Hugging Face's logo

kkfy
/
one-align-icmeugcvqa-ntireugc

Feature Extraction
Transformers
PyTorch
mplug_owl2
custom_code
Model card Files Community
kkfy commited on
Commit
258ab6f
•
1 Parent(s): c26da00

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. config.json +192 -0
  2. generation_config.json +6 -0
  3. preprocessor_config.json +20 -0
  4. pytorch_model-00001-of-00004.bin +3 -0
  5. pytorch_model-00002-of-00004.bin +3 -0
  6. pytorch_model-00003-of-00004.bin +3 -0
  7. pytorch_model-00004-of-00004.bin +3 -0
  8. pytorch_model.bin.index.json +869 -0
  9. special_tokens_map.json +24 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +42 -0
  12. trainer_state.json +3162 -0
  13. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "our_res/one-align-ntire-ugcset-epoch1-randomselectframesort-randomreverse-new-randomcrop-resample-rank1cls1",
3
+ "architectures": [
4
+ "MPLUGOwl2LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_mplug_owl2.MPLUGOwl2Config",
10
+ "AutoModel": "modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM",
11
+ "AutoModelForCausalLM": "modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM"
12
+ },
13
+ "bos_token_id": 1,
14
+ "eos_token_id": 2,
15
+ "freeze_vision_model": false,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 4096,
18
+ "image_aspect_ratio": "pad",
19
+ "image_grid_pinpoints": null,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 11008,
22
+ "max_position_embeddings": 2048,
23
+ "model_type": "mplug_owl2",
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 32,
26
+ "num_key_value_heads": 32,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_scaling": null,
30
+ "rope_theta": 10000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.36.1",
34
+ "tune_visual_abstractor": true,
35
+ "use_cache": true,
36
+ "visual_abstractor_lr": null,
37
+ "visual_config": {
38
+ "visual_abstractor": {
39
+ "_name_or_path": "",
40
+ "add_cross_attention": false,
41
+ "architectures": null,
42
+ "attention_probs_dropout_prob": 0.0,
43
+ "bad_words_ids": null,
44
+ "begin_suppress_tokens": null,
45
+ "bos_token_id": null,
46
+ "chunk_size_feed_forward": 0,
47
+ "cross_attention_hidden_size": null,
48
+ "decoder_start_token_id": null,
49
+ "diversity_penalty": 0.0,
50
+ "do_sample": false,
51
+ "early_stopping": false,
52
+ "encoder_hidden_size": 1024,
53
+ "encoder_no_repeat_ngram_size": 0,
54
+ "eos_token_id": null,
55
+ "exponential_decay_length_penalty": null,
56
+ "finetuning_task": null,
57
+ "forced_bos_token_id": null,
58
+ "forced_eos_token_id": null,
59
+ "grid_size": 32,
60
+ "hidden_size": 1024,
61
+ "id2label": {
62
+ "0": "LABEL_0",
63
+ "1": "LABEL_1"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 2816,
67
+ "is_decoder": false,
68
+ "is_encoder_decoder": false,
69
+ "label2id": {
70
+ "LABEL_0": 0,
71
+ "LABEL_1": 1
72
+ },
73
+ "layer_norm_eps": 1e-06,
74
+ "length_penalty": 1.0,
75
+ "max_length": 20,
76
+ "min_length": 0,
77
+ "model_type": "mplug_owl_visual_abstract",
78
+ "no_repeat_ngram_size": 0,
79
+ "num_attention_heads": 16,
80
+ "num_beam_groups": 1,
81
+ "num_beams": 1,
82
+ "num_hidden_layers": 6,
83
+ "num_learnable_queries": 64,
84
+ "num_return_sequences": 1,
85
+ "output_attentions": false,
86
+ "output_hidden_states": false,
87
+ "output_scores": false,
88
+ "pad_token_id": null,
89
+ "prefix": null,
90
+ "problem_type": null,
91
+ "pruned_heads": {},
92
+ "remove_invalid_values": false,
93
+ "repetition_penalty": 1.0,
94
+ "return_dict": true,
95
+ "return_dict_in_generate": false,
96
+ "sep_token_id": null,
97
+ "suppress_tokens": null,
98
+ "task_specific_params": null,
99
+ "temperature": 1.0,
100
+ "tf_legacy_loss": false,
101
+ "tie_encoder_decoder": false,
102
+ "tie_word_embeddings": true,
103
+ "tokenizer_class": null,
104
+ "top_k": 50,
105
+ "top_p": 1.0,
106
+ "torch_dtype": null,
107
+ "torchscript": false,
108
+ "transformers_version": "4.28.1",
109
+ "typical_p": 1.0,
110
+ "use_bfloat16": false
111
+ },
112
+ "visual_model": {
113
+ "_name_or_path": "",
114
+ "add_cross_attention": false,
115
+ "architectures": null,
116
+ "attention_dropout": 0.0,
117
+ "bad_words_ids": null,
118
+ "begin_suppress_tokens": null,
119
+ "bos_token_id": null,
120
+ "chunk_size_feed_forward": 0,
121
+ "cross_attention_hidden_size": null,
122
+ "decoder_start_token_id": null,
123
+ "diversity_penalty": 0.0,
124
+ "do_sample": false,
125
+ "early_stopping": false,
126
+ "encoder_no_repeat_ngram_size": 0,
127
+ "eos_token_id": null,
128
+ "exponential_decay_length_penalty": null,
129
+ "finetuning_task": null,
130
+ "forced_bos_token_id": null,
131
+ "forced_eos_token_id": null,
132
+ "hidden_act": "quick_gelu",
133
+ "hidden_size": 1024,
134
+ "id2label": {
135
+ "0": "LABEL_0",
136
+ "1": "LABEL_1"
137
+ },
138
+ "image_size": 448,
139
+ "initializer_factor": 1.0,
140
+ "initializer_range": 0.02,
141
+ "intermediate_size": 4096,
142
+ "is_decoder": false,
143
+ "is_encoder_decoder": false,
144
+ "label2id": {
145
+ "LABEL_0": 0,
146
+ "LABEL_1": 1
147
+ },
148
+ "layer_norm_eps": 1e-06,
149
+ "length_penalty": 1.0,
150
+ "max_length": 20,
151
+ "min_length": 0,
152
+ "model_type": "mplug_owl_vision_model",
153
+ "no_repeat_ngram_size": 0,
154
+ "num_attention_heads": 16,
155
+ "num_beam_groups": 1,
156
+ "num_beams": 1,
157
+ "num_channels": 3,
158
+ "num_hidden_layers": 24,
159
+ "num_return_sequences": 1,
160
+ "output_attentions": false,
161
+ "output_hidden_states": false,
162
+ "output_scores": false,
163
+ "pad_token_id": null,
164
+ "patch_size": 14,
165
+ "prefix": null,
166
+ "problem_type": null,
167
+ "projection_dim": 768,
168
+ "pruned_heads": {},
169
+ "remove_invalid_values": false,
170
+ "repetition_penalty": 1.0,
171
+ "return_dict": true,
172
+ "return_dict_in_generate": false,
173
+ "sep_token_id": null,
174
+ "suppress_tokens": null,
175
+ "task_specific_params": null,
176
+ "temperature": 1.0,
177
+ "tf_legacy_loss": false,
178
+ "tie_encoder_decoder": false,
179
+ "tie_word_embeddings": true,
180
+ "tokenizer_class": null,
181
+ "top_k": 50,
182
+ "top_p": 1.0,
183
+ "torch_dtype": null,
184
+ "torchscript": false,
185
+ "transformers_version": "4.28.1",
186
+ "typical_p": 1.0,
187
+ "use_bfloat16": false,
188
+ "use_flash_attn": false
189
+ }
190
+ },
191
+ "vocab_size": 32000
192
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.1"
6
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 448,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 448
19
+ }
20
+
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea00429feafe6debaa0543c4f418dc5827fa118e80565367f09883e215cdb429
3
+ size 4981108780
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71b55f0b3370ffacbcfc1cd6cc577dda5e6a7f52597fb71f18e56dd372a1ce8
3
+ size 4920293259
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca0d532d80c286d7f6707b987b97772d141a7856f46b88035aa64011a2dcd98
3
+ size 4989532454
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54d7b8fd4c94d8f5cc0d8b112be1ac1af91760e3d1c73618bf3b83d624ccb2b5
3
+ size 1518469929
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,869 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16409100288
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.0.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.0.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.1.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.1.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.1.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
27
+ "model.layers.1.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
28
+ "model.layers.1.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
29
+ "model.layers.1.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
30
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
31
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
32
+ "model.layers.1.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
33
+ "model.layers.1.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
34
+ "model.layers.10.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
35
+ "model.layers.10.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
36
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
37
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
38
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "model.layers.10.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
40
+ "model.layers.10.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.10.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
42
+ "model.layers.10.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
43
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.10.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.10.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.11.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.11.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.11.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.11.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.11.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.11.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.11.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.11.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.12.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.12.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.12.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.12.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.12.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.12.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.12.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.12.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.13.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.13.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.13.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.13.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.13.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.13.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.13.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.13.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.14.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.14.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
90
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "model.layers.14.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.14.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
93
+ "model.layers.14.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
94
+ "model.layers.14.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.14.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.14.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
99
+ "model.layers.15.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
100
+ "model.layers.15.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
101
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
102
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
103
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
104
+ "model.layers.15.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
105
+ "model.layers.15.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
106
+ "model.layers.15.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
107
+ "model.layers.15.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
108
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
109
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
110
+ "model.layers.15.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
111
+ "model.layers.15.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
112
+ "model.layers.16.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
113
+ "model.layers.16.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
114
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
115
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
116
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
117
+ "model.layers.16.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
118
+ "model.layers.16.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
119
+ "model.layers.16.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
120
+ "model.layers.16.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
121
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
122
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
123
+ "model.layers.16.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
124
+ "model.layers.16.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
125
+ "model.layers.17.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
126
+ "model.layers.17.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
127
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
128
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
129
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
130
+ "model.layers.17.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
131
+ "model.layers.17.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
132
+ "model.layers.17.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
133
+ "model.layers.17.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
134
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
135
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
136
+ "model.layers.17.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
137
+ "model.layers.17.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
138
+ "model.layers.18.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
139
+ "model.layers.18.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
140
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
141
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
142
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
143
+ "model.layers.18.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
144
+ "model.layers.18.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
145
+ "model.layers.18.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
146
+ "model.layers.18.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
147
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
148
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
149
+ "model.layers.18.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
150
+ "model.layers.18.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
151
+ "model.layers.19.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
152
+ "model.layers.19.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
153
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
154
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
155
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
156
+ "model.layers.19.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
157
+ "model.layers.19.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
158
+ "model.layers.19.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
159
+ "model.layers.19.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
160
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
161
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
162
