": 8.481178502544684e-06,
1988
+ "loss": 0.2313,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 2.12,
1993
+ "learning_rate": 8.368069021550516e-06,
1994
+ "loss": 0.1843,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 2.12,
1999
+ "learning_rate": 8.255518980430115e-06,
2000
+ "loss": 0.2359,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 2.13,
2005
+ "learning_rate": 8.143533792298545e-06,
2006
+ "loss": 0.1243,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 2.13,
2011
+ "learning_rate": 8.032118843104164e-06,
2012
+ "loss": 0.1325,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 2.14,
2017
+ "learning_rate": 7.921279491369575e-06,
2018
+ "loss": 0.099,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 2.15,
2023
+ "learning_rate": 7.811021067933919e-06,
2024
+ "loss": 0.2295,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 2.15,
2029
+ "learning_rate": 7.701348875696486e-06,
2030
+ "loss": 0.1494,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 2.16,
2035
+ "learning_rate": 7.59226818936166e-06,
2036
+ "loss": 0.1063,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 2.17,
2041
+ "learning_rate": 7.483784255185249e-06,
2042
+ "loss": 0.1389,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 2.17,
2047
+ "learning_rate": 7.375902290722146e-06,
2048
+ "loss": 0.176,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 2.18,
2053
+ "learning_rate": 7.268627484575406e-06,
2054
+ "loss": 0.142,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 2.19,
2059
+ "learning_rate": 7.161964996146689e-06,
2060
+ "loss": 0.2029,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 2.19,
2065
+ "learning_rate": 7.055919955388122e-06,
2066
+ "loss": 0.1416,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 2.2,
2071
+ "learning_rate": 6.95049746255557e-06,
2072
+ "loss": 0.1515,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 2.2,
2077
+ "learning_rate": 6.845702587963352e-06,
2078
+ "loss": 0.1573,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 2.21,
2083
+ "learning_rate": 6.741540371740347e-06,
2084
+ "loss": 0.2249,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 2.22,
2089
+ "learning_rate": 6.6380158235876335e-06,
2090
+ "loss": 0.2207,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 2.22,
2095
+ "learning_rate": 6.535133922537513e-06,
2096
+ "loss": 0.1194,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 2.23,
2101
+ "learning_rate": 6.4328996167140786e-06,
2102
+ "loss": 0.1655,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 2.24,
2107
+ "learning_rate": 6.331317823095184e-06,
2108
+ "loss": 0.1652,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 2.24,
2113
+ "learning_rate": 6.230393427276e-06,
2114
+ "loss": 0.2378,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 2.25,
2119
+ "learning_rate": 6.130131283234031e-06,
2120
+ "loss": 0.229,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 2.26,
2125
+ "learning_rate": 6.0305362130956504e-06,
2126
+ "loss": 0.1397,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 2.26,
2131
+ "learning_rate": 5.931613006904196e-06,
2132
+ "loss": 0.1139,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 2.27,
2137
+ "learning_rate": 5.8333664223895906e-06,
2138
+ "loss": 0.1611,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 2.27,
2143
+ "learning_rate": 5.735801184739489e-06,
2144
+ "loss": 0.1784,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 2.28,
2149
+ "learning_rate": 5.638921986372064e-06,
2150
+ "loss": 0.2004,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 2.29,
2155
+ "learning_rate": 5.542733486710299e-06,
2156
+ "loss": 0.1553,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 2.29,
2161
+ "learning_rate": 5.447240311957891e-06,
2162
+ "loss": 0.1787,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 2.3,
2167
+ "learning_rate": 5.352447054876755e-06,
2168
+ "loss": 0.1856,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 2.31,
2173
+ "learning_rate": 5.258358274566142e-06,
2174
+ "loss": 0.2069,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 2.31,
2179
+ "learning_rate": 5.164978496243354e-06,
2180
+ "loss": 0.2023,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 2.32,
2185
+ "learning_rate": 5.072312211026125e-06,
2186
+ "loss": 0.1453,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 2.33,
2191
+ "learning_rate": 4.980363875716592e-06,
2192
+ "loss": 0.1377,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 2.33,
2197
+ "learning_rate": 4.889137912586972e-06,
2198
+ "loss": 0.1887,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 2.34,
2203
+ "learning_rate": 4.7986387091668365e-06,
2204
+ "loss": 0.0932,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 2.35,
2209
+ "learning_rate": 4.708870618032133e-06,
2210
+ "loss": 0.1506,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 2.35,
2215
+ "learning_rate": 4.619837956595825e-06,
2216
+ "loss": 0.1293,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 2.36,
2221
+ "learning_rate": 4.531545006900244e-06,
2222
+ "loss": 0.1505,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 2.36,
2227
+ "learning_rate": 4.443996015411151e-06,
2228
+ "loss": 0.1176,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 2.37,
2233
+ "learning_rate": 4.357195192813504e-06,
2234
+ "loss": 0.2187,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 2.38,
2239
+ "learning_rate": 4.271146713808927e-06,
2240
+ "loss": 0.1538,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 2.38,
2245
+ "learning_rate": 4.185854716914952e-06,
2246
+ "loss": 0.2165,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 2.39,
2251
+ "learning_rate": 4.1013233042659606e-06,
2252
+ "loss": 0.1662,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 2.4,
2257
+ "learning_rate": 4.017556541415888e-06,
2258
+ "loss": 0.143,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 2.4,
2263
+ "learning_rate": 3.9345584571427055e-06,
2264
+ "loss": 0.1883,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 2.41,
2269
+ "learning_rate": 3.852333043254639e-06,
2270
+ "loss": 0.1624,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 2.42,
2275
+ "learning_rate": 3.7708842543981928e-06,
2276
+ "loss": 0.1824,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 2.42,
2281
+ "learning_rate": 3.690216007867944e-06,
2282
+ "loss": 0.1933,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 2.43,
2287
+ "learning_rate": 3.6103321834181437e-06,
2288
+ "loss": 0.1557,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 2.43,
2293
+ "learning_rate": 3.5312366230761154e-06,
2294
+ "loss": 0.143,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 2.44,
2299
+ "learning_rate": 3.452933130957481e-06,
2300
+ "loss": 0.1588,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 2.45,
2305
+ "learning_rate": 3.375425473083185e-06,
2306
+ "loss": 0.1964,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 2.45,
2311
+ "learning_rate": 3.2987173771983816e-06,
2312
+ "loss": 0.1688,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 2.46,
2317
+ "learning_rate": 3.2228125325931514e-06,
2318
+ "loss": 0.1837,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 2.47,
2323
+ "learning_rate": 3.1477145899250326e-06,
2324
+ "loss": 0.1463,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 2.47,
2329
+ "learning_rate": 3.073427161043492e-06,
2330
+ "loss": 0.2133,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 2.48,
2335
+ "learning_rate": 2.9999538188161705e-06,
2336
+ "loss": 0.1345,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 2.49,
2341
+ "learning_rate": 2.927298096957063e-06,
2342
+ "loss": 0.2226,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 2.49,
2347
+ "learning_rate": 2.8554634898565668e-06,
2348
+ "loss": 0.1664,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 2.5,
2353
+ "learning_rate": 2.784453452413405e-06,
2354
+ "loss": 0.1388,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 2.5,
2359
+ "learning_rate": 2.714271399868473e-06,
2360
+ "loss": 0.2065,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 2.51,
2365
+ "learning_rate": 2.6449207076405857e-06,
2366
+ "loss": 0.1353,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 2.52,
2371
+ "learning_rate": 2.57640471116412e-06,
2372
+ "loss": 0.1601,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 2.52,
2377
+ "learning_rate": 2.508726705728617e-06,
2378
+ "loss": 0.2478,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 2.53,
2383
+ "learning_rate": 2.441889946320266e-06,
2384
+ "loss": 0.1515,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 2.54,
2389
+ "learning_rate": 2.3758976474653904e-06,
2390
+ "loss": 0.11,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 2.54,
2395
+ "learning_rate": 2.310752983075819e-06,
2396
+ "loss": 0.179,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 2.55,
2401
+ "learning_rate": 2.2464590862962443e-06,
2402
+ "loss": 0.1746,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 2.56,
2407
+ "learning_rate": 2.1830190493535385e-06,
2408
+ "loss": 0.1632,
2409
+ "step": 400
2410
+ }
2411
+ ],
2412
+ "logging_steps": 1.0,
2413
+ "max_steps": 468,
2414
+ "num_input_tokens_seen": 0,
2415
+ "num_train_epochs": 3,
2416
+ "save_steps": 200,
2417
+ "total_flos": 3.6382398814964637e+21,
2418
+ "train_batch_size": 8,
2419
+ "trial_name": null,
2420
+ "trial_params": null
2421
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d3d5c3efb7261d08cb5ce5aa813634f864a1c2a7db3124b079c96a51cffb73
3
+ size 6264
checkpoint-400/zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
config.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/workspace/pretrained/InternVL2-8B",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "llm_config": {
16
+ "_name_or_path": "internlm/internlm2_5-7b-chat",
17
+ "add_cross_attention": false,
18
+ "architectures": [
19
+ "InternLM2ForCausalLM"
20
+ ],
21
+ "attn_implementation": "flash_attention_2",
22
+ "auto_map": {
23
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
24
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
25
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
26
+ },
27
+ "bad_words_ids": null,
28
+ "begin_suppress_tokens": null,
29
+ "bias": false,
30
+ "bos_token_id": 1,
31
+ "chunk_size_feed_forward": 0,
32
+ "cross_attention_hidden_size": null,
33
+ "decoder_start_token_id": null,
34
+ "diversity_penalty": 0.0,
35
+ "do_sample": false,
36
+ "early_stopping": false,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": 2,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "hidden_act": "silu",
44
+ "hidden_size": 4096,
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 14336,
51
+ "is_decoder": false,
52
+ "is_encoder_decoder": false,
53
+ "label2id": {
54
+ "LABEL_0": 0,
55
+ "LABEL_1": 1
56
+ },
57
+ "length_penalty": 1.0,
58
+ "max_length": 20,
59
+ "max_position_embeddings": 32768,
60
+ "min_length": 0,
61
+ "model_type": "internlm2",
62
+ "no_repeat_ngram_size": 0,
63
+ "num_attention_heads": 32,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_hidden_layers": 32,
67
+ "num_key_value_heads": 8,
68
+ "num_return_sequences": 1,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_scores": false,
72
+ "pad_token_id": 2,
73
+ "prefix": null,
74
+ "pretraining_tp": 1,
75
+ "problem_type": null,
76
+ "pruned_heads": {},
77
+ "remove_invalid_values": false,
78
+ "repetition_penalty": 1.0,
79
+ "return_dict": true,
80
+ "return_dict_in_generate": false,
81
+ "rms_norm_eps": 1e-05,
82
+ "rope_scaling": {
83
+ "factor": 2.0,
84
+ "type": "dynamic"
85
+ },
86
+ "rope_theta": 1000000,
87
+ "sep_token_id": null,
88
+ "suppress_tokens": null,
89
+ "task_specific_params": null,
90
+ "temperature": 1.0,
91
+ "tf_legacy_loss": false,
92
+ "tie_encoder_decoder": false,
93
+ "tie_word_embeddings": false,
94
+ "tokenizer_class": null,
95
+ "top_k": 50,
96
+ "top_p": 1.0,
97
+ "torch_dtype": "bfloat16",
98
+ "torchscript": false,
99
+ "transformers_version": "4.37.2",
100
+ "typical_p": 1.0,
101
+ "use_bfloat16": true,
102
+ "use_cache": false,
103
+ "vocab_size": 92553
104
+ },
105
+ "max_dynamic_patch": 6,
106
+ "min_dynamic_patch": 1,
107
+ "model_type": "internvl_chat",
108
+ "pad2square": false,
109
+ "ps_version": "v2",
110
+ "select_layer": -1,
111
+ "template": "internlm2-chat",
112
+ "torch_dtype": "bfloat16",
113
+ "transformers_version": null,
114
+ "use_backbone_lora": 0,
115
+ "use_llm_lora": 16,
116
+ "use_thumbnail": true,
117
+ "vision_config": {
118
+ "_name_or_path": "",
119
+ "add_cross_attention": false,
120
+ "architectures": [
121
+ "InternVisionModel"
122
+ ],
123
+ "attention_dropout": 0.0,
124
+ "bad_words_ids": null,
125
+ "begin_suppress_tokens": null,
126
+ "bos_token_id": null,
127
+ "chunk_size_feed_forward": 0,
128
+ "cross_attention_hidden_size": null,
129
+ "decoder_start_token_id": null,
130
+ "diversity_penalty": 0.0,
131
+ "do_sample": false,
132
+ "drop_path_rate": 0.0,
133
+ "dropout": 0.0,
134
+ "early_stopping": false,
135
+ "encoder_no_repeat_ngram_size": 0,
136
+ "eos_token_id": null,
137
+ "exponential_decay_length_penalty": null,
138
+ "finetuning_task": null,
139
+ "forced_bos_token_id": null,
140
+ "forced_eos_token_id": null,
141
+ "hidden_act": "gelu",
142
+ "hidden_size": 1024,
143
+ "id2label": {
144
+ "0": "LABEL_0",
145
+ "1": "LABEL_1"
146
+ },
147
+ "image_size": 448,
148
+ "initializer_factor": 1.0,
149
+ "initializer_range": 0.02,
150
+ "intermediate_size": 4096,
151
+ "is_decoder": false,
152
+ "is_encoder_decoder": false,
153
+ "label2id": {
154
+ "LABEL_0": 0,
155
+ "LABEL_1": 1
156
+ },
157
+ "layer_norm_eps": 1e-06,
158
+ "length_penalty": 1.0,
159
+ "max_length": 20,
160
+ "min_length": 0,
161
+ "model_type": "intern_vit_6b",
162
+ "no_repeat_ngram_size": 0,
163
+ "norm_type": "layer_norm",
164
+ "num_attention_heads": 16,
165
+ "num_beam_groups": 1,
166
+ "num_beams": 1,
167
+ "num_channels": 3,
168
+ "num_hidden_layers": 24,
169
+ "num_return_sequences": 1,
170
+ "output_attentions": false,
171
+ "output_hidden_states": false,
172
+ "output_scores": false,
173
+ "pad_token_id": null,
174
+ "patch_size": 14,
175
+ "prefix": null,
176
+ "problem_type": null,
177
+ "pruned_heads": {},
178
+ "qk_normalization": false,
179
+ "qkv_bias": true,
180
+ "remove_invalid_values": false,
181
+ "repetition_penalty": 1.0,
182
+ "return_dict": true,
183
+ "return_dict_in_generate": false,
184
+ "sep_token_id": null,
185
+ "suppress_tokens": null,
186
+ "task_specific_params": null,
187
+ "temperature": 1.0,
188
+ "tf_legacy_loss": false,
189
+ "tie_encoder_decoder": false,
190
+ "tie_word_embeddings": true,
191
+ "tokenizer_class": null,
192
+ "top_k": 50,
193
+ "top_p": 1.0,
194
+ "torch_dtype": "bfloat16",
195
+ "torchscript": false,
196
+ "transformers_version": "4.37.2",
197
+ "typical_p": 1.0,
198
+ "use_bfloat16": true,
199
+ "use_flash_attn": true
200
+ }
201
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 92542,
5
+ 92543
6
+ ],
7
+ "transformers_version": "4.37.2"
8
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41747129636b1ae2dfd32f0f1078e7587074b837fdd41b87704ab384bdb2de0d
3
+ size 4959423416
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d308b0b46770c665bc3bf9d96fd7cb853d1bb3f6f508d5398ee7974ac6266d96
3
+ size 4942476624
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d404941ccdb3af2610824f6674a0439c9805394c5c42df858b829b8eb28003
3
+ size 4942476664
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703352642efab0c541b7d2e198889010e0259971bf2451c44c46dc076d158eff
3
+ size 1381978232
model.safetensors.index.json ADDED
@@ -0,0 +1,900 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16226228224
4
+ },
5
+ "weight_map": {
6
+ "language_model.base_model.model.model.layers.0.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.base_model.model.model.layers.0.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.base_model.model.model.layers.0.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.base_model.model.model.layers.0.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.base_model.model.model.layers.0.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.base_model.model.model.layers.0.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.base_model.model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.base_model.model.model.layers.0.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.base_model.model.model.layers.0.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.base_model.model.model.layers.0.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.base_model.model.model.layers.0.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.base_model.model.model.layers.0.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.base_model.model.model.layers.0.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.base_model.model.model.layers.0.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.base_model.model.model.layers.0.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.base_model.model.model.layers.0.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.base_model.model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.base_model.model.model.layers.1.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.base_model.model.model.layers.1.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.base_model.model.model.layers.1.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.base_model.model.model.layers.1.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.base_model.model.model.layers.1.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.base_model.model.model.layers.1.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
29
+ "language_model.base_model.model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
30
+ "language_model.base_model.model.model.layers.1.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
31
+ "language_model.base_model.model.model.layers.1.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
32
+ "language_model.base_model.model.model.layers.1.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
33
+ "language_model.base_model.model.model.layers.1.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
34
+ "language_model.base_model.model.model.layers.1.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
35
+ "language_model.base_model.model.model.layers.1.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
36
+ "language_model.base_model.model.model.layers.1.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
37
+ "language_model.base_model.model.model.layers.1.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
38
+ "language_model.base_model.model.model.layers.1.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
39
+ "language_model.base_model.model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
40