+ "model.layers.19.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
163
+ "model.layers.19.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
164
+ "model.layers.2.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
165
+ "model.layers.2.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
166
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
167
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
168
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
169
+ "model.layers.2.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
170
+ "model.layers.2.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
171
+ "model.layers.2.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
172
+ "model.layers.2.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
173
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
174
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
175
+ "model.layers.2.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
176
+ "model.layers.2.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
177
+ "model.layers.20.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.20.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
182
+ "model.layers.20.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.20.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
184
+ "model.layers.20.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
185
+ "model.layers.20.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
186
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
187
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
188
+ "model.layers.20.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
189
+ "model.layers.20.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
190
+ "model.layers.21.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.21.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.21.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.21.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.21.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.21.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.21.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.21.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
203
+ "model.layers.22.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.22.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
206
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "model.layers.22.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.22.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.22.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.22.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
212
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
213
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.22.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
215
+ "model.layers.22.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
216
+ "model.layers.23.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
217
+ "model.layers.23.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
218
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
219
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
220
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
221
+ "model.layers.23.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
222
+ "model.layers.23.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
223
+ "model.layers.23.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
224
+ "model.layers.23.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.23.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
228
+ "model.layers.23.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
229
+ "model.layers.24.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.24.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
234
+ "model.layers.24.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
235
+ "model.layers.24.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.24.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
237
+ "model.layers.24.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
238
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
239
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
240
+ "model.layers.24.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
241
+ "model.layers.24.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
242
+ "model.layers.25.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
243
+ "model.layers.25.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
244
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
245
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
246
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
247
+ "model.layers.25.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
248
+ "model.layers.25.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
249
+ "model.layers.25.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
250
+ "model.layers.25.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
251
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
252
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
253
+ "model.layers.25.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
254
+ "model.layers.25.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
255
+ "model.layers.26.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
256
+ "model.layers.26.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
257
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
258
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
259
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
260
+ "model.layers.26.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
261
+ "model.layers.26.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
262
+ "model.layers.26.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
263
+ "model.layers.26.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
264
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
265
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
266
+ "model.layers.26.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
267
+ "model.layers.26.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
268
+ "model.layers.27.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
269
+ "model.layers.27.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
270
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
271
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
272
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
273
+ "model.layers.27.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
274
+ "model.layers.27.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
275
+ "model.layers.27.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
276
+ "model.layers.27.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
277
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
278
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
279
+ "model.layers.27.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
280
+ "model.layers.27.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
281
+ "model.layers.28.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
282
+ "model.layers.28.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
283
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
284
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
285
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
286
+ "model.layers.28.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
287
+ "model.layers.28.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
288
+ "model.layers.28.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
289
+ "model.layers.28.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
290
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
291
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
292
+ "model.layers.28.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
293
+ "model.layers.28.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
294
+ "model.layers.29.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
295
+ "model.layers.29.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
296
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
297
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
298
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
299
+ "model.layers.29.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
300
+ "model.layers.29.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
301
+ "model.layers.29.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
302
+ "model.layers.29.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
303
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
304
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
305
+ "model.layers.29.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
306
+ "model.layers.29.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
307
+ "model.layers.3.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
308
+ "model.layers.3.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
309
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
310
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
311
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
312
+ "model.layers.3.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
313
+ "model.layers.3.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
314
+ "model.layers.3.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
315
+ "model.layers.3.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
316
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
317
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
318
+ "model.layers.3.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
319
+ "model.layers.3.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
320
+ "model.layers.30.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
321
+ "model.layers.30.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
322
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
323
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
324
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
325
+ "model.layers.30.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
326
+ "model.layers.30.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
327
+ "model.layers.30.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
328
+ "model.layers.30.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
329
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
330
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
331
+ "model.layers.30.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
332
+ "model.layers.30.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
333
+ "model.layers.31.input_layernorm.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
334
+ "model.layers.31.input_layernorm.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
335
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
336
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
337
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
338
+ "model.layers.31.post_attention_layernorm.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
339
+ "model.layers.31.post_attention_layernorm.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
340
+ "model.layers.31.self_attn.k_proj.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
341
+ "model.layers.31.self_attn.k_proj.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
342
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
343
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
344
+ "model.layers.31.self_attn.v_proj.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
345
+ "model.layers.31.self_attn.v_proj.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
346
+ "model.layers.4.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
347
+ "model.layers.4.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
348
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
349
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
350
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
351
+ "model.layers.4.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
352
+ "model.layers.4.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
353
+ "model.layers.4.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
354
+ "model.layers.4.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
355
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
356
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
357
+ "model.layers.4.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
358
+ "model.layers.4.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
359
+ "model.layers.5.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
360
+ "model.layers.5.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
361
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
362
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
363
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
364
+ "model.layers.5.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
365
+ "model.layers.5.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
366
+ "model.layers.5.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
367
+ "model.layers.5.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
368
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
369
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
370
+ "model.layers.5.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
371
+ "model.layers.5.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
372
+ "model.layers.6.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
373
+ "model.layers.6.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
374
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
375
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
376
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
377
+ "model.layers.6.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
378
+ "model.layers.6.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
379
+ "model.layers.6.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
380
+ "model.layers.6.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
381
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
382
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
383
+ "model.layers.6.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
384
+ "model.layers.6.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
385
+ "model.layers.7.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
386
+ "model.layers.7.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
387
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
388
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
389
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
390
+ "model.layers.7.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
391
+ "model.layers.7.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
392
+ "model.layers.7.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
393
+ "model.layers.7.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
394