+ "language_model.base_model.model.model.layers.10.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.base_model.model.model.layers.10.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.base_model.model.model.layers.10.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.base_model.model.model.layers.10.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.base_model.model.model.layers.10.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.base_model.model.model.layers.10.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.base_model.model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.base_model.model.model.layers.10.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.base_model.model.model.layers.10.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.base_model.model.model.layers.10.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.base_model.model.model.layers.10.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.base_model.model.model.layers.10.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.base_model.model.model.layers.10.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.base_model.model.model.layers.10.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.base_model.model.model.layers.10.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.base_model.model.model.layers.10.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.base_model.model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.base_model.model.model.layers.11.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.base_model.model.model.layers.11.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.base_model.model.model.layers.11.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.base_model.model.model.layers.11.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.base_model.model.model.layers.11.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.base_model.model.model.layers.11.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.base_model.model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.base_model.model.model.layers.11.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.base_model.model.model.layers.11.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.base_model.model.model.layers.11.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.base_model.model.model.layers.11.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.base_model.model.model.layers.11.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.base_model.model.model.layers.11.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.base_model.model.model.layers.11.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.base_model.model.model.layers.11.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.base_model.model.model.layers.11.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.base_model.model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.base_model.model.model.layers.12.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.base_model.model.model.layers.12.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.base_model.model.model.layers.12.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.base_model.model.model.layers.12.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.base_model.model.model.layers.12.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.base_model.model.model.layers.12.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.base_model.model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.base_model.model.model.layers.12.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.base_model.model.model.layers.12.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.base_model.model.model.layers.12.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.base_model.model.model.layers.12.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.base_model.model.model.layers.12.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.base_model.model.model.layers.12.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.base_model.model.model.layers.12.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.base_model.model.model.layers.12.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.base_model.model.model.layers.12.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.base_model.model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.base_model.model.model.layers.13.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.base_model.model.model.layers.13.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.base_model.model.model.layers.13.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.base_model.model.model.layers.13.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.base_model.model.model.layers.13.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.base_model.model.model.layers.13.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.base_model.model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.base_model.model.model.layers.13.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.base_model.model.model.layers.13.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.base_model.model.model.layers.13.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.base_model.model.model.layers.13.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.base_model.model.model.layers.13.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.base_model.model.model.layers.13.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.base_model.model.model.layers.13.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.base_model.model.model.layers.13.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.base_model.model.model.layers.13.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.base_model.model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.base_model.model.model.layers.14.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.base_model.model.model.layers.14.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.base_model.model.model.layers.14.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.base_model.model.model.layers.14.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.base_model.model.model.layers.14.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.base_model.model.model.layers.14.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.base_model.model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.base_model.model.model.layers.14.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.base_model.model.model.layers.14.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.base_model.model.model.layers.14.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
118
+ "language_model.base_model.model.model.layers.14.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
119
+ "language_model.base_model.model.model.layers.14.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
120
+ "language_model.base_model.model.model.layers.14.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
121
+ "language_model.base_model.model.model.layers.14.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
122
+ "language_model.base_model.model.model.layers.14.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
123
+ "language_model.base_model.model.model.layers.14.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
124
+ "language_model.base_model.model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
125
+ "language_model.base_model.model.model.layers.15.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
126
+ "language_model.base_model.model.model.layers.15.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
127
+ "language_model.base_model.model.model.layers.15.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
128
+ "language_model.base_model.model.model.layers.15.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
129
+ "language_model.base_model.model.model.layers.15.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
130
+ "language_model.base_model.model.model.layers.15.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
131
+ "language_model.base_model.model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
132
+ "language_model.base_model.model.model.layers.15.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
133
+ "language_model.base_model.model.model.layers.15.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
134
+ "language_model.base_model.model.model.layers.15.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
135
+ "language_model.base_model.model.model.layers.15.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
136
+ "language_model.base_model.model.model.layers.15.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
137
+ "language_model.base_model.model.model.layers.15.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
138
+ "language_model.base_model.model.model.layers.15.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
139
+ "language_model.base_model.model.model.layers.15.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
140
+ "language_model.base_model.model.model.layers.15.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
141
+ "language_model.base_model.model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
142
+ "language_model.base_model.model.model.layers.16.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
143
+ "language_model.base_model.model.model.layers.16.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
144
+ "language_model.base_model.model.model.layers.16.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
145
+ "language_model.base_model.model.model.layers.16.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
146
+ "language_model.base_model.model.model.layers.16.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
147
+ "language_model.base_model.model.model.layers.16.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
148
+ "language_model.base_model.model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
149
+ "language_model.base_model.model.model.layers.16.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
150
+ "language_model.base_model.model.model.layers.16.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
151
+ "language_model.base_model.model.model.layers.16.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
152
+ "language_model.base_model.model.model.layers.16.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
153
+ "language_model.base_model.model.model.layers.16.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
154
+ "language_model.base_model.model.model.layers.16.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
155
+ "language_model.base_model.model.model.layers.16.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
156
+ "language_model.base_model.model.model.layers.16.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
157
+ "language_model.base_model.model.model.layers.16.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
158
+ "language_model.base_model.model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
159
+ "language_model.base_model.model.model.layers.17.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
160
+ "language_model.base_model.model.model.layers.17.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
161
+ "language_model.base_model.model.model.layers.17.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
162
+ "language_model.base_model.model.model.layers.17.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
163
+ "language_model.base_model.model.model.layers.17.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
164
+ "language_model.base_model.model.model.layers.17.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
165
+ "language_model.base_model.model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
166
+ "language_model.base_model.model.model.layers.17.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
167
+ "language_model.base_model.model.model.layers.17.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
168
+ "language_model.base_model.model.model.layers.17.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
169
+ "language_model.base_model.model.model.layers.17.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
170
+ "language_model.base_model.model.model.layers.17.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
171
+ "language_model.base_model.model.model.layers.17.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
172
+ "language_model.base_model.model.model.layers.17.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
173
+ "language_model.base_model.model.model.layers.17.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
174
+ "language_model.base_model.model.model.layers.17.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
175
+ "language_model.base_model.model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
176
+ "language_model.base_model.model.model.layers.18.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
177
+ "language_model.base_model.model.model.layers.18.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
178
+ "language_model.base_model.model.model.layers.18.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
179
+ "language_model.base_model.model.model.layers.18.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
180
+ "language_model.base_model.model.model.layers.18.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
181
+ "language_model.base_model.model.model.layers.18.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
182
+ "language_model.base_model.model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
183
+ "language_model.base_model.model.model.layers.18.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
184
+ "language_model.base_model.model.model.layers.18.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
185
+ "language_model.base_model.model.model.layers.18.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
186
+ "language_model.base_model.model.model.layers.18.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
187
+ "language_model.base_model.model.model.layers.18.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
188
+ "language_model.base_model.model.model.layers.18.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
189
+ "language_model.base_model.model.model.layers.18.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
190
+ "language_model.base_model.model.model.layers.18.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
191
+ "language_model.base_model.model.model.layers.18.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
192
+ "language_model.base_model.model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
193
+ "language_model.base_model.model.model.layers.19.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
194
+ "language_model.base_model.model.model.layers.19.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
195
+ "language_model.base_model.model.model.layers.19.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
196
+ "language_model.base_model.model.model.layers.19.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
197
+ "language_model.base_model.model.model.layers.19.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
198
+ "language_model.base_model.model.model.layers.19.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
199
+ "language_model.base_model.model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.base_model.model.model.layers.19.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
201
+ "language_model.base_model.model.model.layers.19.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
202
+ "language_model.base_model.model.model.layers.19.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
203
+ "language_model.base_model.model.model.layers.19.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.base_model.model.model.layers.19.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.base_model.model.model.layers.19.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.base_model.model.model.layers.19.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.base_model.model.model.layers.19.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.base_model.model.model.layers.19.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.base_model.model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.base_model.model.model.layers.2.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
211
+ "language_model.base_model.model.model.layers.2.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.base_model.model.model.layers.2.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
213
+ "language_model.base_model.model.model.layers.2.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.base_model.model.model.layers.2.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
215
+ "language_model.base_model.model.model.layers.2.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.base_model.model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.base_model.model.model.layers.2.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.base_model.model.model.layers.2.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
219
+ "language_model.base_model.model.model.layers.2.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
220
+ "language_model.base_model.model.model.layers.2.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
221
+ "language_model.base_model.model.model.layers.2.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
222
+ "language_model.base_model.model.model.layers.2.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
223
+ "language_model.base_model.model.model.layers.2.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
224
+ "language_model.base_model.model.model.layers.2.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
225
+ "language_model.base_model.model.model.layers.2.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
226
+ "language_model.base_model.model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
227
+ "language_model.base_model.model.model.layers.20.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.base_model.model.model.layers.20.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.base_model.model.model.layers.20.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.base_model.model.model.layers.20.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.base_model.model.model.layers.20.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.base_model.model.model.layers.20.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.base_model.model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.base_model.model.model.layers.20.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
235
+ "language_model.base_model.model.model.layers.20.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
236
+ "language_model.base_model.model.model.layers.20.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.base_model.model.model.layers.20.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.base_model.model.model.layers.20.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.base_model.model.model.layers.20.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.base_model.model.model.layers.20.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.base_model.model.model.layers.20.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.base_model.model.model.layers.20.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.base_model.model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.base_model.model.model.layers.21.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