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
395
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
396
+ "model.layers.7.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
397
+ "model.layers.7.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
398
+ "model.layers.8.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
399
+ "model.layers.8.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
400
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
401
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
402
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
403
+ "model.layers.8.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
404
+ "model.layers.8.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
405
+ "model.layers.8.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
406
+ "model.layers.8.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
407
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
408
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
409
+ "model.layers.8.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
410
+ "model.layers.8.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
411
+ "model.layers.9.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
412
+ "model.layers.9.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
413
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
414
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
415
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
416
+ "model.layers.9.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
417
+ "model.layers.9.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
418
+ "model.layers.9.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
419
+ "model.layers.9.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
420
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
421
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
422
+ "model.layers.9.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
423
+ "model.layers.9.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
424
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin",
425
+ "model.vision_model.embeddings.cls_token": "pytorch_model-00004-of-00004.bin",
426
+ "model.vision_model.embeddings.patch_embed.weight": "pytorch_model-00004-of-00004.bin",
427
+ "model.vision_model.embeddings.position_embedding": "pytorch_model-00004-of-00004.bin",
428
+ "model.vision_model.embeddings.pre_layernorm.bias": "pytorch_model-00004-of-00004.bin",
429
+ "model.vision_model.embeddings.pre_layernorm.weight": "pytorch_model-00004-of-00004.bin",
430
+ "model.vision_model.encoder.layers.0.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
431
+ "model.vision_model.encoder.layers.0.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
432
+ "model.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
433
+ "model.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
434
+ "model.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
435
+ "model.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
436
+ "model.vision_model.encoder.layers.0.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
437
+ "model.vision_model.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
438
+ "model.vision_model.encoder.layers.0.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
439
+ "model.vision_model.encoder.layers.0.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
440
+ "model.vision_model.encoder.layers.0.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
441
+ "model.vision_model.encoder.layers.0.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
442
+ "model.vision_model.encoder.layers.1.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
443
+ "model.vision_model.encoder.layers.1.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
444
+ "model.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
445
+ "model.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
446
+ "model.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
447
+ "model.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
448
+ "model.vision_model.encoder.layers.1.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
449
+ "model.vision_model.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
450
+ "model.vision_model.encoder.layers.1.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
451
+ "model.vision_model.encoder.layers.1.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
452
+ "model.vision_model.encoder.layers.1.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
453
+ "model.vision_model.encoder.layers.1.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
454
+ "model.vision_model.encoder.layers.10.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
455
+ "model.vision_model.encoder.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
456
+ "model.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
457
+ "model.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
458
+ "model.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
459
+ "model.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
460
+ "model.vision_model.encoder.layers.10.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
461
+ "model.vision_model.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
462
+ "model.vision_model.encoder.layers.10.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
463
+ "model.vision_model.encoder.layers.10.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
464
+ "model.vision_model.encoder.layers.10.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
465
+ "model.vision_model.encoder.layers.10.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
466
+ "model.vision_model.encoder.layers.11.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
467
+ "model.vision_model.encoder.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
468
+ "model.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
469
+ "model.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
470
+ "model.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
471
+ "model.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
472
+ "model.vision_model.encoder.layers.11.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
473
+ "model.vision_model.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
474
+ "model.vision_model.encoder.layers.11.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
475
+ "model.vision_model.encoder.layers.11.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
476
+ "model.vision_model.encoder.layers.11.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
477
+ "model.vision_model.encoder.layers.11.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
478
+ "model.vision_model.encoder.layers.12.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
479
+ "model.vision_model.encoder.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
480
+ "model.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
481
+ "model.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
482
+ "model.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
483
+ "model.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
484
+ "model.vision_model.encoder.layers.12.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
485
+ "model.vision_model.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
486
+ "model.vision_model.encoder.layers.12.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
487
+ "model.vision_model.encoder.layers.12.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
488
+ "model.vision_model.encoder.layers.12.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
489
+ "model.vision_model.encoder.layers.12.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
490
+ "model.vision_model.encoder.layers.13.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
491
+ "model.vision_model.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
492
+ "model.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
493
+ "model.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
494
+ "model.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
495
+ "model.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
496
+ "model.vision_model.encoder.layers.13.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
497
+ "model.vision_model.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
498
+ "model.vision_model.encoder.layers.13.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
499
+ "model.vision_model.encoder.layers.13.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
500
+ "model.vision_model.encoder.layers.13.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
501
+ "model.vision_model.encoder.layers.13.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
502
+ "model.vision_model.encoder.layers.14.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
503
+ "model.vision_model.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
504
+ "model.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
505
+ "model.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
506
+ "model.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
507
+ "model.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
508
+ "model.vision_model.encoder.layers.14.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
509
+ "model.vision_model.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
510
+ "model.vision_model.encoder.layers.14.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
511
+ "model.vision_model.encoder.layers.14.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
512
+ "model.vision_model.encoder.layers.14.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
513
+ "model.vision_model.encoder.layers.14.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
514
+ "model.vision_model.encoder.layers.15.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
515
+ "model.vision_model.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
516
+ "model.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
517
+ "model.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
518
+ "model.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
519
+ "model.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
520
+ "model.vision_model.encoder.layers.15.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
521
+ "model.vision_model.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
522
+ "model.vision_model.encoder.layers.15.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
523
+ "model.vision_model.encoder.layers.15.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
524
+ "model.vision_model.encoder.layers.15.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
525
+ "model.vision_model.encoder.layers.15.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
526
+ "model.vision_model.encoder.layers.16.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
527
+ "model.vision_model.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
528
+ "model.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
529
+ "model.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
530
+ "model.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
531
+ "model.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
532
+ "model.vision_model.encoder.layers.16.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
533
+ "model.vision_model.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
534
+ "model.vision_model.encoder.layers.16.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
535
+ "model.vision_model.encoder.layers.16.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
536
+ "model.vision_model.encoder.layers.16.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
537
+ "model.vision_model.encoder.layers.16.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
538
+ "model.vision_model.encoder.layers.17.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
539
+ "model.vision_model.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
540
+ "model.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
541
+ "model.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
542
+ "model.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
543
+ "model.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
544
+ "model.vision_model.encoder.layers.17.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
545
+ "model.vision_model.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
546
+ "model.vision_model.encoder.layers.17.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
547
+ "model.vision_model.encoder.layers.17.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
548
+ "model.vision_model.encoder.layers.17.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
549
+ "model.vision_model.encoder.layers.17.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
550
+ "model.vision_model.encoder.layers.18.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
551
+ "model.vision_model.encoder.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
552
+ "model.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
553
+ "model.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
554
+ "model.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
555
+ "model.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
556
+ "model.vision_model.encoder.layers.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
557
+ "model.vision_model.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
558
+ "model.vision_model.encoder.layers.18.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
559
+ "model.vision_model.encoder.layers.18.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
560
+ "model.vision_model.encoder.layers.18.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
561
+ "model.vision_model.encoder.layers.18.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
562
+ "model.vision_model.encoder.layers.19.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
563
+ "model.vision_model.encoder.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
564
+ "model.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
565
+ "model.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
566
+ "model.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
567
+ "model.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
568
+ "model.vision_model.encoder.layers.19.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
569
+ "model.vision_model.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
570
+ "model.vision_model.encoder.layers.19.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
571
+ "model.vision_model.encoder.layers.19.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
572
+ "model.vision_model.encoder.layers.19.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
573
+ "model.vision_model.encoder.layers.19.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
574
+ "model.vision_model.encoder.layers.2.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
575
+ "model.vision_model.encoder.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
576
+ "model.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
577
+ "model.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
578
+ "model.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
579
+ "model.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
580
+ "model.vision_model.encoder.layers.2.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
581
+ "model.vision_model.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
582
+ "model.vision_model.encoder.layers.2.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
583
+ "model.vision_model.encoder.layers.2.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
584
+ "model.vision_model.encoder.layers.2.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
585
+ "model.vision_model.encoder.layers.2.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
586
+ "model.vision_model.encoder.layers.20.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
587
+ "model.vision_model.encoder.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
588
+ "model.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
589
+ "model.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
590
+ "model.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
591
+ "model.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
592
+ "model.vision_model.encoder.layers.20.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
593
+ "model.vision_model.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
594
+ "model.vision_model.encoder.layers.20.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
595
+ "model.vision_model.encoder.layers.20.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
596
+ "model.vision_model.encoder.layers.20.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
597
+ "model.vision_model.encoder.layers.20.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
598
+ "model.vision_model.encoder.layers.21.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
599
+ "model.vision_model.encoder.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
600
+ "model.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
601
+ "model.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
602
+ "model.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
603
+ "model.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
604
+ "model.vision_model.encoder.layers.21.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
605
+ "model.vision_model.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
606
+ "model.vision_model.encoder.layers.21.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
607
+ "model.vision_model.encoder.layers.21.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
608
+ "model.vision_model.encoder.layers.21.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
609
+ "model.vision_model.encoder.layers.21.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
610
+ "model.vision_model.encoder.layers.22.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
611
+ "model.vision_model.encoder.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
612
+ "model.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
613
+ "model.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
614
+ "model.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
615
+ "model.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
616
+ "model.vision_model.encoder.layers.22.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
617
+ "model.vision_model.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
618
+ "model.vision_model.encoder.layers.22.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
619
+ "model.vision_model.encoder.layers.22.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
620
+ "model.vision_model.encoder.layers.22.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
621
+ "model.vision_model.encoder.layers.22.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
622
+ "model.vision_model.encoder.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
623
+ "model.vision_model.encoder.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
624
+ "model.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
625
+ "model.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
626
+ "model.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
627
+ "model.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
628
+ "model.vision_model.encoder.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
629
+ "model.vision_model.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
630
+ "model.vision_model.encoder.layers.23.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
631
+ "model.vision_model.encoder.layers.23.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
632
+ "model.vision_model.encoder.layers.23.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
633
+ "model.vision_model.encoder.layers.23.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
634
+ "model.vision_model.encoder.layers.3.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
635
+ "model.vision_model.encoder.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
636
+ "model.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
637
+ "model.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
638
+ "model.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
639
+ "model.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
640
+ "model.vision_model.encoder.layers.3.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
641
+ "model.vision_model.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
642
+ "model.vision_model.encoder.layers.3.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
643
+ "model.vision_model.encoder.layers.3.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
644
+ "model.vision_model.encoder.layers.3.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
645
+ "model.vision_model.encoder.layers.3.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
646
+ "model.vision_model.encoder.layers.4.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
647
+ "model.vision_model.encoder.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
648
+ "model.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
649
+ "model.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
650
+ "model.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
651
+ "model.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
652
+ "model.vision_model.encoder.layers.4.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
653
+ "model.vision_model.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
654
+ "model.vision_model.encoder.layers.4.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
655
+ "model.vision_model.encoder.layers.4.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
656
+ "model.vision_model.encoder.layers.4.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
657
+ "model.vision_model.encoder.layers.4.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
658
+ "model.vision_model.encoder.layers.5.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
659
+ "model.vision_model.encoder.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
660
+ "model.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
661
+ "model.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
662
+ "model.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
663
+ "model.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
664
+ "model.vision_model.encoder.layers.5.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
665
+ "model.vision_model.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
666
+ "model.vision_model.encoder.layers.5.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
667
+ "model.vision_model.encoder.layers.5.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
668
+ "model.vision_model.encoder.layers.5.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
669
+ "model.vision_model.encoder.layers.5.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
670
+ "model.vision_model.encoder.layers.6.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
671
+ "model.vision_model.encoder.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
672
+ "model.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
673
+ "model.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
674
+ "model.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
675
+ "model.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
676
+ "model.vision_model.encoder.layers.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
677
+ "model.vision_model.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
678
+ "model.vision_model.encoder.layers.6.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
679
+ "model.vision_model.encoder.layers.6.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
680
+ "model.vision_model.encoder.layers.6.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
681
+ "model.vision_model.encoder.layers.6.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
682
+ "model.vision_model.encoder.layers.7.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
683
+ "model.vision_model.encoder.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
684
+ "model.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
685
+ "model.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
686
+ "model.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
687
+ "model.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
688
+ "model.vision_model.encoder.layers.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
689
+ "model.vision_model.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
690
+ "model.vision_model.encoder.layers.7.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
691
+ "model.vision_model.encoder.layers.7.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
692
+ "model.vision_model.encoder.layers.7.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
693
+ "model.vision_model.encoder.layers.7.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
694
+ "model.vision_model.encoder.layers.8.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
695
+ "model.vision_model.encoder.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
696
+ "model.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
697
+ "model.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
698
+ "model.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
699
+ "model.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
700
+ "model.vision_model.encoder.layers.8.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
701
+ "model.vision_model.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
702
+ "model.vision_model.encoder.layers.8.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
703
+ "model.vision_model.encoder.layers.8.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
704
+ "model.vision_model.encoder.layers.8.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
705
+ "model.vision_model.encoder.layers.8.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
706
+ "model.vision_model.encoder.layers.9.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
707
+ "model.vision_model.encoder.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
708
+ "model.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
709
+ "model.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
710
+ "model.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
711
+ "model.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
712
+ "model.vision_model.encoder.layers.9.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
713
+ "model.vision_model.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
714
+ "model.vision_model.encoder.layers.9.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
715
+ "model.vision_model.encoder.layers.9.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
716
+ "model.vision_model.encoder.layers.9.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
717
+ "model.vision_model.encoder.layers.9.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
718
+ "model.vision_model.post_layernorm.bias": "pytorch_model-00004-of-00004.bin",
719
+ "model.vision_model.post_layernorm.weight": "pytorch_model-00004-of-00004.bin",
720
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
721
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
722
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
723
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
724
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
725
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
726
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
727
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
728
+ "model.visual_abstractor.encoder.layers.0.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
729
+ "model.visual_abstractor.encoder.layers.0.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
730
+ "model.visual_abstractor.encoder.layers.0.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
731
+ "model.visual_abstractor.encoder.layers.0.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
732
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
733
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
734
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
735
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
736
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
737
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
738
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
739
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
740
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
741
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
742
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
743
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
744
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
745
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
746
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
747
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
748
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
749
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
750
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
751
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
752
+ "model.visual_abstractor.encoder.layers.1.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
753
+ "model.visual_abstractor.encoder.layers.1.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
754
+ "model.visual_abstractor.encoder.layers.1.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
755
+ "model.visual_abstractor.encoder.layers.1.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
756
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
757
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
758
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
759
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
760
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
761
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
762
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
763
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
764
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
765