245
+ "language_model.base_model.model.model.layers.21.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
246
+ "language_model.base_model.model.model.layers.21.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
247
+ "language_model.base_model.model.model.layers.21.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
248
+ "language_model.base_model.model.model.layers.21.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
249
+ "language_model.base_model.model.model.layers.21.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
250
+ "language_model.base_model.model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
251
+ "language_model.base_model.model.model.layers.21.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
252
+ "language_model.base_model.model.model.layers.21.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
253
+ "language_model.base_model.model.model.layers.21.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
254
+ "language_model.base_model.model.model.layers.21.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
255
+ "language_model.base_model.model.model.layers.21.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
256
+ "language_model.base_model.model.model.layers.21.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
257
+ "language_model.base_model.model.model.layers.21.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
258
+ "language_model.base_model.model.model.layers.21.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
259
+ "language_model.base_model.model.model.layers.21.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
260
+ "language_model.base_model.model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
261
+ "language_model.base_model.model.model.layers.22.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
262
+ "language_model.base_model.model.model.layers.22.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
263
+ "language_model.base_model.model.model.layers.22.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
264
+ "language_model.base_model.model.model.layers.22.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
265
+ "language_model.base_model.model.model.layers.22.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
266
+ "language_model.base_model.model.model.layers.22.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
267
+ "language_model.base_model.model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
268
+ "language_model.base_model.model.model.layers.22.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
269
+ "language_model.base_model.model.model.layers.22.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
270
+ "language_model.base_model.model.model.layers.22.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
271
+ "language_model.base_model.model.model.layers.22.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
272
+ "language_model.base_model.model.model.layers.22.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
273
+ "language_model.base_model.model.model.layers.22.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
274
+ "language_model.base_model.model.model.layers.22.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
275
+ "language_model.base_model.model.model.layers.22.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
276
+ "language_model.base_model.model.model.layers.22.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
277
+ "language_model.base_model.model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
278
+ "language_model.base_model.model.model.layers.23.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
279
+ "language_model.base_model.model.model.layers.23.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
280
+ "language_model.base_model.model.model.layers.23.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
281
+ "language_model.base_model.model.model.layers.23.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
282
+ "language_model.base_model.model.model.layers.23.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
283
+ "language_model.base_model.model.model.layers.23.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
284
+ "language_model.base_model.model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
285
+ "language_model.base_model.model.model.layers.23.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
286
+ "language_model.base_model.model.model.layers.23.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
287
+ "language_model.base_model.model.model.layers.23.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
288
+ "language_model.base_model.model.model.layers.23.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
289
+ "language_model.base_model.model.model.layers.23.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
290
+ "language_model.base_model.model.model.layers.23.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
291
+ "language_model.base_model.model.model.layers.23.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
292
+ "language_model.base_model.model.model.layers.23.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
293
+ "language_model.base_model.model.model.layers.23.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
294
+ "language_model.base_model.model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
295
+ "language_model.base_model.model.model.layers.24.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
296
+ "language_model.base_model.model.model.layers.24.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
297
+ "language_model.base_model.model.model.layers.24.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
298
+ "language_model.base_model.model.model.layers.24.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
299
+ "language_model.base_model.model.model.layers.24.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
300
+ "language_model.base_model.model.model.layers.24.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
301
+ "language_model.base_model.model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
302
+ "language_model.base_model.model.model.layers.24.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
303
+ "language_model.base_model.model.model.layers.24.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
304
+ "language_model.base_model.model.model.layers.24.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
305
+ "language_model.base_model.model.model.layers.24.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
306
+ "language_model.base_model.model.model.layers.24.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
307
+ "language_model.base_model.model.model.layers.24.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
308
+ "language_model.base_model.model.model.layers.24.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
309
+ "language_model.base_model.model.model.layers.24.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
310
+ "language_model.base_model.model.model.layers.24.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
311
+ "language_model.base_model.model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
312
+ "language_model.base_model.model.model.layers.25.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
313
+ "language_model.base_model.model.model.layers.25.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
314
+ "language_model.base_model.model.model.layers.25.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
315
+ "language_model.base_model.model.model.layers.25.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
316
+ "language_model.base_model.model.model.layers.25.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
317
+ "language_model.base_model.model.model.layers.25.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
318
+ "language_model.base_model.model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
319
+ "language_model.base_model.model.model.layers.25.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
320
+ "language_model.base_model.model.model.layers.25.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
321
+ "language_model.base_model.model.model.layers.25.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
322
+ "language_model.base_model.model.model.layers.25.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
323
+ "language_model.base_model.model.model.layers.25.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
324
+ "language_model.base_model.model.model.layers.25.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
325
+ "language_model.base_model.model.model.layers.25.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
326
+ "language_model.base_model.model.model.layers.25.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
327
+ "language_model.base_model.model.model.layers.25.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
328
+ "language_model.base_model.model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
329
+ "language_model.base_model.model.model.layers.26.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
330
+ "language_model.base_model.model.model.layers.26.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
331
+ "language_model.base_model.model.model.layers.26.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
332
+ "language_model.base_model.model.model.layers.26.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
333
+ "language_model.base_model.model.model.layers.26.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
334
+ "language_model.base_model.model.model.layers.26.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
335
+ "language_model.base_model.model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
336
+ "language_model.base_model.model.model.layers.26.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
337
+ "language_model.base_model.model.model.layers.26.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
338
+ "language_model.base_model.model.model.layers.26.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
339
+ "language_model.base_model.model.model.layers.26.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
340
+ "language_model.base_model.model.model.layers.26.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
341
+ "language_model.base_model.model.model.layers.26.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
342
+ "language_model.base_model.model.model.layers.26.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
343
+ "language_model.base_model.model.model.layers.26.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
344
+ "language_model.base_model.model.model.layers.26.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
345
+ "language_model.base_model.model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
346
+ "language_model.base_model.model.model.layers.27.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
347
+ "language_model.base_model.model.model.layers.27.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
348
+ "language_model.base_model.model.model.layers.27.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
349
+ "language_model.base_model.model.model.layers.27.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
350
+ "language_model.base_model.model.model.layers.27.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
351
+ "language_model.base_model.model.model.layers.27.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
352
+ "language_model.base_model.model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
353
+ "language_model.base_model.model.model.layers.27.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
354
+ "language_model.base_model.model.model.layers.27.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
355
+ "language_model.base_model.model.model.layers.27.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
356
+ "language_model.base_model.model.model.layers.27.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
357
+ "language_model.base_model.model.model.layers.27.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
358
+ "language_model.base_model.model.model.layers.27.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
359
+ "language_model.base_model.model.model.layers.27.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
360
+ "language_model.base_model.model.model.layers.27.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
361
+ "language_model.base_model.model.model.layers.27.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
362
+ "language_model.base_model.model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
363
+ "language_model.base_model.model.model.layers.28.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
364
+ "language_model.base_model.model.model.layers.28.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
365
+ "language_model.base_model.model.model.layers.28.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
366
+ "language_model.base_model.model.model.layers.28.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
367
+ "language_model.base_model.model.model.layers.28.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
368
+ "language_model.base_model.model.model.layers.28.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
369
+ "language_model.base_model.model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
370
+ "language_model.base_model.model.model.layers.28.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
371
+ "language_model.base_model.model.model.layers.28.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
372
+ "language_model.base_model.model.model.layers.28.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
373
+ "language_model.base_model.model.model.layers.28.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
374
+ "language_model.base_model.model.model.layers.28.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
375
+ "language_model.base_model.model.model.layers.28.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
376
+ "language_model.base_model.model.model.layers.28.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
377
+ "language_model.base_model.model.model.layers.28.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
378
+ "language_model.base_model.model.model.layers.28.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
379
+ "language_model.base_model.model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
380
+ "language_model.base_model.model.model.layers.29.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
381
+ "language_model.base_model.model.model.layers.29.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
382
+ "language_model.base_model.model.model.layers.29.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
383
+ "language_model.base_model.model.model.layers.29.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
384
+ "language_model.base_model.model.model.layers.29.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
385
+ "language_model.base_model.model.model.layers.29.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
386
+ "language_model.base_model.model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
387
+ "language_model.base_model.model.model.layers.29.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
388
+ "language_model.base_model.model.model.layers.29.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
389
+ "language_model.base_model.model.model.layers.29.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
390
+ "language_model.base_model.model.model.layers.29.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
391
+ "language_model.base_model.model.model.layers.29.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
392
+ "language_model.base_model.model.model.layers.29.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
393
+ "language_model.base_model.model.model.layers.29.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
394
+ "language_model.base_model.model.model.layers.29.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
395
+ "language_model.base_model.model.model.layers.29.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
396
+ "language_model.base_model.model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
397
+ "language_model.base_model.model.model.layers.3.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
398
+ "language_model.base_model.model.model.layers.3.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
399
+ "language_model.base_model.model.model.layers.3.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
400
+ "language_model.base_model.model.model.layers.3.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
401
+ "language_model.base_model.model.model.layers.3.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
402
+ "language_model.base_model.model.model.layers.3.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
403
+ "language_model.base_model.model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
404
+ "language_model.base_model.model.model.layers.3.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
405
+ "language_model.base_model.model.model.layers.3.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
406
+ "language_model.base_model.model.model.layers.3.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
407
+ "language_model.base_model.model.model.layers.3.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
408
+ "language_model.base_model.model.model.layers.3.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
409
+ "language_model.base_model.model.model.layers.3.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
410
+ "language_model.base_model.model.model.layers.3.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
411
+ "language_model.base_model.model.model.layers.3.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
412
+ "language_model.base_model.model.model.layers.3.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
413
+ "language_model.base_model.model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
414
+ "language_model.base_model.model.model.layers.30.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
415
+ "language_model.base_model.model.model.layers.30.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
416
+ "language_model.base_model.model.model.layers.30.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
417
+ "language_model.base_model.model.model.layers.30.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
418
+ "language_model.base_model.model.model.layers.30.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
419
+ "language_model.base_model.model.model.layers.30.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
420
+ "language_model.base_model.model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
421
+ "language_model.base_model.model.model.layers.30.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
422
+ "language_model.base_model.model.model.layers.30.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
423
+ "language_model.base_model.model.model.layers.30.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
424
+ "language_model.base_model.model.model.layers.30.feed_forward.w2.base_layer.weight": "model-00004-of-00004.safetensors",
425
+ "language_model.base_model.model.model.layers.30.feed_forward.w2.lora_A.default.weight": "model-00004-of-00004.safetensors",
426
+ "language_model.base_model.model.model.layers.30.feed_forward.w2.lora_B.default.weight": "model-00004-of-00004.safetensors",
427
+ "language_model.base_model.model.model.layers.30.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
428
+ "language_model.base_model.model.model.layers.30.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
429
+ "language_model.base_model.model.model.layers.30.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
430
+ "language_model.base_model.model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
431
+ "language_model.base_model.model.model.layers.31.attention.wo.base_layer.weight": "model-00004-of-00004.safetensors",
432
+ "language_model.base_model.model.model.layers.31.attention.wo.lora_A.default.weight": "model-00004-of-00004.safetensors",
433
+ "language_model.base_model.model.model.layers.31.attention.wo.lora_B.default.weight": "model-00004-of-00004.safetensors",
434
+ "language_model.base_model.model.model.layers.31.attention.wqkv.base_layer.weight": "model-00004-of-00004.safetensors",
435
+ "language_model.base_model.model.model.layers.31.attention.wqkv.lora_A.default.weight": "model-00004-of-00004.safetensors",
436
+ "language_model.base_model.model.model.layers.31.attention.wqkv.lora_B.default.weight": "model-00004-of-00004.safetensors",
437
+ "language_model.base_model.model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
438
+ "language_model.base_model.model.model.layers.31.feed_forward.w1.base_layer.weight": "model-00004-of-00004.safetensors",
439
+ "language_model.base_model.model.model.layers.31.feed_forward.w1.lora_A.default.weight": "model-00004-of-00004.safetensors",
440
+ "language_model.base_model.model.model.layers.31.feed_forward.w1.lora_B.default.weight": "model-00004-of-00004.safetensors",
441
+ "language_model.base_model.model.model.layers.31.feed_forward.w2.base_layer.weight": "model-00004-of-00004.safetensors",
442
+ "language_model.base_model.model.model.layers.31.feed_forward.w2.lora_A.default.weight": "model-00004-of-00004.safetensors",
443
+ "language_model.base_model.model.model.layers.31.feed_forward.w2.lora_B.default.weight": "model-00004-of-00004.safetensors",
444
+ "language_model.base_model.model.model.layers.31.feed_forward.w3.base_layer.weight": "model-00004-of-00004.safetensors",
445
+ "language_model.base_model.model.model.layers.31.feed_forward.w3.lora_A.default.weight": "model-00004-of-00004.safetensors",
446
+ "language_model.base_model.model.model.layers.31.feed_forward.w3.lora_B.default.weight": "model-00004-of-00004.safetensors",
447
+ "language_model.base_model.model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
448
+ "language_model.base_model.model.model.layers.4.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
449
+ "language_model.base_model.model.model.layers.4.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
450
+ "language_model.base_model.model.model.layers.4.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
451
+ "language_model.base_model.model.model.layers.4.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
452
+ "language_model.base_model.model.model.layers.4.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
453
+ "language_model.base_model.model.model.layers.4.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
454
+ "language_model.base_model.model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
455
+ "language_model.base_model.model.model.layers.4.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
456
+ "language_model.base_model.model.model.layers.4.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
457
+ "language_model.base_model.model.model.layers.4.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
458
+ "language_model.base_model.model.model.layers.4.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
459
+ "language_model.base_model.model.model.layers.4.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
460
+ "language_model.base_model.model.model.layers.4.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
461
+ "language_model.base_model.model.model.layers.4.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
462
+ "language_model.base_model.model.model.layers.4.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
463
+ "language_model.base_model.model.model.layers.4.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
464
+ "language_model.base_model.model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
465
+ "language_model.base_model.model.model.layers.5.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
466
+ "language_model.base_model.model.model.layers.5.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
467
+ "language_model.base_model.model.model.layers.5.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
468
+ "language_model.base_model.model.model.layers.5.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
469
+ "language_model.base_model.model.model.layers.5.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
470
+ "language_model.base_model.model.model.layers.5.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
471
+ "language_model.base_model.model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
472
+ "language_model.base_model.model.model.layers.5.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
473
+ "language_model.base_model.model.model.layers.5.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
474
+ "language_model.base_model.model.model.layers.5.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
475
+ "language_model.base_model.model.model.layers.5.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
476
+ "language_model.base_model.model.model.layers.5.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
477
+ "language_model.base_model.model.model.layers.5.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
478
+ "language_model.base_model.model.model.layers.5.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
479
+ "language_model.base_model.model.model.layers.5.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
480
+ "language_model.base_model.model.model.layers.5.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
481
+ "language_model.base_model.model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
482
+ "language_model.base_model.model.model.layers.6.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
483
+ "language_model.base_model.model.model.layers.6.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
484
+ "language_model.base_model.model.model.layers.6.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
485
+ "language_model.base_model.model.model.layers.6.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
486
+ "language_model.base_model.model.model.layers.6.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
487
+ "language_model.base_model.model.model.layers.6.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
488
+ "language_model.base_model.model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
489
+ "language_model.base_model.model.model.layers.6.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
490
+ "language_model.base_model.model.model.layers.6.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
491
+ "language_model.base_model.model.model.layers.6.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
492
+ "language_model.base_model.model.model.layers.6.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
493
+ "language_model.base_model.model.model.layers.6.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
494
+ "language_model.base_model.model.model.layers.6.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
495
+ "language_model.base_model.model.model.layers.6.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
496
+ "language_model.base_model.model.model.layers.6.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
497
+ "language_model.base_model.model.model.layers.6.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
498
+ "language_model.base_model.model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
499
+ "language_model.base_model.model.model.layers.7.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
500
+ "language_model.base_model.model.model.layers.7.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
501
+ "language_model.base_model.model.model.layers.7.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
502
+ "language_model.base_model.model.model.layers.7.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
503
+ "language_model.base_model.model.model.layers.7.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
504
+ "language_model.base_model.model.model.layers.7.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
505
+ "language_model.base_model.model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
506
+ "language_model.base_model.model.model.layers.7.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
507
+ "language_model.base_model.model.model.layers.7.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
508
+ "language_model.base_model.model.model.layers.7.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
509
+ "language_model.base_model.model.model.layers.7.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
510
+ "language_model.base_model.model.model.layers.7.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
511
+ "language_model.base_model.model.model.layers.7.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
512
+ "language_model.base_model.model.model.layers.7.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
513
+ "language_model.base_model.model.model.layers.7.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
514
+ "language_model.base_model.model.model.layers.7.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
515
+ "language_model.base_model.model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
516
+ "language_model.base_model.model.model.layers.8.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
517
+ "language_model.base_model.model.model.layers.8.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
518
+ "language_model.base_model.model.model.layers.8.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
519
+ "language_model.base_model.model.model.layers.8.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
520
+ "language_model.base_model.model.model.layers.8.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
521
+ "language_model.base_model.model.model.layers.8.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
522
+ "language_model.base_model.model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
523
+ "language_model.base_model.model.model.layers.8.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
524
+ "language_model.base_model.model.model.layers.8.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
525
+ "language_model.base_model.model.model.layers.8.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
526
+ "language_model.base_model.model.model.layers.8.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
527
+ "language_model.base_model.model.model.layers.8.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
528
+ "language_model.base_model.model.model.layers.8.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
529
+ "language_model.base_model.model.model.layers.8.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
530
+ "language_model.base_model.model.model.layers.8.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
531
+ "language_model.base_model.model.model.layers.8.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
532
+ "language_model.base_model.model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
533
+ "language_model.base_model.model.model.layers.9.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
534
+ "language_model.base_model.model.model.layers.9.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
535
+ "language_model.base_model.model.model.layers.9.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
536
+ "language_model.base_model.model.model.layers.9.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
537
+ "language_model.base_model.model.model.layers.9.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
538
+ "language_model.base_model.model.model.layers.9.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
539
+ "language_model.base_model.model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
540
+ "language_model.base_model.model.model.layers.9.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
541
+ "language_model.base_model.model.model.layers.9.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
542
+ "language_model.base_model.model.model.layers.9.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
543
+ "language_model.base_model.model.model.layers.9.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
544
+ "language_model.base_model.model.model.layers.9.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
545
+ "language_model.base_model.model.model.layers.9.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
546
+ "language_model.base_model.model.model.layers.9.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
547
+ "language_model.base_model.model.model.layers.9.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
548
+ "language_model.base_model.model.model.layers.9.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
549
+ "language_model.base_model.model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
550
+ "language_model.base_model.model.model.norm.weight": "model-00004-of-00004.safetensors",
551
+ "language_model.base_model.model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
552
+ "language_model.base_model.model.output.weight": "model-00004-of-00004.safetensors",
553
+ "mlp1.0.bias": "model-00004-of-00004.safetensors",
554
+ "mlp1.0.weight": "model-00004-of-00004.safetensors",
555
+ "mlp1.1.bias": "model-00004-of-00004.safetensors",
556
+ "mlp1.1.weight": "model-00004-of-00004.safetensors",
557
+ "mlp1.3.bias": "model-00004-of-00004.safetensors",
558
+ "mlp1.3.weight": "model-00004-of-00004.safetensors",
559
+ "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
560
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
561
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
562
+ "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
563
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
564
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
565
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
568
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
569
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
570
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
571
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
576
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
578
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
579
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
580
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
581
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
582
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
583
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
584
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
585
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
586
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
587
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
588
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
589
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
590
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
591
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
592
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
593
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
594
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
595
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
596
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
597
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
598
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
599
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
600
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
602
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
603
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
604
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
605
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
606
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
607
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
608
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
609
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
610
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
611
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
612
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
613
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
614
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
615
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
616
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
617
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
618
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
619
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
620
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
621
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
622
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
623
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
624
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
625
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
626
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
627
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
628
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
629
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
630
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
631
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
632
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
633
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
636
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
637
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
638
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
639
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
640
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
641
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
642
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
643
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
644
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
645
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
646
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
647
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
648
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
649
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
650
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
651
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
652