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
766
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
767
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
768
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
769
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
770
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
771
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
772
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
773
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
774
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
775
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
776
+ "model.visual_abstractor.encoder.layers.2.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
777
+ "model.visual_abstractor.encoder.layers.2.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
778
+ "model.visual_abstractor.encoder.layers.2.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
779
+ "model.visual_abstractor.encoder.layers.2.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
780
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
781
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
782
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
783
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
784
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
785
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
786
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
787
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
788
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
789
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
790
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
791
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
792
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
793
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
794
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
795
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
796
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
797
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
798
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
799
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
800
+ "model.visual_abstractor.encoder.layers.3.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
801
+ "model.visual_abstractor.encoder.layers.3.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
802
+ "model.visual_abstractor.encoder.layers.3.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
803
+ "model.visual_abstractor.encoder.layers.3.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
804
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
805
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
806
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
807
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
808
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
809
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
810
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
811
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
812
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
813
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
814
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
815
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
816
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
817
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
818
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
819
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
820
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
821
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
822
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
823
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
824
+ "model.visual_abstractor.encoder.layers.4.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
825
+ "model.visual_abstractor.encoder.layers.4.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
826
+ "model.visual_abstractor.encoder.layers.4.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
827
+ "model.visual_abstractor.encoder.layers.4.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
828
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
829
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
830
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
831
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
832
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
833
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
834
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
835
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
836
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
837
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
838
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
839
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
840
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
841
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
842
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
843
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
844
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
845
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
846
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
847
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
848
+ "model.visual_abstractor.encoder.layers.5.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
849
+ "model.visual_abstractor.encoder.layers.5.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
850
+ "model.visual_abstractor.encoder.layers.5.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
851
+ "model.visual_abstractor.encoder.layers.5.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
852
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
853
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
854
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
855
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
856
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
857
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
858
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
859
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
860
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
861
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
862
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
863
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
864
+ "model.visual_abstractor.query_embeds": "pytorch_model-00004-of-00004.bin",
865
+ "model.visual_abstractor.visual_fc.bias": "pytorch_model-00004-of-00004.bin",
866
+ "model.visual_abstractor.visual_fc.weight": "pytorch_model-00004-of-00004.bin",
867
+ "model.visual_abstractor.vit_eos": "pytorch_model-00004-of-00004.bin"
868
+ }
869
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 2048,
35
+ "pad_token": "<unk>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
trainer_state.json ADDED
@@ -0,0 +1,3162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 522,
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": 1.25e-06,
14
+ "loss": 0.2765,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2.5e-06,
20
+ "loss": 0.3431,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 3.7500000000000005e-06,
26
+ "loss": 0.3124,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 5e-06,
32
+ "loss": 0.3076,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 6.25e-06,
38
+ "loss": 0.2718,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 7.500000000000001e-06,
44
+ "loss": 0.1714,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 8.750000000000001e-06,
50
+ "loss": 0.2527,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 1e-05,
56
+ "loss": 0.2631,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 1.125e-05,
62
+ "loss": 0.2238,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 1.25e-05,
68
+ "loss": 0.248,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 1.375e-05,
74
+ "loss": 0.2666,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 1.5000000000000002e-05,
80
+ "loss": 0.2083,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 1.6250000000000002e-05,
86
+ "loss": 0.1746,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 1.7500000000000002e-05,
92
+ "loss": 0.1791,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 1.8750000000000002e-05,
98
+ "loss": 0.2358,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 2e-05,
104
+ "loss": 0.2399,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 1.9999807262012045e-05,
110
+ "loss": 0.1813,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.1,
115
+ "learning_rate": 1.9999229055477764e-05,
116
+ "loss": 0.1674,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 1.999826540268562e-05,
122
+ "loss": 0.1757,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.11,
127
+ "learning_rate": 1.999691634078213e-05,
128
+ "loss": 0.1642,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 1.999518192177038e-05,
134
+ "loss": 0.1927,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 1.9993062212508054e-05,
140
+ "loss": 0.1804,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.13,
145
+ "learning_rate": 1.9990557294704857e-05,
146
+ "loss": 0.1726,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.14,
151
+ "learning_rate": 1.998766726491935e-05,
152
+ "loss": 0.1665,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.14,
157
+ "learning_rate": 1.998439223455524e-05,
158
+ "loss": 0.1611,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 1.9980732329857077e-05,
164
+ "loss": 0.1685,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.16,
169
+ "learning_rate": 1.9976687691905394e-05,
170
+ "loss": 0.1503,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.16,
175
+ "learning_rate": 1.997225847661127e-05,
176
+ "loss": 0.155,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.17,
181
+ "learning_rate": 1.9967444854710313e-05,
182
+ "loss": 0.1278,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.17,
187
+ "learning_rate": 1.996224701175608e-05,
188
+ "loss": 0.1516,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.18,
193
+ "learning_rate": 1.9956665148112936e-05,
194
+ "loss": 0.1586,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.18,
199
+ "learning_rate": 1.995069947894831e-05,
200
+ "loss": 0.1419,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.19,
205
+ "learning_rate": 1.9944350234224415e-05,
206
+ "loss": 0.127,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.2,
211
+ "learning_rate": 1.9937617658689385e-05,
212
+ "loss": 0.1428,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.2,
217
+ "learning_rate": 1.993050201186783e-05,
218
+ "loss": 0.1233,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.21,
223
+ "learning_rate": 1.9923003568050846e-05,
224
+ "loss": 0.1267,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.21,
229
+ "learning_rate": 1.991512261628542e-05,
230
+ "loss": 0.1085,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.22,
235
+ "learning_rate": 1.9906859460363307e-05,
236
+ "loss": 0.1196,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.22,
241
+ "learning_rate": 1.989821441880933e-05,
242
+ "loss": 0.1081,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.23,
247
+ "learning_rate": 1.988918782486906e-05,
248
+ "loss": 0.1016,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.24,
253
+ "learning_rate": 1.987978002649601e-05,
254
+ "loss": 0.1202,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.24,
259
+ "learning_rate": 1.986999138633821e-05,
260
+ "loss": 0.0963,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.25,
265
+ "learning_rate": 1.9859822281724218e-05,
266
+ "loss": 0.1064,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.25,
271
+ "learning_rate": 1.9849273104648592e-05,
272
+ "loss": 0.1919,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.26,
277
+ "learning_rate": 1.9838344261756755e-05,
278
+ "loss": 0.1058,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.26,
283
+ "learning_rate": 1.9827036174329355e-05,
284
+ "loss": 0.1003,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.27,
289
+ "learning_rate": 1.981534927826599e-05,
290
+ "loss": 0.1484,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.28,
295
+ "learning_rate": 1.9803284024068428e-05,
296
+ "loss": 0.1591,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.28,
301
+ "learning_rate": 1.979084087682323e-05,
302
+ "loss": 0.1178,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.29,
307
+ "learning_rate": 1.9778020316183834e-05,
308
+ "loss": 0.1231,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.29,
313
+ "learning_rate": 1.9764822836352046e-05,
314
+ "loss": 0.11,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.3,
319
+ "learning_rate": 1.9751248946059016e-05,
320
+ "loss": 0.1231,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.3,
325
+ "learning_rate": 1.97372991685456e-05,
326
+ "loss": 0.1077,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.31,
331
+ "learning_rate": 1.9722974041542205e-05,
332
+ "loss": 0.0854,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.32,
337
+ "learning_rate": 1.9708274117248067e-05,
338
+ "loss": 0.1268,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.32,
343
+ "learning_rate": 1.969319996230995e-05,
344
+ "loss": 0.1285,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.33,
349
+ "learning_rate": 1.9677752157800316e-05,
350
+ "loss": 0.1178,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.33,
355
+ "learning_rate": 1.966193129919491e-05,
356
+ "loss": 0.1077,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.34,
361
+ "learning_rate": 1.9645737996349828e-05,
362
+ "loss": 0.0975,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.34,
367
+ "learning_rate": 1.9629172873477995e-05,
368
+ "loss": 0.1049,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.35,
373
+ "learning_rate": 1.9612236569125093e-05,
374
+ "loss": 0.0843,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.36,
379
+ "learning_rate": 1.9594929736144978e-05,
380
+ "loss": 0.1513,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.36,
385
+ "learning_rate": 1.957725304167447e-05,
386
+ "loss": 0.0983,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.37,
391
+ "learning_rate": 1.9559207167107684e-05,
392
+ "loss": 0.079,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.37,
397
+ "learning_rate": 1.9540792808069726e-05,
398
+ "loss": 0.0924,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.38,
403
+ "learning_rate": 1.95220106743899e-05,
404
+ "loss": 0.0964,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.39,
409
+ "learning_rate": 1.950286149007434e-05,
410
+ "loss": 0.1039,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.39,
415
+ "learning_rate": 1.948334599327809e-05,
416
+ "loss": 0.0935,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.4,
421
+ "learning_rate": 1.9463464936276676e-05,
422
+ "loss": 0.0951,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.4,
427
+ "learning_rate": 1.944321908543708e-05,
428