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
653
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
654
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
655
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
656
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
657
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
658
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
659
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
660
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
661
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
662
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
663
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
664
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
665
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
666
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
667
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
668
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
669
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
670
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
671
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
672
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
673
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
674
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
675
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
676
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
677
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
678
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
679
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
680
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
681
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
682
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
683
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
684
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
685
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
686
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
687
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
688
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
689
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
690
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
691
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
692
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
693
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
694
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
695
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
696
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
697
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
698
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
699
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
700
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
701
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
702
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
703
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
704
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
705
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
706
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
707
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
708
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
709
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
710
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
711
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
712
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
713
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
714
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
715
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
716
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
717
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
718
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
719
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
720
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
721
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
722
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
723
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
724
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
725
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
726
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
727
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
728
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
729
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
730
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
731
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
732
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
733
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
734
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
735
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
736
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
737
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
738
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
739
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
740
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
741
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
742
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
743
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
744
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
745
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
746
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
747
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
748
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
749
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
750
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
751
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
752
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
753
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
754
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
755
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
756
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
757
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
758
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
759
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
760
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
761
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
762
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
763
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
764
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
765
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
766
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
767
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
768
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
769
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
770
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
771
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
772
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
773
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
774
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
775
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
776
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
777
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
778
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
779
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
780
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
781
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
782
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
783
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
784
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
785
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
786
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
787
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
788
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
789
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
790
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
791
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
792
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
793
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
794
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
795
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
796
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
797
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
798
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
799
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
800
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
801
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
802
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
803
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
804
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
805
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
806
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
807
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
808
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
809
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
810
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
811
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
812
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
813
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
814
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
815
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
816
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
817
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
818
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
819
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
820
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
821
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
822
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
823
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
824
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
825
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
826
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
827
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
828
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
829
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
830
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
831
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
832
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
833
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
834
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
835
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
836
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
837
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
838
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
839
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
840
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
841
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
842
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
843
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
844
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
845
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
846
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
847
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
848
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
849
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
850
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
851
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
852
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
853
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
854
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
855
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
856
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
857
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
858
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
859
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
860
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
861
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
862
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
863
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
864
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
865
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
866
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
867
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
868
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
869
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
870
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
871
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
872
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
873
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
874
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
875
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
876
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
877
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
878
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
879
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
880
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
881
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
882
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
883
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
884
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
885
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
886
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
887
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
888
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
889
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
890
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
891
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
892
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
893
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
894
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
895
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
896
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
897
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
898
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
899
+ }
900
+ }
runs/Sep15_15-26-42_1fe2e16e3880/events.out.tfevents.1726414020.1fe2e16e3880 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488f6f9756ca9273e85e71f87dba61fcfcb91e0d49dc5f9f9d2a14d42ccbc4a2
3
+ size 11292
runs/Sep15_15-32-38_1fe2e16e3880/events.out.tfevents.1726414376.1fe2e16e3880 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d39e8845e045452a9e46d3f2691ca3baaff8da69c34f71ac92a45c0b02042a1
3
+ size 10830
runs/Sep15_15-34-50_1fe2e16e3880/events.out.tfevents.1726414508.1fe2e16e3880 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfa12b0af40dff32d0a4a5cf642616d9a0f03ab7f6d004ac24e40205131e78a
3
+ size 82893
special_tokens_map.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<img>",
10
+ "</img>",
11
+ "<IMG_CONTEXT>",
12
+ "<quad>",
13
+ "</quad>",
14
+ "<ref>",
15
+ "</ref>",
16
+ "<box>",
17
+ "</box>"
18
+ ],
19
+ "bos_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "eos_token": {
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "unk_token": {
41
+ "content": "<unk>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ }
47
+ }
tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ }
147
+ },
148
+ "additional_special_tokens": [
149
+ "<|im_start|>",
150
+ "<|im_end|>",
151
+ "<|action_start|>",
152
+ "<|action_end|>",
153
+ "<|interpreter|>",
154
+ "<|plugin|>",
155
+ "<img>",
156
+ "</img>",
157
+ "<IMG_CONTEXT>",
158
+ "<quad>",
159
+ "</quad>",
160
+ "<ref>",
161
+ "</ref>",
162
+ "<box>",
163
+ "</box>"
164
+ ],
165
+ "auto_map": {
166
+ "AutoTokenizer": [
167
+ "tokenization_internlm2.InternLM2Tokenizer",
168
+ null
169
+ ]
170
+ },
171
+ "bos_token": "<s>",
172
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
173
+ "clean_up_tokenization_spaces": false,
174
+ "eos_token": "</s>",
175
+ "model_max_length": 4096,
176
+ "pad_token": "</s>",
177
+ "tokenizer_class": "InternLM2Tokenizer",
178
+ "unk_token": "<unk>"
179
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99,
3
+ "train_loss": 0.3061195729762061,
4
+ "train_runtime": 5033.3609,
5
+ "train_samples": 9996,
6
+ "train_samples_per_second": 5.958,
7
+ "train_steps_per_second": 0.093
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,2838 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9904153354632586,
5
+ "eval_steps": 500,
6
+ "global_step": 468,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2.666666666666667e-06,
14
+ "loss": 3.7352,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 5.333333333333334e-06,
20
+ "loss": 3.7667,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 8.000000000000001e-06,
26
+ "loss": 3.7797,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.03,
31
+ "learning_rate": 1.0666666666666667e-05,
32
+ "loss": 3.6592,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 1.3333333333333333e-05,
38
+ "loss": 3.6968,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 1.6000000000000003e-05,
44
+ "loss": 3.7754,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 1.866666666666667e-05,
50
+ "loss": 3.4281,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 2.1333333333333335e-05,
56
+ "loss": 3.6136,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.06,
61
+ "learning_rate": 2.4e-05,
62
+ "loss": 3.0098,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 2.6666666666666667e-05,
68
+ "loss": 2.7693,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 2.9333333333333333e-05,
74
+ "loss": 2.2559,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.08,
79
+ "learning_rate": 3.2000000000000005e-05,
80
+ "loss": 2.1567,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "learning_rate": 3.466666666666667e-05,
86
+ "loss": 1.7343,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.09,
91
+ "learning_rate": 3.733333333333334e-05,
92
+ "loss": 1.677,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.1,
97
+ "learning_rate": 4e-05,
98
+ "loss": 1.2854,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.1,
103
+ "learning_rate": 3.999951904814875e-05,
104
+ "loss": 1.1381,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.11,
109
+ "learning_rate": 3.999807621572648e-05,
110
+ "loss": 0.7843,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.12,
115
+ "learning_rate": 3.999567157212646e-05,
116
+ "loss": 0.7415,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.12,
121
+ "learning_rate": 3.999230523300049e-05,
122
+ "loss": 0.6684,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.13,
127
+ "learning_rate": 3.998797736025326e-05,
128
+ "loss": 0.4267,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.13,
133
+ "learning_rate": 3.9982688162034624e-05,
134
+ "loss": 0.5993,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.14,
139
+ "learning_rate": 3.997643789272954e-05,
140
+ "loss": 0.555,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.15,
145
+ "learning_rate": 3.996922685294587e-05,
146
+ "loss": 0.5142,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.15,
151
+ "learning_rate": 3.9961055389499904e-05,
152
+ "loss": 0.3841,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.16,
157
+ "learning_rate": 3.9951923895399696e-05,
158
+ "loss": 0.3057,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.17,
163
+ "learning_rate": 3.9941832809826136e-05,
164
+ "loss": 0.4327,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.17,
169
+ "learning_rate": 3.993078261811186e-05,
170
+ "loss": 0.3207,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.18,
175
+ "learning_rate": 3.991877385171789e-05,
176
+ "loss": 0.454,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.19,
181
+ "learning_rate": 3.990580708820805e-05,
182
+ "loss": 0.2997,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.19,
187
+ "learning_rate": 3.9891882951221246e-05,
188
+ "loss": 0.3583,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.2,
193
+ "learning_rate": 3.9877002110441424e-05,
194
+ "loss": 0.2823,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.2,
199
+ "learning_rate": 3.986116528156537e-05,
200
+ "loss": 0.2659,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.21,
205
+ "learning_rate": 3.9844373226268305e-05,
206
+ "loss": 0.3158,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.22,
211
+ "learning_rate": 3.982662675216723e-05,
212
+ "loss": 0.2704,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.22,
217
+ "learning_rate": 3.9807926712782115e-05,
218
+ "loss": 0.3642,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.23,
223
+ "learning_rate": 3.978827400749481e-05,
224
+ "loss": 0.3058,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.24,
229
+ "learning_rate": 3.976766958150581e-05,
230
+ "loss": 0.3343,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.24,
235
+ "learning_rate": 3.97461144257888e-05,
236
+ "loss": 0.2987,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.25,
241
+ "learning_rate": 3.972360957704298e-05,
242
+ "loss": 0.2469,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.26,
247
+ "learning_rate": 3.970015611764323e-05,
248
+ "loss": 0.359,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.26,
253
+ "learning_rate": 3.9675755175588006e-05,
254
+ "loss": 0.2903,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.27,
259
+ "learning_rate": 3.9650407924445147e-05,
260
+ "loss": 0.3881,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.27,
265
+ "learning_rate": 3.9624115583295375e-05,
266
+ "loss": 0.2877,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.28,
271
+ "learning_rate": 3.959687941667372e-05,
272
+ "loss": 0.2628,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.29,
277
+ "learning_rate": 3.9568700734508645e-05,
278
+ "loss": 0.2789,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.29,
283
+ "learning_rate": 3.9539580892059086e-05,
284
+ "loss": 0.2164,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.3,
289
+ "learning_rate": 3.950952128984927e-05,
290
+ "loss": 0.217,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.31,
295
+ "learning_rate": 3.9478523373601325e-05,
296
+ "loss": 0.2196,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.31,
301
+ "learning_rate": 3.944658863416575e-05,
302
+ "loss": 0.3036,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.32,
307
+ "learning_rate": 3.941371860744978e-05,
308
+ "loss": 0.2398,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.33,
313
+ "learning_rate": 3.937991487434342e-05,
314
+ "loss": 0.2441,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.33,
319
+ "learning_rate": 3.934517906064348e-05,
320
+ "loss": 0.2922,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.34,
325
+ "learning_rate": 3.930951283697534e-05,
326
+ "loss": 0.3127,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.35,
331
+ "learning_rate": 3.927291791871264e-05,
332
+ "loss": 0.2994,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.35,
337
+ "learning_rate": 3.923539606589473e-05,
338
+ "loss": 0.2534,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.36,
343
+ "learning_rate": 3.919694908314209e-05,
344
+ "loss": 0.2855,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.36,
349
+ "learning_rate": 3.9157578819569455e-05,
350
+ "loss": 0.2889,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.37,
355
+ "learning_rate": 3.9117287168696956e-05,
356
+ "loss": 0.3228,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.38,
361
+ "learning_rate": 3.907607606835899e-05,
362
+ "loss": 0.2197,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.38,
367
+ "learning_rate": 3.903394750061106e-05,
368
+ "loss": 0.3422,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.39,
373
+ "learning_rate": 3.899090349163444e-05,
374
+ "loss": 0.2788,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.4,
379
+ "learning_rate": 3.8946946111638696e-05,
380
+ "loss": 0.3245,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.4,
385
+ "learning_rate": 3.8902077474762155e-05,
386
+ "loss": 0.336,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.41,
391
+ "learning_rate": 3.8856299738970225e-05,
392
+ "loss": 0.2951,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.42,
397
+ "learning_rate": 3.880961510595158e-05,
398
+ "loss": 0.3156,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.42,
403
+ "learning_rate": 3.876202582101229e-05,
404
+ "loss": 0.2534,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.43,
409
+ "learning_rate": 3.8713534172967815e-05,
410
+ "loss": 0.2775,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.43,
415
+ "learning_rate": 3.866414249403295e-05,
416
+ "loss": 0.3381,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.44,
421
+ "learning_rate": 3.861385315970964e-05,
422
+ "loss": 0.2593,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.45,
427
+ "learning_rate": 3.856266858867273e-05,
428
+ "loss": 0.166,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.45,
433
+ "learning_rate": 3.851059124265363e-05,
434
+ "loss": 0.3453,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.46,
439
+ "learning_rate": 3.8457623626321944e-05,
440
+ "loss": 0.2238,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.47,
445
+ "learning_rate": 3.840376828716499e-05,
446
+ "loss": 0.2773,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.47,
451
+ "learning_rate": 3.834902781536527e-05,
452
+ "loss": 0.2777,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.48,
457
+ "learning_rate": 3.8293404843675904e-05,
458
+ "loss": 0.3032,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.49,
463
+ "learning_rate": 3.8236902047294015e-05,
464
+ "loss": 0.2138,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.49,
469
+ "learning_rate": 3.817952214373206e-05,
470
+ "loss": 0.2605,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.5,
475
+ "learning_rate": 3.812126789268712e-05,
476
+ "loss": 0.3205,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.5,
481
+ "learning_rate": 3.806214209590819e-05,
482
+ "loss": 0.27,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.51,
487
+ "learning_rate": 3.80021475970614e-05,
488
+ "loss": 0.2882,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.52,
493
+ "learning_rate": 3.7941287281593284e-05,
494
+ "loss": 0.3081,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.52,
499
+ "learning_rate": 3.787956407659198e-05,
500
+ "loss": 0.3268,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.53,
505
+ "learning_rate": 3.781698095064647e-05,
506
+ "loss": 0.2018,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.54,
511
+ "learning_rate": 3.775354091370376e-05,
512
+ "loss": 0.2624,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.54,
517
+ "learning_rate": 3.7689247016924186e-05,
518
+ "loss": 0.2042,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.55,
523
+ "learning_rate": 3.7624102352534615e-05,
524
+ "loss": 0.3193,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.56,
529
+ "learning_rate": 3.755811005367974e-05,
530
+ "loss": 0.2487,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.56,
535
+ "learning_rate": 3.7491273294271386e-05,
536
+ "loss": 0.1408,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.57,
541
+ "learning_rate": 3.742359528883588e-05,
542
+ "loss": 0.276,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.58,
547
+ "learning_rate": 3.735507929235941e-05,
548
+ "loss": 0.2293,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.58,
553
+ "learning_rate": 3.7285728600131535e-05,
554
+ "loss": 0.2223,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.59,
559
+ "learning_rate": 3.7215546547586596e-05,
560
+ "loss": 0.3011,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.59,
565
+ "learning_rate": 3.7144536510143436e-05,
566
+ "loss": 0.2439,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.6,
571
+ "learning_rate": 3.707270190304294e-05,
572
+ "loss": 0.2061,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.61,
577
+ "learning_rate": 3.7000046181183834e-05,
578
+ "loss": 0.1888,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.61,
583
+ "learning_rate": 3.692657283895651e-05,
584
+ "loss": 0.2698,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.62,
589
+ "learning_rate": 3.6852285410074974e-05,
590
+ "loss": 0.1813,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.63,
595
+ "learning_rate": 3.6777187467406857e-05,
596
+ "loss": 0.3824,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.63,
601
+ "learning_rate": 3.6701282622801626e-05,
602
+ "loss": 0.2891,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.64,
607
+ "learning_rate": 3.662457452691682e-05,
608
+ "loss": 0.1906,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.65,
613
+ "learning_rate": 3.6547066869042524e-05,
614
+ "loss": 0.2127,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.65,
619
+ "learning_rate": 3.6468763376923886e-05,
620
+ "loss": 0.3177,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.66,
625
+ "learning_rate": 3.638966781658187e-05,
626
+ "loss": 0.1738,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.66,
631
+ "learning_rate": 3.630978399213206e-05,
632
+ "loss": 0.1801,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.67,
637
+ "learning_rate": 3.622911574560181e-05,
638
+ "loss": 0.2335,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.68,
643
+ "learning_rate": 3.6147666956745364e-05,
644
+ "loss": 0.2521,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.68,
649
+ "learning_rate": 3.60654415428573e-05,
650
+ "loss": 0.204,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.69,
655
+ "learning_rate": 3.598244345858412e-05,
656
+ "loss": 0.2199,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.7,
661
+ "learning_rate": 3.589867669573404e-05,
662
+ "loss": 0.322,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.7,
667
+ "learning_rate": 3.5814145283085055e-05,
668
+ "loss": 0.2733,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.71,
673
+ "learning_rate": 3.5728853286191075e-05,
674
+ "loss": 0.3102,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.72,
679
+ "learning_rate": 3.56428048071865e-05,
680
+ "loss": 0.2365,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.72,
685
+ "learning_rate": 3.555600398458885e-05,
686
+ "loss": 0.1718,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.73,
691
+ "learning_rate": 3.546845499309976e-05,
692
+ "loss": 0.198,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.73,
697
+ "learning_rate": 3.538016204340418e-05,
698
+ "loss": 0.2557,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.74,
703
+ "learning_rate": 3.529112938196787e-05,
704
+ "loss": 0.1825,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.75,
709
+ "learning_rate": 3.5201361290833165e-05,
710
+ "loss": 0.3099,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.75,
715
+ "learning_rate": 3.511086208741303e-05,
716
+ "loss": 0.3273,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.76,
721
+ "learning_rate": 3.501963612428341e-05,
722
+ "loss": 0.4337,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.77,
727
+ "learning_rate": 3.492768778897388e-05,
728
+ "loss": 0.2754,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.77,
733
+ "learning_rate": 3.483502150375665e-05,
734
+ "loss": 0.2226,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.78,
739
+ "learning_rate": 3.474164172543386e-05,
740
+ "loss": 0.2698,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.79,
745
+ "learning_rate": 3.464755294512325e-05,
746
+ "loss": 0.2,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.79,
751
+ "learning_rate": 3.455275968804212e-05,
752
+ "loss": 0.1865,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.8,
757
+ "learning_rate": 3.445726651328971e-05,
758
+ "loss": 0.2586,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.81,
763
+ "learning_rate": 3.4361078013627945e-05,
764
+ "loss": 0.3064,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.81,
769
+ "learning_rate": 3.426419881526052e-05,
770
+ "loss": 0.21,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.82,
775
+ "learning_rate": 3.4166633577610425e-05,
776
+ "loss": 0.1701,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.82,
781
+ "learning_rate": 3.4068386993095806e-05,
782
+ "loss": 0.2909,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.83,
787
+ "learning_rate": 3.396946378690435e-05,
788
+ "loss": 0.2558,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.84,
793
+ "learning_rate": 3.386986871676597e-05,
794
+ "loss": 0.1833,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.84,
799
+ "learning_rate": 3.3769606572724e-05,
800
+ "loss": 0.184,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.85,
805
+ "learning_rate": 3.366868217690482e-05,
806
+ "loss": 0.2481,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.86,
811
+ "learning_rate": 3.3567100383285925e-05,
812
+ "loss": 0.1628,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.86,
817
+ "learning_rate": 3.346486607746249e-05,
818
+ "loss": 0.1711,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.87,
823
+ "learning_rate": 3.336198417641238e-05,
824
+ "loss": 0.2293,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.88,
829
+ "learning_rate": 3.325845962825966e-05,
830
+ "loss": 0.2515,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.88,
835
+ "learning_rate": 3.315429741203666e-05,
836
+ "loss": 0.1741,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.89,
841
+ "learning_rate": 3.304950253744443e-05,
842
+ "loss": 0.1595,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.89,
847
+ "learning_rate": 3.294408004461188e-05,
848
+ "loss": 0.1889,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.9,
853
+ "learning_rate": 3.283803500385332e-05,
854
+ "loss": 0.2864,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.91,
859
+ "learning_rate": 3.27313725154246e-05,
860
+ "loss": 0.1941,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.91,
865
+ "learning_rate": 3.2624097709277855e-05,
866
+ "loss": 0.2526,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.92,
871
+ "learning_rate": 3.251621574481475e-05,
872
+ "loss": 0.1784,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.93,
877
+ "learning_rate": 3.240773181063834e-05,
878
+ "loss": 0.3217,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.93,
883
+ "learning_rate": 3.229865112430352e-05,
884
+ "loss": 0.2438,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.94,
889
+ "learning_rate": 3.218897893206608e-05,
890
+ "loss": 0.2797,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.95,
895
+ "learning_rate": 3.2078720508630427e-05,
896
+ "loss": 0.2358,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.95,
901
+ "learning_rate": 3.196788115689584e-05,
902
+ "loss": 0.2403,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.96,
907
+ "learning_rate": 3.185646620770146e-05,
908
+ "loss": 0.2295,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.96,
913
+ "learning_rate": 3.1744481019569885e-05,
914
+ "loss": 0.2063,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.97,
919
+ "learning_rate": 3.163193097844949e-05,
920
+ "loss": 0.2654,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.98,
925
+ "learning_rate": 3.1518821497455326e-05,
926
+ "loss": 0.2071,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.98,
931
+ "learning_rate": 3.1405158016608806e-05,
932
+ "loss": 0.2035,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.99,
937
+ "learning_rate": 3.129094600257611e-05,
938
+ "loss": 0.2398,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 1.0,
943
+ "learning_rate": 3.1176190948405194e-05,
944
+ "loss": 0.1623,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 1.0,
949
+ "learning_rate": 3.106089837326161e-05,
950
+ "loss": 0.2313,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 1.01,
955
+ "learning_rate": 3.094507382216312e-05,
956
+ "loss": 0.2687,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 1.02,
961
+ "learning_rate": 3.082872286571295e-05,
962
+ "loss": 0.246,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 1.02,
967
+ "learning_rate": 3.0711851099831885e-05,
968
+ "loss": 0.191,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 1.03,
973
+ "learning_rate": 3.059446414548915e-05,
974
+ "loss": 0.1543,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 1.04,
979
+ "learning_rate": 3.047656764843203e-05,
980
+ "loss": 0.1978,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 1.04,
985
+ "learning_rate": 3.0358167278914387e-05,
986
+ "loss": 0.2698,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 1.05,
991
+ "learning_rate": 3.023926873142391e-05,
992
+ "loss": 0.2351,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 1.05,
997
+ "learning_rate": 3.011987772440825e-05,
998
+ "loss": 0.1925,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 1.06,
1003
+ "learning_rate": 3.0000000000000004e-05,
1004
+ "loss": 0.2246,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 1.07,
1009
+ "learning_rate": 2.9879641323740505e-05,
1010
+ "loss": 0.2093,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 1.07,
1015
+ "learning_rate": 2.9758807484302566e-05,
1016
+ "loss": 0.2332,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 1.08,
1021
+ "learning_rate": 2.963750429321208e-05,
1022
+ "loss": 0.1983,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 1.09,
1027
+ "learning_rate": 2.9515737584568463e-05,
1028
+ "loss": 0.2707,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 1.09,
1033
+ "learning_rate": 2.939351321476412e-05,
1034
+ "loss": 0.2485,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 1.1,
1039
+ "learning_rate": 2.927083706220274e-05,
1040
+ "loss": 0.1947,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 1.11,
1045
+ "learning_rate": 2.9147715027016593e-05,
1046
+ "loss": 0.1949,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 1.11,
1051
+ "learning_rate": 2.902415303078275e-05,
1052
+ "loss": 0.1907,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.12,
1057
+ "learning_rate": 2.8900157016238296e-05,
1058
+ "loss": 0.1801,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.12,
1063
+ "learning_rate": 2.8775732946994508e-05,