+ "loss": 0.1086,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.41,
433
+ "learning_rate": 1.9422609221188208e-05,
434
+ "loss": 0.0648,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.41,
439
+ "learning_rate": 1.9401636137990814e-05,
440
+ "loss": 0.0676,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.42,
445
+ "learning_rate": 1.938030064430688e-05,
446
+ "loss": 0.106,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.43,
451
+ "learning_rate": 1.9358603562568417e-05,
452
+ "loss": 0.074,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.43,
457
+ "learning_rate": 1.933654572914581e-05,
458
+ "loss": 0.0809,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.44,
463
+ "learning_rate": 1.931412799431554e-05,
464
+ "loss": 0.0787,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.44,
469
+ "learning_rate": 1.929135122222743e-05,
470
+ "loss": 0.0788,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.45,
475
+ "learning_rate": 1.926821629087133e-05,
476
+ "loss": 0.0882,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.45,
481
+ "learning_rate": 1.924472409204326e-05,
482
+ "loss": 0.0901,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.46,
487
+ "learning_rate": 1.9220875531311044e-05,
488
+ "loss": 0.0523,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.47,
493
+ "learning_rate": 1.9196671527979407e-05,
494
+ "loss": 0.0643,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.47,
499
+ "learning_rate": 1.917211301505453e-05,
500
+ "loss": 0.0738,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.48,
505
+ "learning_rate": 1.9147200939208088e-05,
506
+ "loss": 0.0986,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.48,
511
+ "learning_rate": 1.9121936260740752e-05,
512
+ "loss": 0.066,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.49,
517
+ "learning_rate": 1.9096319953545186e-05,
518
+ "loss": 0.0891,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.49,
523
+ "learning_rate": 1.9070353005068484e-05,
524
+ "loss": 0.0782,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.5,
529
+ "learning_rate": 1.9044036416274133e-05,
530
+ "loss": 0.0544,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.51,
535
+ "learning_rate": 1.901737120160341e-05,
536
+ "loss": 0.0851,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.51,
541
+ "learning_rate": 1.899035838893627e-05,
542
+ "loss": 0.0894,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.52,
547
+ "learning_rate": 1.8962999019551755e-05,
548
+ "loss": 0.0763,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.52,
553
+ "learning_rate": 1.8935294148087822e-05,
554
+ "loss": 0.0534,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.53,
559
+ "learning_rate": 1.8907244842500706e-05,
560
+ "loss": 0.0789,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.53,
565
+ "learning_rate": 1.8878852184023754e-05,
566
+ "loss": 0.0699,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.54,
571
+ "learning_rate": 1.885011726712574e-05,
572
+ "loss": 0.0532,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.55,
577
+ "learning_rate": 1.8821041199468677e-05,
578
+ "loss": 0.1086,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.55,
583
+ "learning_rate": 1.8791625101865117e-05,
584
+ "loss": 0.0813,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.56,
589
+ "learning_rate": 1.876187010823496e-05,
590
+ "loss": 0.074,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.56,
595
+ "learning_rate": 1.8731777365561723e-05,
596
+ "loss": 0.0609,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.57,
601
+ "learning_rate": 1.870134803384834e-05,
602
+ "loss": 0.0476,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.57,
607
+ "learning_rate": 1.8670583286072443e-05,
608
+ "loss": 0.0883,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.58,
613
+ "learning_rate": 1.8639484308141157e-05,
614
+ "loss": 0.1177,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.59,
619
+ "learning_rate": 1.860805229884536e-05,
620
+ "loss": 0.0849,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.59,
625
+ "learning_rate": 1.8576288469813506e-05,
626
+ "loss": 0.0621,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.6,
631
+ "learning_rate": 1.8544194045464888e-05,
632
+ "loss": 0.1144,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.6,
637
+ "learning_rate": 1.8511770262962462e-05,
638
+ "loss": 0.1004,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.61,
643
+ "learning_rate": 1.8479018372165148e-05,
644
+ "loss": 0.0804,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.61,
649
+ "learning_rate": 1.8445939635579658e-05,
650
+ "loss": 0.069,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.62,
655
+ "learning_rate": 1.8412535328311813e-05,
656
+ "loss": 0.0603,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.63,
661
+ "learning_rate": 1.837880673801741e-05,
662
+ "loss": 0.0692,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.63,
667
+ "learning_rate": 1.8344755164852572e-05,
668
+ "loss": 0.0732,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.64,
673
+ "learning_rate": 1.8310381921423644e-05,
674
+ "loss": 0.0797,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.64,
679
+ "learning_rate": 1.8275688332736577e-05,
680
+ "loss": 0.0643,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.65,
685
+ "learning_rate": 1.8240675736145866e-05,
686
+ "loss": 0.0617,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.66,
691
+ "learning_rate": 1.8205345481303e-05,
692
+ "loss": 0.0647,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.66,
697
+ "learning_rate": 1.816969893010442e-05,
698
+ "loss": 0.074,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.67,
703
+ "learning_rate": 1.8133737456639043e-05,
704
+ "loss": 0.0546,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.67,
709
+ "learning_rate": 1.8097462447135273e-05,
710
+ "loss": 0.0712,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.68,
715
+ "learning_rate": 1.806087529990758e-05,
716
+ "loss": 0.0758,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.68,
721
+ "learning_rate": 1.802397742530259e-05,
722
+ "loss": 0.0612,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.69,
727
+ "learning_rate": 1.7986770245644728e-05,
728
+ "loss": 0.0797,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.7,
733
+ "learning_rate": 1.7949255195181387e-05,
734
+ "loss": 0.0663,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.7,
739
+ "learning_rate": 1.7911433720027624e-05,
740
+ "loss": 0.0885,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.71,
745
+ "learning_rate": 1.787330727811045e-05,
746
+ "loss": 0.0664,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.71,
751
+ "learning_rate": 1.7834877339112613e-05,
752
+ "loss": 0.0708,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.72,
757
+ "learning_rate": 1.779614538441593e-05,
758
+ "loss": 0.085,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.72,
763
+ "learning_rate": 1.77571129070442e-05,
764
+ "loss": 0.0798,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.73,
769
+ "learning_rate": 1.771778141160566e-05,
770
+ "loss": 0.0991,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.74,
775
+ "learning_rate": 1.767815241423497e-05,
776
+ "loss": 0.0429,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.74,
781
+ "learning_rate": 1.763822744253477e-05,
782
+ "loss": 0.076,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.75,
787
+ "learning_rate": 1.75980080355168e-05,
788
+ "loss": 0.0776,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.75,
793
+ "learning_rate": 1.7557495743542586e-05,
794
+ "loss": 0.0684,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.76,
799
+ "learning_rate": 1.7516692128263647e-05,
800
+ "loss": 0.0427,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.76,
805
+ "learning_rate": 1.7475598762561333e-05,
806
+ "loss": 0.0813,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.77,
811
+ "learning_rate": 1.7434217230486162e-05,
812
+ "loss": 0.0673,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.78,
817
+ "learning_rate": 1.739254912719679e-05,
818
+ "loss": 0.0407,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.78,
823
+ "learning_rate": 1.7350596058898482e-05,
824
+ "loss": 0.0584,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.79,
829
+ "learning_rate": 1.730835964278124e-05,
830
+ "loss": 0.0787,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.79,
835
+ "learning_rate": 1.726584150695744e-05,
836
+ "loss": 0.0502,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.8,
841
+ "learning_rate": 1.7223043290399065e-05,
842
+ "loss": 0.0392,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.8,
847
+ "learning_rate": 1.7179966642874543e-05,
848
+ "loss": 0.0395,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.81,
853
+ "learning_rate": 1.7136613224885157e-05,
854
+ "loss": 0.0593,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.82,
859
+ "learning_rate": 1.7092984707601007e-05,
860
+ "loss": 0.033,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.82,
865
+ "learning_rate": 1.7049082772796635e-05,
866
+ "loss": 0.0344,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.83,
871
+ "learning_rate": 1.7004909112786142e-05,
872
+ "loss": 0.0461,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.83,
877
+ "learning_rate": 1.696046543035801e-05,
878
+ "loss": 0.0563,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.84,
883
+ "learning_rate": 1.6915753438709415e-05,
884
+ "loss": 0.0432,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.84,
889
+ "learning_rate": 1.687077486138023e-05,
890
+ "loss": 0.0601,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.85,
895
+ "learning_rate": 1.6825531432186545e-05,
896
+ "loss": 0.0454,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.86,
901
+ "learning_rate": 1.6780024895153862e-05,
902
+ "loss": 0.0689,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.86,
907
+ "learning_rate": 1.6734257004449863e-05,
908
+ "loss": 0.0489,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.87,
913
+ "learning_rate": 1.6688229524316782e-05,
914
+ "loss": 0.074,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.87,
919
+ "learning_rate": 1.6641944229003395e-05,
920
+ "loss": 0.0508,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.88,
925
+ "learning_rate": 1.6595402902696648e-05,
926
+ "loss": 0.0642,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.89,
931
+ "learning_rate": 1.6548607339452853e-05,
932
+ "loss": 0.0747,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.89,
937
+ "learning_rate": 1.6501559343128553e-05,
938
+ "loss": 0.0862,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.9,
943
+ "learning_rate": 1.645426072731098e-05,
944
+ "loss": 0.0303,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.9,
949
+ "learning_rate": 1.640671331524814e-05,
950
+ "loss": 0.0739,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.91,
955
+ "learning_rate": 1.6358918939778538e-05,
956
+ "loss": 0.058,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.91,
961
+ "learning_rate": 1.631087944326053e-05,
962
+ "loss": 0.0627,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.92,
967
+ "learning_rate": 1.6262596677501297e-05,
968
+ "loss": 0.0567,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.93,
973
+ "learning_rate": 1.621407250368546e-05,
974
+ "loss": 0.0874,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.93,
979
+ "learning_rate": 1.616530879230335e-05,
980
+ "loss": 0.0395,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.94,
985
+ "learning_rate": 1.611630742307889e-05,
986
+ "loss": 0.0676,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.94,
991
+ "learning_rate": 1.606707028489714e-05,
992
+ "loss": 0.0519,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.95,
997
+ "learning_rate": 1.6017599275731482e-05,
998
+ "loss": 0.0662,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.95,
1003
+ "learning_rate": 1.5967896302570485e-05,
1004
+ "loss": 0.0402,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.96,
1009
+ "learning_rate": 1.5917963281344346e-05,
1010
+ "loss": 0.0852,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.97,
1015
+ "learning_rate": 1.5867802136851078e-05,
1016
+ "loss": 0.0364,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.97,
1021
+ "learning_rate": 1.5817414802682292e-05,
1022
+ "loss": 0.0571,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.98,
1027
+ "learning_rate": 1.5766803221148676e-05,
1028
+ "loss": 0.0583,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.98,
1033
+ "learning_rate": 1.5715969343205094e-05,
1034
+ "loss": 0.064,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.99,
1039
+ "learning_rate": 1.566491512837543e-05,
1040
+ "loss": 0.0674,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.99,
1045
+ "learning_rate": 1.561364254467701e-05,
1046
+ "loss": 0.0675,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 1.0,
1051
+ "learning_rate": 1.5562153568544753e-05,
1052
+ "loss": 0.0629,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.01,
1057
+ "learning_rate": 1.5510450184754996e-05,
1058
+ "loss": 0.0552,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.01,
1063
+ "learning_rate": 1.5458534386348967e-05,
1064
+ "loss": 0.0655,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.02,
1069
+ "learning_rate": 1.5406408174555978e-05,
1070
+ "loss": 0.0379,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.02,
1075
+ "learning_rate": 1.535407355871626e-05,
1076
+ "loss": 0.0606,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.03,
1081
+ "learning_rate": 1.5301532556203524e-05,
1082
+ "loss": 0.0369,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.03,
1087
+ "learning_rate": 1.5248787192347196e-05,
1088
+ "loss": 0.0467,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.04,
1093
+ "learning_rate": 1.5195839500354337e-05,
1094
+ "loss": 0.0426,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.05,
1099
+ "learning_rate": 1.5142691521231267e-05,
1100
+ "loss": 0.0487,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.05,
1105
+ "learning_rate": 1.5089345303704901e-05,
1106
+ "loss": 0.0386,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.06,
1111
+ "learning_rate": 1.503580290414376e-05,
1112
+ "loss": 0.0447,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.06,
1117
+ "learning_rate": 1.4982066386478727e-05,
1118
+ "loss": 0.0516,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.07,
1123
+ "learning_rate": 1.4928137822123451e-05,
1124
+ "loss": 0.0489,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.07,
1129
+ "learning_rate": 1.4874019289894536e-05,
1130
+ "loss": 0.0266,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.08,
1135
+ "learning_rate": 1.481971287593138e-05,
1136
+ "loss": 0.062,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.09,
1141
+ "learning_rate": 1.4765220673615774e-05,
1142
+ "loss": 0.0329,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.09,
1147
+ "learning_rate": 1.471054478349121e-05,
1148