1064
+ "loss": 0.2489,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.13,
1069
+ "learning_rate": 2.8650886807250024e-05,
1070
+ "loss": 0.1969,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.14,
1075
+ "learning_rate": 2.8525624601503055e-05,
1076
+ "loss": 0.1724,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.14,
1081
+ "learning_rate": 2.8399952354262566e-05,
1082
+ "loss": 0.1797,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.15,
1087
+ "learning_rate": 2.8273876109758568e-05,
1088
+ "loss": 0.1341,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.16,
1093
+ "learning_rate": 2.8147401931651363e-05,
1094
+ "loss": 0.2223,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.16,
1099
+ "learning_rate": 2.802053590273997e-05,
1100
+ "loss": 0.2221,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.17,
1105
+ "learning_rate": 2.789328412466953e-05,
1106
+ "loss": 0.2019,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.18,
1111
+ "learning_rate": 2.7765652717637873e-05,
1112
+ "loss": 0.1336,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.18,
1117
+ "learning_rate": 2.763764782010116e-05,
1118
+ "loss": 0.2361,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.19,
1123
+ "learning_rate": 2.7509275588478606e-05,
1124
+ "loss": 0.2023,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.19,
1129
+ "learning_rate": 2.738054219685647e-05,
1130
+ "loss": 0.2428,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.2,
1135
+ "learning_rate": 2.725145383669106e-05,
1136
+ "loss": 0.2394,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.21,
1141
+ "learning_rate": 2.712201671651094e-05,
1142
+ "loss": 0.1464,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.21,
1147
+ "learning_rate": 2.699223706161839e-05,
1148
+ "loss": 0.2485,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.22,
1153
+ "learning_rate": 2.6862121113789917e-05,
1154
+ "loss": 0.3039,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.23,
1159
+ "learning_rate": 2.673167513097613e-05,
1160
+ "loss": 0.1387,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.23,
1165
+ "learning_rate": 2.6600905387000716e-05,
1166
+ "loss": 0.2657,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.24,
1171
+ "learning_rate": 2.6469818171258723e-05,
1172
+ "loss": 0.176,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.25,
1177
+ "learning_rate": 2.633841978841406e-05,
1178
+ "loss": 0.1876,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.25,
1183
+ "learning_rate": 2.620671655809627e-05,
1184
+ "loss": 0.1726,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.26,
1189
+ "learning_rate": 2.60747148145966e-05,
1190
+ "loss": 0.2352,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.27,
1195
+ "learning_rate": 2.594242090656335e-05,
1196
+ "loss": 0.254,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.27,
1201
+ "learning_rate": 2.5809841196696504e-05,
1202
+ "loss": 0.2125,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.28,
1207
+ "learning_rate": 2.5676982061441763e-05,
1208
+ "loss": 0.2049,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 1.28,
1213
+ "learning_rate": 2.5543849890683813e-05,
1214
+ "loss": 0.1865,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 1.29,
1219
+ "learning_rate": 2.5410451087439075e-05,
1220
+ "loss": 0.2203,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 1.3,
1225
+ "learning_rate": 2.5276792067547672e-05,
1226
+ "loss": 0.2002,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 1.3,
1231
+ "learning_rate": 2.514287925936492e-05,
1232
+ "loss": 0.1524,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 1.31,
1237
+ "learning_rate": 2.500871910345212e-05,
1238
+ "loss": 0.2059,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 1.32,
1243
+ "learning_rate": 2.4874318052266794e-05,
1244
+ "loss": 0.1885,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 1.32,
1249
+ "learning_rate": 2.473968256985238e-05,
1250
+ "loss": 0.1837,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 1.33,
1255
+ "learning_rate": 2.460481913152734e-05,
1256
+ "loss": 0.1938,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 1.34,
1261
+ "learning_rate": 2.4469734223573703e-05,
1262
+ "loss": 0.1497,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 1.34,
1267
+ "learning_rate": 2.4334434342925133e-05,
1268
+ "loss": 0.2644,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 1.35,
1273
+ "learning_rate": 2.4198925996854422e-05,
1274
+ "loss": 0.1937,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 1.35,
1279
+ "learning_rate": 2.4063215702660564e-05,
1280
+ "loss": 0.2791,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 1.36,
1285
+ "learning_rate": 2.392730998735529e-05,
1286
+ "loss": 0.24,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 1.37,
1291
+ "learning_rate": 2.379121538734912e-05,
1292
+ "loss": 0.1574,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 1.37,
1297
+ "learning_rate": 2.3654938448137062e-05,
1298
+ "loss": 0.1896,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 1.38,
1303
+ "learning_rate": 2.351848572398371e-05,
1304
+ "loss": 0.1865,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 1.39,
1309
+ "learning_rate": 2.338186377760811e-05,
1310
+ "loss": 0.1336,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 1.39,
1315
+ "learning_rate": 2.3245079179868054e-05,
1316
+ "loss": 0.2047,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 1.4,
1321
+ "learning_rate": 2.31081385094441e-05,
1322
+ "loss": 0.31,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 1.41,
1327
+ "learning_rate": 2.297104835252314e-05,
1328
+ "loss": 0.2096,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 1.41,
1333
+ "learning_rate": 2.283381530248165e-05,
1334
+ "loss": 0.2593,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 1.42,
1339
+ "learning_rate": 2.2696445959568577e-05,
1340
+ "loss": 0.1585,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 1.42,
1345
+ "learning_rate": 2.2558946930587907e-05,
1346
+ "loss": 0.1781,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 1.43,
1351
+ "learning_rate": 2.2421324828580877e-05,
1352
+ "loss": 0.1462,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 1.44,
1357
+ "learning_rate": 2.2283586272507975e-05,
1358
+ "loss": 0.1687,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 1.44,
1363
+ "learning_rate": 2.214573788693054e-05,
1364
+ "loss": 0.1716,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 1.45,
1369
+ "learning_rate": 2.2007786301692205e-05,
1370
+ "loss": 0.2694,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 1.46,
1375
+ "learning_rate": 2.18697381516e-05,
1376
+ "loss": 0.1615,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 1.46,
1381
+ "learning_rate": 2.1731600076105264e-05,
1382
+ "loss": 0.1891,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 1.47,
1387
+ "learning_rate": 2.159337871898431e-05,
1388
+ "loss": 0.1321,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 1.48,
1393
+ "learning_rate": 2.145508072801888e-05,
1394
+ "loss": 0.1706,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 1.48,
1399
+ "learning_rate": 2.131671275467647e-05,
1400
+ "loss": 0.2391,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 1.49,
1405
+ "learning_rate": 2.1178281453790358e-05,
1406
+ "loss": 0.1462,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 1.5,
1411
+ "learning_rate": 2.1039793483239607e-05,
1412
+ "loss": 0.1928,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 1.5,
1417
+ "learning_rate": 2.090125550362879e-05,
1418
+ "loss": 0.3621,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 1.51,
1423
+ "learning_rate": 2.0762674177967676e-05,
1424
+ "loss": 0.1987,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 1.51,
1429
+ "learning_rate": 2.0624056171350785e-05,
1430
+ "loss": 0.2071,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 1.52,
1435
+ "learning_rate": 2.0485408150636804e-05,
1436
+ "loss": 0.1817,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 1.53,
1441
+ "learning_rate": 2.0346736784127955e-05,
1442
+ "loss": 0.1615,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 1.53,
1447
+ "learning_rate": 2.0208048741249288e-05,
1448
+ "loss": 0.1521,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 1.54,
1453
+ "learning_rate": 2.006935069222789e-05,
1454
+ "loss": 0.156,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 1.55,
1459
+ "learning_rate": 1.9930649307772114e-05,
1460
+ "loss": 0.2438,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 1.55,
1465
+ "learning_rate": 1.979195125875072e-05,
1466
+ "loss": 0.2432,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.56,
1471
+ "learning_rate": 1.9653263215872048e-05,
1472
+ "loss": 0.1292,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.57,
1477
+ "learning_rate": 1.9514591849363203e-05,
1478
+ "loss": 0.2293,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.57,
1483
+ "learning_rate": 1.9375943828649215e-05,
1484
+ "loss": 0.1932,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.58,
1489
+ "learning_rate": 1.923732582203233e-05,
1490
+ "loss": 0.1508,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.58,
1495
+ "learning_rate": 1.909874449637122e-05,
1496
+ "loss": 0.2317,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.59,
1501
+ "learning_rate": 1.8960206516760396e-05,
1502
+ "loss": 0.218,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.6,
1507
+ "learning_rate": 1.8821718546209646e-05,
1508
+ "loss": 0.1777,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.6,
1513
+ "learning_rate": 1.8683287245323536e-05,
1514
+ "loss": 0.1577,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.61,
1519
+ "learning_rate": 1.8544919271981125e-05,
1520
+ "loss": 0.2977,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.62,
1525
+ "learning_rate": 1.84066212810157e-05,
1526
+ "loss": 0.2277,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.62,
1531
+ "learning_rate": 1.8268399923894736e-05,
1532
+ "loss": 0.1574,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.63,
1537
+ "learning_rate": 1.8130261848399996e-05,
1538
+ "loss": 0.3187,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.64,
1543
+ "learning_rate": 1.7992213698307795e-05,
1544
+ "loss": 0.1758,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.64,
1549
+ "learning_rate": 1.7854262113069468e-05,
1550
+ "loss": 0.2118,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.65,
1555
+ "learning_rate": 1.7716413727492035e-05,
1556
+ "loss": 0.1539,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.65,
1561
+ "learning_rate": 1.757867517141913e-05,
1562
+ "loss": 0.1885,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.66,
1567
+ "learning_rate": 1.7441053069412103e-05,
1568
+ "loss": 0.1915,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.67,
1573
+ "learning_rate": 1.7303554040431426e-05,
1574
+ "loss": 0.1716,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.67,
1579
+ "learning_rate": 1.7166184697518352e-05,
1580
+ "loss": 0.2217,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.68,
1585
+ "learning_rate": 1.7028951647476862e-05,
1586
+ "loss": 0.3266,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.69,
1591
+ "learning_rate": 1.6891861490555906e-05,
1592
+ "loss": 0.2631,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.69,
1597
+ "learning_rate": 1.6754920820131946e-05,
1598
+ "loss": 0.2481,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.7,
1603
+ "learning_rate": 1.6618136222391893e-05,
1604
+ "loss": 0.2521,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.71,
1609
+ "learning_rate": 1.6481514276016297e-05,
1610
+ "loss": 0.2022,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.71,
1615
+ "learning_rate": 1.634506155186295e-05,
1616
+ "loss": 0.2055,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.72,
1621
+ "learning_rate": 1.6208784612650883e-05,
1622
+ "loss": 0.2257,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.73,
1627
+ "learning_rate": 1.6072690012644717e-05,
1628
+ "loss": 0.2634,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.73,
1633
+ "learning_rate": 1.593678429733944e-05,
1634
+ "loss": 0.2195,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.74,
1639
+ "learning_rate": 1.5801074003145585e-05,
1640
+ "loss": 0.2063,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.74,
1645
+ "learning_rate": 1.5665565657074874e-05,
1646
+ "loss": 0.2601,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.75,
1651
+ "learning_rate": 1.5530265776426294e-05,
1652
+ "loss": 0.1633,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.76,
1657
+ "learning_rate": 1.5395180868472662e-05,
1658
+ "loss": 0.2333,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.76,
1663
+ "learning_rate": 1.5260317430147627e-05,
1664
+ "loss": 0.149,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.77,
1669
+ "learning_rate": 1.512568194773322e-05,
1670
+ "loss": 0.2587,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.78,
1675
+ "learning_rate": 1.4991280896547893e-05,
1676
+ "loss": 0.1951,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.78,
1681
+ "learning_rate": 1.4857120740635084e-05,
1682
+ "loss": 0.2757,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.79,
1687
+ "learning_rate": 1.472320793245233e-05,
1688
+ "loss": 0.2321,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.8,
1693
+ "learning_rate": 1.4589548912560932e-05,
1694
+ "loss": 0.2177,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.8,
1699
+ "learning_rate": 1.4456150109316192e-05,
1700
+ "loss": 0.1363,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.81,
1705
+ "learning_rate": 1.4323017938558245e-05,
1706
+ "loss": 0.1428,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.81,
1711
+ "learning_rate": 1.4190158803303498e-05,
1712
+ "loss": 0.2112,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.82,
1717
+ "learning_rate": 1.4057579093436653e-05,
1718
+ "loss": 0.2269,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.83,
1723
+ "learning_rate": 1.3925285185403406e-05,
1724
+ "loss": 0.1712,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.83,
1729
+ "learning_rate": 1.3793283441903737e-05,
1730
+ "loss": 0.1182,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.84,
1735
+ "learning_rate": 1.3661580211585947e-05,
1736
+ "loss": 0.1667,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.85,
1741
+ "learning_rate": 1.3530181828741285e-05,
1742
+ "loss": 0.2887,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.85,
1747
+ "learning_rate": 1.3399094612999291e-05,
1748
+ "loss": 0.1624,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.86,
1753
+ "learning_rate": 1.3268324869023878e-05,
1754
+ "loss": 0.2356,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.87,
1759
+ "learning_rate": 1.313787888621009e-05,
1760
+ "loss": 0.2557,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.87,
1765
+ "learning_rate": 1.3007762938381619e-05,
1766
+ "loss": 0.2203,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.88,
1771
+ "learning_rate": 1.2877983283489062e-05,
1772
+ "loss": 0.3142,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.88,
1777
+ "learning_rate": 1.2748546163308947e-05,
1778
+ "loss": 0.16,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.89,
1783
+ "learning_rate": 1.261945780314354e-05,
1784
+ "loss": 0.1647,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.9,
1789
+ "learning_rate": 1.2490724411521406e-05,
1790
+ "loss": 0.2373,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.9,
1795
+ "learning_rate": 1.2362352179898855e-05,
1796
+ "loss": 0.1701,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.91,
1801
+ "learning_rate": 1.2234347282362129e-05,
1802
+ "loss": 0.1522,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.92,
1807
+ "learning_rate": 1.2106715875330475e-05,
1808
+ "loss": 0.1613,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 1.92,
1813
+ "learning_rate": 1.1979464097260039e-05,
1814
+ "loss": 0.1883,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 1.93,
1819
+ "learning_rate": 1.1852598068348642e-05,
1820
+ "loss": 0.2338,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 1.94,
1825
+ "learning_rate": 1.1726123890241439e-05,
1826
+ "loss": 0.2248,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 1.94,
1831
+ "learning_rate": 1.1600047645737433e-05,
1832
+ "loss": 0.1811,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 1.95,
1837
+ "learning_rate": 1.1474375398496948e-05,
1838
+ "loss": 0.1893,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 1.96,
1843
+ "learning_rate": 1.1349113192749986e-05,
1844
+ "loss": 0.203,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 1.96,
1849
+ "learning_rate": 1.1224267053005504e-05,
1850
+ "loss": 0.1425,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 1.97,
1855
+ "learning_rate": 1.1099842983761712e-05,
1856
+ "loss": 0.1337,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 1.97,
1861
+ "learning_rate": 1.0975846969217258e-05,
1862
+ "loss": 0.1684,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 1.98,
1867
+ "learning_rate": 1.0852284972983415e-05,
1868
+ "loss": 0.165,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 1.99,
1873
+ "learning_rate": 1.0729162937797257e-05,
1874
+ "loss": 0.2462,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 1.99,
1879
+ "learning_rate": 1.0606486785235879e-05,
1880
+ "loss": 0.2298,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 2.0,
1885
+ "learning_rate": 1.0484262415431536e-05,
1886
+ "loss": 0.2047,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 2.01,
1891
+ "learning_rate": 1.0362495706787923e-05,
1892
+ "loss": 0.2365,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 2.01,
1897
+ "learning_rate": 1.0241192515697432e-05,
1898
+ "loss": 0.1738,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 2.02,
1903
+ "learning_rate": 1.0120358676259508e-05,
1904
+ "loss": 0.2467,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 2.03,
1909
+ "learning_rate": 1.0000000000000006e-05,
1910
+ "loss": 0.1459,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 2.03,
1915
+ "learning_rate": 9.880122275591752e-06,
1916
+ "loss": 0.1594,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 2.04,
1921
+ "learning_rate": 9.760731268576095e-06,
1922
+ "loss": 0.1145,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 2.04,
1927
+ "learning_rate": 9.64183272108562e-06,
1928
+ "loss": 0.1485,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 2.05,
1933
+ "learning_rate": 9.523432351567979e-06,
1934
+ "loss": 0.0932,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 2.06,
1939
+ "learning_rate": 9.405535854510863e-06,
1940
+ "loss": 0.1819,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 2.06,
1945
+ "learning_rate": 9.288148900168122e-06,
1946
+ "loss": 0.1534,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 2.07,
1951
+ "learning_rate": 9.171277134287057e-06,
1952
+ "loss": 0.1875,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 2.08,
1957
+ "learning_rate": 9.054926177836878e-06,
1958
+ "loss": 0.1416,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 2.08,