+ "loss": 0.0272,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.1,
1153
+ "learning_rate": 1.4655687313181896e-05,
1154
+ "loss": 0.034,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.1,
1159
+ "learning_rate": 1.4600650377311523e-05,
1160
+ "loss": 0.0498,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.11,
1165
+ "learning_rate": 1.4545436097421745e-05,
1166
+ "loss": 0.0623,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.11,
1171
+ "learning_rate": 1.4490046601890405e-05,
1172
+ "loss": 0.0633,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.12,
1177
+ "learning_rate": 1.4434484025849494e-05,
1178
+ "loss": 0.0606,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.13,
1183
+ "learning_rate": 1.4378750511102826e-05,
1184
+ "loss": 0.0357,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.13,
1189
+ "learning_rate": 1.4322848206043505e-05,
1190
+ "loss": 0.051,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.14,
1195
+ "learning_rate": 1.4266779265571087e-05,
1196
+ "loss": 0.0528,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.14,
1201
+ "learning_rate": 1.4210545851008529e-05,
1202
+ "loss": 0.0441,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.15,
1207
+ "learning_rate": 1.4154150130018867e-05,
1208
+ "loss": 0.0355,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 1.16,
1213
+ "learning_rate": 1.4097594276521658e-05,
1214
+ "loss": 0.0393,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 1.16,
1219
+ "learning_rate": 1.4040880470609186e-05,
1220
+ "loss": 0.0474,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 1.17,
1225
+ "learning_rate": 1.3984010898462417e-05,
1226
+ "loss": 0.0493,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 1.17,
1231
+ "learning_rate": 1.3926987752266733e-05,
1232
+ "loss": 0.0819,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 1.18,
1237
+ "learning_rate": 1.3869813230127432e-05,
1238
+ "loss": 0.0538,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 1.18,
1243
+ "learning_rate": 1.381248953598498e-05,
1244
+ "loss": 0.0543,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 1.19,
1249
+ "learning_rate": 1.3755018879530075e-05,
1250
+ "loss": 0.0357,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 1.2,
1255
+ "learning_rate": 1.3697403476118453e-05,
1256
+ "loss": 0.041,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 1.2,
1261
+ "learning_rate": 1.36396455466855e-05,
1262
+ "loss": 0.0539,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 1.21,
1267
+ "learning_rate": 1.3581747317660641e-05,
1268
+ "loss": 0.0358,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 1.21,
1273
+ "learning_rate": 1.3523711020881504e-05,
1274
+ "loss": 0.0857,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 1.22,
1279
+ "learning_rate": 1.3465538893507908e-05,
1280
+ "loss": 0.0409,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 1.22,
1285
+ "learning_rate": 1.3407233177935608e-05,
1286
+ "loss": 0.0436,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 1.23,
1291
+ "learning_rate": 1.3348796121709862e-05,
1292
+ "loss": 0.0408,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 1.24,
1297
+ "learning_rate": 1.3290229977438802e-05,
1298
+ "loss": 0.0773,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 1.24,
1303
+ "learning_rate": 1.3231537002706594e-05,
1304
+ "loss": 0.0865,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 1.25,
1309
+ "learning_rate": 1.31727194599864e-05,
1310
+ "loss": 0.0388,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 1.25,
1315
+ "learning_rate": 1.3113779616553189e-05,
1316
+ "loss": 0.0323,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 1.26,
1321
+ "learning_rate": 1.3054719744396333e-05,
1322
+ "loss": 0.0321,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 1.26,
1327
+ "learning_rate": 1.2995542120132016e-05,
1328
+ "loss": 0.0282,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 1.27,
1333
+ "learning_rate": 1.2936249024915487e-05,
1334
+ "loss": 0.0361,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 1.28,
1339
+ "learning_rate": 1.2876842744353113e-05,
1340
+ "loss": 0.0631,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 1.28,
1345
+ "learning_rate": 1.2817325568414299e-05,
1346
+ "loss": 0.041,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 1.29,
1351
+ "learning_rate": 1.2757699791343188e-05,
1352
+ "loss": 0.0609,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 1.29,
1357
+ "learning_rate": 1.2697967711570243e-05,
1358
+ "loss": 0.0316,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 1.3,
1363
+ "learning_rate": 1.2638131631623641e-05,
1364
+ "loss": 0.0346,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 1.3,
1369
+ "learning_rate": 1.2578193858040508e-05,
1370
+ "loss": 0.0329,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 1.31,
1375
+ "learning_rate": 1.251815670127802e-05,
1376
+ "loss": 0.0587,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 1.32,
1381
+ "learning_rate": 1.2458022475624343e-05,
1382
+ "loss": 0.0608,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 1.32,
1387
+ "learning_rate": 1.2397793499109403e-05,
1388
+ "loss": 0.0513,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 1.33,
1393
+ "learning_rate": 1.2337472093415554e-05,
1394
+ "loss": 0.04,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 1.33,
1399
+ "learning_rate": 1.2277060583788065e-05,
1400
+ "loss": 0.0583,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 1.34,
1405
+ "learning_rate": 1.2216561298945502e-05,
1406
+ "loss": 0.0471,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 1.34,
1411
+ "learning_rate": 1.2155976570989949e-05,
1412
+ "loss": 0.0487,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 1.35,
1417
+ "learning_rate": 1.2095308735317126e-05,
1418
+ "loss": 0.057,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 1.36,
1423
+ "learning_rate": 1.2034560130526341e-05,
1424
+ "loss": 0.0359,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 1.36,
1429
+ "learning_rate": 1.197373309833037e-05,
1430
+ "loss": 0.0736,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 1.37,
1435
+ "learning_rate": 1.1912829983465169e-05,
1436
+ "loss": 0.04,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 1.37,
1441
+ "learning_rate": 1.1851853133599507e-05,
1442
+ "loss": 0.0418,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 1.38,
1447
+ "learning_rate": 1.1790804899244453e-05,
1448
+ "loss": 0.0269,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 1.39,
1453
+ "learning_rate": 1.1729687633662776e-05,
1454
+ "loss": 0.0537,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 1.39,
1459
+ "learning_rate": 1.1668503692778239e-05,
1460
+ "loss": 0.0373,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 1.4,
1465
+ "learning_rate": 1.1607255435084772e-05,
1466
+ "loss": 0.0509,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.4,
1471
+ "learning_rate": 1.1545945221555571e-05,
1472
+ "loss": 0.0445,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.41,
1477
+ "learning_rate": 1.1484575415552069e-05,
1478
+ "loss": 0.0641,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.41,
1483
+ "learning_rate": 1.1423148382732854e-05,
1484
+ "loss": 0.0382,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.42,
1489
+ "learning_rate": 1.1361666490962468e-05,
1490
+ "loss": 0.0244,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.43,
1495
+ "learning_rate": 1.1300132110220135e-05,
1496
+ "loss": 0.0632,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.43,
1501
+ "learning_rate": 1.12385476125084e-05,
1502
+ "loss": 0.0486,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.44,
1507
+ "learning_rate": 1.1176915371761702e-05,
1508
+ "loss": 0.0432,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.44,
1513
+ "learning_rate": 1.1115237763754856e-05,
1514
+ "loss": 0.047,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.45,
1519
+ "learning_rate": 1.1053517166011471e-05,
1520
+ "loss": 0.0298,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.45,
1525
+ "learning_rate": 1.0991755957712317e-05,
1526
+ "loss": 0.0641,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.46,
1531
+ "learning_rate": 1.0929956519603595e-05,
1532
+ "loss": 0.0479,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.47,
1537
+ "learning_rate": 1.0868121233905183e-05,
1538
+ "loss": 0.0267,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.47,
1543
+ "learning_rate": 1.080625248421878e-05,
1544
+ "loss": 0.0442,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.48,
1549
+ "learning_rate": 1.0744352655436058e-05,
1550
+ "loss": 0.0389,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.48,
1555
+ "learning_rate": 1.0682424133646712e-05,
1556
+ "loss": 0.0404,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.49,
1561
+ "learning_rate": 1.0620469306046473e-05,
1562
+ "loss": 0.0386,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.49,
1567
+ "learning_rate": 1.0558490560845107e-05,
1568
+ "loss": 0.0367,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.5,
1573
+ "learning_rate": 1.0496490287174343e-05,
1574
+ "loss": 0.0499,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.51,
1579
+ "learning_rate": 1.0434470874995781e-05,
1580
+ "loss": 0.0356,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.51,
1585
+ "learning_rate": 1.0372434715008763e-05,
1586
+ "loss": 0.0573,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.52,
1591
+ "learning_rate": 1.0310384198558226e-05,
1592
+ "loss": 0.0545,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.52,
1597
+ "learning_rate": 1.0248321717542505e-05,
1598
+ "loss": 0.0327,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.53,
1603
+ "learning_rate": 1.0186249664321139e-05,
1604
+ "loss": 0.0454,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.53,
1609
+ "learning_rate": 1.012417043162266e-05,
1610
+ "loss": 0.0501,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.54,
1615
+ "learning_rate": 1.0062086412452353e-05,
1616
+ "loss": 0.0332,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.55,
1621
+ "learning_rate": 1e-05,
1622
+ "loss": 0.0586,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.55,
1627
+ "learning_rate": 9.93791358754765e-06,
1628
+ "loss": 0.0464,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.56,
1633
+ "learning_rate": 9.875829568377343e-06,
1634
+ "loss": 0.0363,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.56,
1639
+ "learning_rate": 9.813750335678866e-06,
1640
+ "loss": 0.0939,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.57,
1645
+ "learning_rate": 9.751678282457502e-06,
1646
+ "loss": 0.025,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.57,
1651
+ "learning_rate": 9.689615801441776e-06,
1652
+ "loss": 0.0476,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.58,
1657
+ "learning_rate": 9.627565284991237e-06,
1658
+ "loss": 0.0475,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.59,
1663
+ "learning_rate": 9.56552912500422e-06,
1664
+ "loss": 0.0605,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.59,
1669
+ "learning_rate": 9.50350971282566e-06,
1670
+ "loss": 0.0391,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.6,
1675
+ "learning_rate": 9.441509439154896e-06,
1676
+ "loss": 0.0383,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.6,
1681
+ "learning_rate": 9.37953069395353e-06,
1682
+ "loss": 0.0393,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.61,
1687
+ "learning_rate": 9.317575866353293e-06,
1688
+ "loss": 0.0475,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.61,
1693
+ "learning_rate": 9.255647344563943e-06,
1694
+ "loss": 0.0302,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.62,
1699
+ "learning_rate": 9.193747515781225e-06,
1700
+ "loss": 0.0437,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.63,
1705
+ "learning_rate": 9.131878766094822e-06,
1706
+ "loss": 0.0574,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.63,
1711
+ "learning_rate": 9.070043480396404e-06,
1712
+ "loss": 0.0619,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.64,
1717
+ "learning_rate": 9.008244042287684e-06,
1718
+ "loss": 0.0475,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.64,
1723
+ "learning_rate": 8.94648283398853e-06,
1724
+ "loss": 0.0354,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.65,
1729
+ "learning_rate": 8.884762236245146e-06,
1730
+ "loss": 0.0632,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.66,
1735
+ "learning_rate": 8.8230846282383e-06,
1736
+ "loss": 0.0394,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.66,
1741
+ "learning_rate": 8.761452387491601e-06,
1742
+ "loss": 0.0677,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.67,
1747
+ "learning_rate": 8.699867889779869e-06,
1748
+ "loss": 0.0375,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.67,
1753
+ "learning_rate": 8.638333509037537e-06,
1754
+ "loss": 0.056,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.68,
1759
+ "learning_rate": 8.576851617267151e-06,
1760
+ "loss": 0.0283,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.68,
1765
+ "learning_rate": 8.515424584447935e-06,
1766
+ "loss": 0.0426,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.69,
1771
+ "learning_rate": 8.45405477844443e-06,
1772
+ "loss": 0.0432,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.7,
1777
+ "learning_rate": 8.392744564915228e-06,
1778
+ "loss": 0.0559,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.7,
1783
+ "learning_rate": 8.331496307221763e-06,
1784
+ "loss": 0.0323,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.71,
1789
+ "learning_rate": 8.270312366337227e-06,
1790
+ "loss": 0.0369,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.71,
1795
+ "learning_rate": 8.209195100755552e-06,
1796
+ "loss": 0.0459,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.72,
1801
+ "learning_rate": 8.148146866400498e-06,
1802
+ "loss": 0.0402,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.72,
1807
+ "learning_rate": 8.087170016534836e-06,
1808
+ "loss": 0.0314,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 1.73,
1813
+ "learning_rate": 8.026266901669635e-06,
1814
+ "loss": 0.063,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 1.74,
1819
+ "learning_rate": 7.965439869473664e-06,
1820
+ "loss": 0.0475,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 1.74,
1825
+ "learning_rate": 7.90469126468288e-06,
1826
+ "loss": 0.0265,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 1.75,
1831
+ "learning_rate": 7.844023429010051e-06,
1832
+ "loss": 0.0249,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 1.75,
1837
+ "learning_rate": 7.7834387010545e-06,
1838
+ "loss": 0.0455,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 1.76,
1843
+ "learning_rate": 7.722939416211938e-06,
1844
+ "loss": 0.0299,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 1.76,
1849
+ "learning_rate": 7.66252790658445e-06,
1850
+ "loss": 0.0446,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 1.77,
1855
+ "learning_rate": 7.6022065008906e-06,