1963
+ "learning_rate": 8.939101626738395e-06,
1964
+ "loss": 0.1717,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 2.09,
1969
+ "learning_rate": 8.823809051594816e-06,
1970
+ "loss": 0.1975,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 2.1,
1975
+ "learning_rate": 8.70905399742389e-06,
1976
+ "loss": 0.1706,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 2.1,
1981
+ "learning_rate": 8.594841983391196e-06,
1982
+ "loss": 0.1869,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 2.11,
1987
+ "learning_rate": 8.481178502544684e-06,
1988
+ "loss": 0.2313,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 2.12,
1993
+ "learning_rate": 8.368069021550516e-06,
1994
+ "loss": 0.1843,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 2.12,
1999
+ "learning_rate": 8.255518980430115e-06,
2000
+ "loss": 0.2359,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 2.13,
2005
+ "learning_rate": 8.143533792298545e-06,
2006
+ "loss": 0.1243,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 2.13,
2011
+ "learning_rate": 8.032118843104164e-06,
2012
+ "loss": 0.1325,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 2.14,
2017
+ "learning_rate": 7.921279491369575e-06,
2018
+ "loss": 0.099,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 2.15,
2023
+ "learning_rate": 7.811021067933919e-06,
2024
+ "loss": 0.2295,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 2.15,
2029
+ "learning_rate": 7.701348875696486e-06,
2030
+ "loss": 0.1494,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 2.16,
2035
+ "learning_rate": 7.59226818936166e-06,
2036
+ "loss": 0.1063,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 2.17,
2041
+ "learning_rate": 7.483784255185249e-06,
2042
+ "loss": 0.1389,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 2.17,
2047
+ "learning_rate": 7.375902290722146e-06,
2048
+ "loss": 0.176,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 2.18,
2053
+ "learning_rate": 7.268627484575406e-06,
2054
+ "loss": 0.142,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 2.19,
2059
+ "learning_rate": 7.161964996146689e-06,
2060
+ "loss": 0.2029,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 2.19,
2065
+ "learning_rate": 7.055919955388122e-06,
2066
+ "loss": 0.1416,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 2.2,
2071
+ "learning_rate": 6.95049746255557e-06,
2072
+ "loss": 0.1515,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 2.2,
2077
+ "learning_rate": 6.845702587963352e-06,
2078
+ "loss": 0.1573,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 2.21,
2083
+ "learning_rate": 6.741540371740347e-06,
2084
+ "loss": 0.2249,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 2.22,
2089
+ "learning_rate": 6.6380158235876335e-06,
2090
+ "loss": 0.2207,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 2.22,
2095
+ "learning_rate": 6.535133922537513e-06,
2096
+ "loss": 0.1194,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 2.23,
2101
+ "learning_rate": 6.4328996167140786e-06,
2102
+ "loss": 0.1655,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 2.24,
2107
+ "learning_rate": 6.331317823095184e-06,
2108
+ "loss": 0.1652,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 2.24,
2113
+ "learning_rate": 6.230393427276e-06,
2114
+ "loss": 0.2378,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 2.25,
2119
+ "learning_rate": 6.130131283234031e-06,
2120
+ "loss": 0.229,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 2.26,
2125
+ "learning_rate": 6.0305362130956504e-06,
2126
+ "loss": 0.1397,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 2.26,
2131
+ "learning_rate": 5.931613006904196e-06,
2132
+ "loss": 0.1139,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 2.27,
2137
+ "learning_rate": 5.8333664223895906e-06,
2138
+ "loss": 0.1611,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 2.27,
2143
+ "learning_rate": 5.735801184739489e-06,
2144
+ "loss": 0.1784,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 2.28,
2149
+ "learning_rate": 5.638921986372064e-06,
2150
+ "loss": 0.2004,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 2.29,
2155
+ "learning_rate": 5.542733486710299e-06,
2156
+ "loss": 0.1553,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 2.29,
2161
+ "learning_rate": 5.447240311957891e-06,
2162
+ "loss": 0.1787,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 2.3,
2167
+ "learning_rate": 5.352447054876755e-06,
2168
+ "loss": 0.1856,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 2.31,
2173
+ "learning_rate": 5.258358274566142e-06,
2174
+ "loss": 0.2069,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 2.31,
2179
+ "learning_rate": 5.164978496243354e-06,
2180
+ "loss": 0.2023,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 2.32,
2185
+ "learning_rate": 5.072312211026125e-06,
2186
+ "loss": 0.1453,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 2.33,
2191
+ "learning_rate": 4.980363875716592e-06,
2192
+ "loss": 0.1377,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 2.33,
2197
+ "learning_rate": 4.889137912586972e-06,
2198
+ "loss": 0.1887,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 2.34,
2203
+ "learning_rate": 4.7986387091668365e-06,
2204
+ "loss": 0.0932,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 2.35,
2209
+ "learning_rate": 4.708870618032133e-06,
2210
+ "loss": 0.1506,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 2.35,
2215
+ "learning_rate": 4.619837956595825e-06,
2216
+ "loss": 0.1293,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 2.36,
2221
+ "learning_rate": 4.531545006900244e-06,
2222
+ "loss": 0.1505,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 2.36,
2227
+ "learning_rate": 4.443996015411151e-06,
2228
+ "loss": 0.1176,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 2.37,
2233
+ "learning_rate": 4.357195192813504e-06,
2234
+ "loss": 0.2187,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 2.38,
2239
+ "learning_rate": 4.271146713808927e-06,
2240
+ "loss": 0.1538,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 2.38,
2245
+ "learning_rate": 4.185854716914952e-06,
2246
+ "loss": 0.2165,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 2.39,
2251
+ "learning_rate": 4.1013233042659606e-06,
2252
+ "loss": 0.1662,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 2.4,
2257
+ "learning_rate": 4.017556541415888e-06,
2258
+ "loss": 0.143,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 2.4,
2263
+ "learning_rate": 3.9345584571427055e-06,
2264
+ "loss": 0.1883,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 2.41,
2269
+ "learning_rate": 3.852333043254639e-06,
2270
+ "loss": 0.1624,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 2.42,
2275
+ "learning_rate": 3.7708842543981928e-06,
2276
+ "loss": 0.1824,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 2.42,
2281
+ "learning_rate": 3.690216007867944e-06,
2282
+ "loss": 0.1933,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 2.43,
2287
+ "learning_rate": 3.6103321834181437e-06,
2288
+ "loss": 0.1557,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 2.43,
2293
+ "learning_rate": 3.5312366230761154e-06,
2294
+ "loss": 0.143,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 2.44,
2299
+ "learning_rate": 3.452933130957481e-06,
2300
+ "loss": 0.1588,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 2.45,
2305
+ "learning_rate": 3.375425473083185e-06,
2306
+ "loss": 0.1964,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 2.45,
2311
+ "learning_rate": 3.2987173771983816e-06,
2312
+ "loss": 0.1688,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 2.46,
2317
+ "learning_rate": 3.2228125325931514e-06,
2318
+ "loss": 0.1837,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 2.47,
2323
+ "learning_rate": 3.1477145899250326e-06,
2324
+ "loss": 0.1463,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 2.47,
2329
+ "learning_rate": 3.073427161043492e-06,
2330
+ "loss": 0.2133,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 2.48,
2335
+ "learning_rate": 2.9999538188161705e-06,
2336
+ "loss": 0.1345,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 2.49,
2341
+ "learning_rate": 2.927298096957063e-06,
2342
+ "loss": 0.2226,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 2.49,
2347
+ "learning_rate": 2.8554634898565668e-06,
2348
+ "loss": 0.1664,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 2.5,
2353
+ "learning_rate": 2.784453452413405e-06,
2354
+ "loss": 0.1388,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 2.5,
2359
+ "learning_rate": 2.714271399868473e-06,
2360
+ "loss": 0.2065,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 2.51,
2365
+ "learning_rate": 2.6449207076405857e-06,
2366
+ "loss": 0.1353,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 2.52,
2371
+ "learning_rate": 2.57640471116412e-06,
2372
+ "loss": 0.1601,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 2.52,
2377
+ "learning_rate": 2.508726705728617e-06,
2378
+ "loss": 0.2478,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 2.53,
2383
+ "learning_rate": 2.441889946320266e-06,
2384
+ "loss": 0.1515,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 2.54,
2389
+ "learning_rate": 2.3758976474653904e-06,
2390
+ "loss": 0.11,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 2.54,
2395
+ "learning_rate": 2.310752983075819e-06,
2396
+ "loss": 0.179,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 2.55,
2401
+ "learning_rate": 2.2464590862962443e-06,
2402
+ "loss": 0.1746,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 2.56,
2407
+ "learning_rate": 2.1830190493535385e-06,
2408
+ "loss": 0.1632,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 2.56,
2413
+ "learning_rate": 2.1204359234080196e-06,
2414
+ "loss": 0.2318,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 2.57,
2419
+ "learning_rate": 2.058712718406719e-06,
2420
+ "loss": 0.2058,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 2.58,
2425
+ "learning_rate": 1.9978524029386026e-06,
2426
+ "loss": 0.1229,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 2.58,
2431
+ "learning_rate": 1.937857904091818e-06,
2432
+ "loss": 0.1819,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 2.59,
2437
+ "learning_rate": 1.8787321073128817e-06,
2438
+ "loss": 0.1619,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 2.59,
2443
+ "learning_rate": 1.8204778562679437e-06,
2444
+ "loss": 0.1799,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 2.6,
2449
+ "learning_rate": 1.7630979527059877e-06,
2450
+ "loss": 0.1823,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 2.61,
2455
+ "learning_rate": 1.7065951563241022e-06,
2456
+ "loss": 0.1946,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 2.61,
2461
+ "learning_rate": 1.6509721846347382e-06,
2462
+ "loss": 0.1903,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 2.62,
2467
+ "learning_rate": 1.5962317128350147e-06,
2468
+ "loss": 0.1675,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 2.63,
2473
+ "learning_rate": 1.5423763736780583e-06,
2474
+ "loss": 0.1545,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 2.63,
2479
+ "learning_rate": 1.4894087573463734e-06,
2480
+ "loss": 0.1292,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 2.64,
2485
+ "learning_rate": 1.437331411327274e-06,
2486
+ "loss": 0.1341,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 2.65,
2491
+ "learning_rate": 1.3861468402903634e-06,
2492
+ "loss": 0.1419,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 2.65,
2497
+ "learning_rate": 1.3358575059670532e-06,
2498
+ "loss": 0.2009,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 2.66,
2503
+ "learning_rate": 1.2864658270321905e-06,
2504
+ "loss": 0.1272,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 2.66,
2509
+ "learning_rate": 1.2379741789877175e-06,
2510
+ "loss": 0.1821,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 2.67,
2515
+ "learning_rate": 1.1903848940484241e-06,
2516
+ "loss": 0.1756,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 2.68,
2521
+ "learning_rate": 1.1437002610297787e-06,
2522
+ "loss": 0.1342,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 2.68,
2527
+ "learning_rate": 1.097922525237849e-06,
2528
+ "loss": 0.2193,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 2.69,
2533
+ "learning_rate": 1.0530538883613129e-06,
2534
+ "loss": 0.1873,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 2.7,
2539
+ "learning_rate": 1.0090965083655657e-06,
2540
+ "loss": 0.2289,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 2.7,
2545
+ "learning_rate": 9.660524993889386e-07,
2546
+ "loss": 0.1694,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 2.71,
2551
+ "learning_rate": 9.239239316410109e-07,
2552
+ "loss": 0.1551,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 2.72,
2557
+ "learning_rate": 8.827128313030453e-07,
2558
+ "loss": 0.2198,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 2.72,
2563
+ "learning_rate": 8.42421180430546e-07,
2564
+ "loss": 0.1434,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 2.73,
2569
+ "learning_rate": 8.03050916857917e-07,
2570
+ "loss": 0.2212,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 2.73,
2575
+ "learning_rate": 7.646039341052747e-07,
2576
+ "loss": 0.214,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 2.74,
2581
+ "learning_rate": 7.270820812873714e-07,
2582
+ "loss": 0.1959,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 2.75,
2587
+ "learning_rate": 6.904871630246646e-07,
2588
+ "loss": 0.1571,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 2.75,
2593
+ "learning_rate": 6.548209393565241e-07,
2594
+ "loss": 0.1282,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 2.76,
2599
+ "learning_rate": 6.200851256565799e-07,
2600
+ "loss": 0.0944,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 2.77,
2605
+ "learning_rate": 5.862813925502209e-07,
2606
+ "loss": 0.1417,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 2.77,
2611
+ "learning_rate": 5.53411365834251e-07,
2612
+ "loss": 0.2177,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 2.78,
2617
+ "learning_rate": 5.214766263986848e-07,
2618
+ "loss": 0.1399,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 2.79,
2623
+ "learning_rate": 4.904787101507324e-07,
2624
+ "loss": 0.1264,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 2.79,
2629
+ "learning_rate": 4.604191079409126e-07,
2630
+ "loss": 0.1468,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 2.8,
2635
+ "learning_rate": 4.3129926549136057e-07,
2636
+ "loss": 0.1082,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 2.81,
2641
+ "learning_rate": 4.031205833262863e-07,
2642
+ "loss": 0.1996,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 2.81,
2647
+ "learning_rate": 3.7588441670462827e-07,
2648
+ "loss": 0.159,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 2.82,
2653
+ "learning_rate": 3.4959207555485873e-07,
2654
+ "loss": 0.1389,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 2.82,
2659
+ "learning_rate": 3.242448244119967e-07,
2660
+ "loss": 0.1808,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 2.83,
2665
+ "learning_rate": 2.99843882356774e-07,
2666
+ "loss": 0.1019,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 2.84,
2671
+ "learning_rate": 2.7639042295702245e-07,
2672
+ "loss": 0.1137,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 2.84,
2677
+ "learning_rate": 2.5388557421120564e-07,
2678
+ "loss": 0.2141,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 2.85,
2683
+ "learning_rate": 2.3233041849419547e-07,
2684
+ "loss": 0.1763,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 2.86,
2689
+ "learning_rate": 2.1172599250519398e-07,
2690
+ "loss": 0.1588,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 2.86,
2695
+ "learning_rate": 1.9207328721788653e-07,
2696
+ "loss": 0.2067,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 2.87,
2701
+ "learning_rate": 1.7337324783276878e-07,
2702
+ "loss": 0.1241,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 2.88,
2707
+ "learning_rate": 1.5562677373169855e-07,
2708
+ "loss": 0.1489,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 2.88,
2713
+ "learning_rate": 1.388347184346328e-07,
2714
+ "loss": 0.136,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 2.89,
2719
+ "learning_rate": 1.2299788955857817e-07,
2720
+ "loss": 0.1723,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 2.89,
2725
+ "learning_rate": 1.0811704877875528e-07,
2726
+ "loss": 0.227,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 2.9,
2731
+ "learning_rate": 9.419291179195267e-08,
2732
+ "loss": 0.1729,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 2.91,
2737
+ "learning_rate": 8.122614828211861e-08,
2738
+ "loss": 0.1533,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 2.91,
2743
+ "learning_rate": 6.921738188814254e-08,
2744
+ "loss": 0.1285,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 2.92,
2749
+ "learning_rate": 5.816719017386785e-08,
2750
+ "loss": 0.2263,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 2.93,
2755
+ "learning_rate": 4.807610460030976e-08,
2756
+ "loss": 0.1303,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 2.93,
2761
+ "learning_rate": 3.894461050010012e-08,
2762
+ "loss": 0.1302,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 2.94,
2767
+ "learning_rate": 3.077314705413503e-08,
2768
+ "loss": 0.1507,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 2.95,
2773
+ "learning_rate": 2.356210727046504e-08,
2774
+ "loss": 0.2156,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 2.95,
2779
+ "learning_rate": 1.7311837965379164e-08,
2780
+ "loss": 0.2267,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 2.96,
2785
+ "learning_rate": 1.202263974674045e-08,
2786
+ "loss": 0.2884,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 2.96,
2791
+ "learning_rate": 7.694766999513104e-09,
2792
+ "loss": 0.163,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 2.97,
2797
+ "learning_rate": 4.328427873541152e-09,
2798
+ "loss": 0.1972,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 2.98,
2803
+ "learning_rate": 1.9237842735275737e-09,
2804
+ "loss": 0.1847,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 2.98,
2809
+ "learning_rate": 4.809518512494116e-10,
2810
+ "loss": 0.2029,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 2.99,
2815
+ "learning_rate": 0.0,
2816
+ "loss": 0.1615,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 2.99,
2821
+ "step": 468,
2822
+ "total_flos": 4.256702100026721e+21,
2823
+ "train_loss": 0.3061195729762061,
2824
+ "train_runtime": 5033.3609,
2825
+ "train_samples_per_second": 5.958,
2826
+ "train_steps_per_second": 0.093
2827
+ }
2828
+ ],
2829
+ "logging_steps": 1.0,
2830
+ "max_steps": 468,
2831
+ "num_input_tokens_seen": 0,
2832
+ "num_train_epochs": 3,
2833
+ "save_steps": 200,
2834
+ "total_flos": 4.256702100026721e+21,
2835
+ "train_batch_size": 8,
2836
+ "trial_name": null,
2837
+ "trial_params": null
2838
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d3d5c3efb7261d08cb5ce5aa813634f864a1c2a7db3124b079c96a51cffb73
3
+ size 6264
training_log.txt ADDED
The diff for this file is too large to render. See raw diff