1856
+ "loss": 0.0577,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 1.78,
1861
+ "learning_rate": 7.541977524375661e-06,
1862
+ "loss": 0.0295,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 1.78,
1867
+ "learning_rate": 7.481843298721982e-06,
1868
+ "loss": 0.0279,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 1.79,
1873
+ "learning_rate": 7.421806141959498e-06,
1874
+ "loss": 0.0447,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 1.79,
1879
+ "learning_rate": 7.361868368376364e-06,
1880
+ "loss": 0.0484,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 1.8,
1885
+ "learning_rate": 7.3020322884297565e-06,
1886
+ "loss": 0.0389,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 1.8,
1891
+ "learning_rate": 7.242300208656814e-06,
1892
+ "loss": 0.0457,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 1.81,
1897
+ "learning_rate": 7.182674431585703e-06,
1898
+ "loss": 0.0475,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 1.82,
1903
+ "learning_rate": 7.123157255646889e-06,
1904
+ "loss": 0.0484,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 1.82,
1909
+ "learning_rate": 7.0637509750845175e-06,
1910
+ "loss": 0.0407,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 1.83,
1915
+ "learning_rate": 7.004457879867987e-06,
1916
+ "loss": 0.0562,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 1.83,
1921
+ "learning_rate": 6.9452802556036705e-06,
1922
+ "loss": 0.0601,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 1.84,
1927
+ "learning_rate": 6.886220383446814e-06,
1928
+ "loss": 0.0369,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 1.84,
1933
+ "learning_rate": 6.827280540013607e-06,
1934
+ "loss": 0.0399,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 1.85,
1939
+ "learning_rate": 6.768462997293412e-06,
1940
+ "loss": 0.033,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 1.86,
1945
+ "learning_rate": 6.709770022561197e-06,
1946
+ "loss": 0.0388,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 1.86,
1951
+ "learning_rate": 6.651203878290139e-06,
1952
+ "loss": 0.02,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 1.87,
1957
+ "learning_rate": 6.592766822064396e-06,
1958
+ "loss": 0.0446,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 1.87,
1963
+ "learning_rate": 6.534461106492094e-06,
1964
+ "loss": 0.0471,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 1.88,
1969
+ "learning_rate": 6.476288979118497e-06,
1970
+ "loss": 0.059,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 1.89,
1975
+ "learning_rate": 6.418252682339362e-06,
1976
+ "loss": 0.0422,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 1.89,
1981
+ "learning_rate": 6.360354453314502e-06,
1982
+ "loss": 0.0318,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 1.9,
1987
+ "learning_rate": 6.30259652388155e-06,
1988
+ "loss": 0.0592,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 1.9,
1993
+ "learning_rate": 6.244981120469928e-06,
1994
+ "loss": 0.0381,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 1.91,
1999
+ "learning_rate": 6.187510464015023e-06,
2000
+ "loss": 0.0613,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 1.91,
2005
+ "learning_rate": 6.13018676987257e-06,
2006
+ "loss": 0.032,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 1.92,
2011
+ "learning_rate": 6.073012247733267e-06,
2012
+ "loss": 0.0236,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 1.93,
2017
+ "learning_rate": 6.015989101537586e-06,
2018
+ "loss": 0.058,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 1.93,
2023
+ "learning_rate": 5.959119529390818e-06,
2024
+ "loss": 0.0379,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 1.94,
2029
+ "learning_rate": 5.902405723478346e-06,
2030
+ "loss": 0.0658,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 1.94,
2035
+ "learning_rate": 5.845849869981137e-06,
2036
+ "loss": 0.0339,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 1.95,
2041
+ "learning_rate": 5.789454148991477e-06,
2042
+ "loss": 0.0224,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 1.95,
2047
+ "learning_rate": 5.733220734428919e-06,
2048
+ "loss": 0.053,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 1.96,
2053
+ "learning_rate": 5.677151793956501e-06,
2054
+ "loss": 0.0396,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 1.97,
2059
+ "learning_rate": 5.621249488897176e-06,
2060
+ "loss": 0.0335,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 1.97,
2065
+ "learning_rate": 5.5655159741505085e-06,
2066
+ "loss": 0.0265,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 1.98,
2071
+ "learning_rate": 5.5099533981095945e-06,
2072
+ "loss": 0.0394,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 1.98,
2077
+ "learning_rate": 5.454563902578256e-06,
2078
+ "loss": 0.0362,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 1.99,
2083
+ "learning_rate": 5.399349622688479e-06,
2084
+ "loss": 0.0342,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 1.99,
2089
+ "learning_rate": 5.344312686818106e-06,
2090
+ "loss": 0.0205,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 2.0,
2095
+ "learning_rate": 5.289455216508792e-06,
2096
+ "loss": 0.058,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 2.01,
2101
+ "learning_rate": 5.234779326384227e-06,
2102
+ "loss": 0.0278,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 2.01,
2107
+ "learning_rate": 5.180287124068624e-06,
2108
+ "loss": 0.0292,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 2.02,
2113
+ "learning_rate": 5.1259807101054686e-06,
2114
+ "loss": 0.0362,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 2.02,
2119
+ "learning_rate": 5.071862177876548e-06,
2120
+ "loss": 0.0431,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 2.03,
2125
+ "learning_rate": 5.017933613521273e-06,
2126
+ "loss": 0.0239,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 2.03,
2131
+ "learning_rate": 4.964197095856237e-06,
2132
+ "loss": 0.0284,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 2.04,
2137
+ "learning_rate": 4.9106546962951e-06,
2138
+ "loss": 0.0297,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 2.05,
2143
+ "learning_rate": 4.857308478768733e-06,
2144
+ "loss": 0.0295,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 2.05,
2149
+ "learning_rate": 4.804160499645667e-06,
2150
+ "loss": 0.0138,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 2.06,
2155
+ "learning_rate": 4.7512128076528065e-06,
2156
+ "loss": 0.0296,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 2.06,
2161
+ "learning_rate": 4.698467443796479e-06,
2162
+ "loss": 0.03,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 2.07,
2167
+ "learning_rate": 4.645926441283745e-06,
2168
+ "loss": 0.0298,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 2.07,
2173
+ "learning_rate": 4.593591825444028e-06,
2174
+ "loss": 0.0285,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 2.08,
2179
+ "learning_rate": 4.541465613651034e-06,
2180
+ "loss": 0.0375,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 2.09,
2185
+ "learning_rate": 4.489549815245008e-06,
2186
+ "loss": 0.0343,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 2.09,
2191
+ "learning_rate": 4.437846431455249e-06,
2192
+ "loss": 0.0372,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 2.1,
2197
+ "learning_rate": 4.3863574553229936e-06,
2198
+ "loss": 0.0331,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 2.1,
2203
+ "learning_rate": 4.335084871624572e-06,
2204
+ "loss": 0.0418,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 2.11,
2209
+ "learning_rate": 4.284030656794908e-06,
2210
+ "loss": 0.019,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 2.11,
2215
+ "learning_rate": 4.2331967788513295e-06,
2216
+ "loss": 0.0209,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 2.12,
2221
+ "learning_rate": 4.182585197317709e-06,
2222
+ "loss": 0.0498,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 2.13,
2227
+ "learning_rate": 4.132197863148925e-06,
2228
+ "loss": 0.0364,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 2.13,
2233
+ "learning_rate": 4.082036718655657e-06,
2234
+ "loss": 0.0333,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 2.14,
2239
+ "learning_rate": 4.032103697429516e-06,
2240
+ "loss": 0.0356,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 2.14,
2245
+ "learning_rate": 3.982400724268516e-06,
2246
+ "loss": 0.0302,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 2.15,
2251
+ "learning_rate": 3.932929715102863e-06,
2252
+ "loss": 0.028,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 2.16,
2257
+ "learning_rate": 3.883692576921111e-06,
2258
+ "loss": 0.0203,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 2.16,
2263
+ "learning_rate": 3.834691207696649e-06,
2264
+ "loss": 0.0181,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 2.17,
2269
+ "learning_rate": 3.785927496314543e-06,
2270
+ "loss": 0.0264,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 2.17,
2275
+ "learning_rate": 3.7374033224987084e-06,
2276
+ "loss": 0.0258,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 2.18,
2281
+ "learning_rate": 3.689120556739475e-06,
2282
+ "loss": 0.0243,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 2.18,
2287
+ "learning_rate": 3.6410810602214687e-06,
2288
+ "loss": 0.0451,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 2.19,
2293
+ "learning_rate": 3.5932866847518654e-06,
2294
+ "loss": 0.0289,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 2.2,
2299
+ "learning_rate": 3.545739272689024e-06,
2300
+ "loss": 0.0315,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 2.2,
2305
+ "learning_rate": 3.498440656871449e-06,
2306
+ "loss": 0.011,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 2.21,
2311
+ "learning_rate": 3.4513926605471504e-06,
2312
+ "loss": 0.0268,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 2.21,
2317
+ "learning_rate": 3.404597097303356e-06,
2318
+ "loss": 0.0404,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 2.22,
2323
+ "learning_rate": 3.3580557709966066e-06,
2324
+ "loss": 0.0344,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 2.22,
2329
+ "learning_rate": 3.3117704756832226e-06,
2330
+ "loss": 0.0418,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 2.23,
2335
+ "learning_rate": 3.2657429955501396e-06,
2336
+ "loss": 0.0279,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 2.24,
2341
+ "learning_rate": 3.2199751048461414e-06,
2342
+ "loss": 0.0142,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 2.24,
2347
+ "learning_rate": 3.174468567813461e-06,
2348
+ "loss": 0.0135,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 2.25,
2353
+ "learning_rate": 3.1292251386197727e-06,
2354
+ "loss": 0.0253,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 2.25,
2359
+ "learning_rate": 3.084246561290584e-06,
2360
+ "loss": 0.0154,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 2.26,
2365
+ "learning_rate": 3.039534569641992e-06,
2366
+ "loss": 0.0329,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 2.26,
2371
+ "learning_rate": 2.9950908872138585e-06,
2372
+ "loss": 0.0177,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 2.27,
2377
+ "learning_rate": 2.9509172272033683e-06,
2378
+ "loss": 0.0244,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 2.28,
2383
+ "learning_rate": 2.9070152923989947e-06,
2384
+ "loss": 0.0304,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 2.28,
2389
+ "learning_rate": 2.863386775114848e-06,
2390
+ "loss": 0.0138,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 2.29,
2395
+ "learning_rate": 2.8200333571254603e-06,
2396
+ "loss": 0.0233,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 2.29,
2401
+ "learning_rate": 2.776956709600941e-06,
2402
+ "loss": 0.0341,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 2.3,
2407
+ "learning_rate": 2.7341584930425656e-06,
2408
+ "loss": 0.0247,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 2.3,
2413
+ "learning_rate": 2.691640357218759e-06,
2414
+ "loss": 0.0332,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 2.31,
2419
+ "learning_rate": 2.6494039411015192e-06,
2420
+ "loss": 0.0301,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 2.32,
2425
+ "learning_rate": 2.6074508728032135e-06,
2426
+ "loss": 0.0209,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 2.32,
2431
+ "learning_rate": 2.565782769513837e-06,
2432
+ "loss": 0.0321,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 2.33,
2437
+ "learning_rate": 2.5244012374386695e-06,
2438
+ "loss": 0.0179,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 2.33,
2443
+ "learning_rate": 2.4833078717363544e-06,
2444
+ "loss": 0.0182,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 2.34,
2449
+ "learning_rate": 2.4425042564574186e-06,
2450
+ "loss": 0.0126,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 2.34,
2455
+ "learning_rate": 2.4019919644832023e-06,
2456
+ "loss": 0.0329,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 2.35,
2461
+ "learning_rate": 2.3617725574652352e-06,
2462
+ "loss": 0.0186,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 2.36,
2467
+ "learning_rate": 2.3218475857650347e-06,
2468
+ "loss": 0.0285,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 2.36,
2473
+ "learning_rate": 2.2822185883943404e-06,
2474
+ "loss": 0.0212,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 2.37,
2479
+ "learning_rate": 2.2428870929558012e-06,
2480
+ "loss": 0.0215,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 2.37,
2485
+ "learning_rate": 2.2038546155840733e-06,
2486
+ "loss": 0.0259,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 2.38,
2491
+ "learning_rate": 2.1651226608873876e-06,
2492
+ "loss": 0.0271,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 2.39,
2497
+ "learning_rate": 2.1266927218895507e-06,
2498
+ "loss": 0.0258,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 2.39,
2503
+ "learning_rate": 2.0885662799723807e-06,
2504
+ "loss": 0.0229,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 2.4,
2509
+ "learning_rate": 2.0507448048186205e-06,
2510
+ "loss": 0.0211,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 2.4,
2515
+ "learning_rate": 2.013229754355276e-06,
2516
+ "loss": 0.0392,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 2.41,
2521
+ "learning_rate": 1.9760225746974136e-06,
2522
+ "loss": 0.0228,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 2.41,
2527
+ "learning_rate": 1.9391247000924227e-06,
2528
+ "loss": 0.0377,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 2.42,
2533
+ "learning_rate": 1.9025375528647294e-06,
2534
+ "loss": 0.0127,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 2.43,
2539
+ "learning_rate": 1.8662625433609582e-06,
2540
+ "loss": 0.0309,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 2.43,
2545
+ "learning_rate": 1.8303010698955803e-06,
2546
+ "loss": 0.0363,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 2.44,
2551
+ "learning_rate": 1.7946545186970022e-06,
2552
+ "loss": 0.0263,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 2.44,
2557
+ "learning_rate": 1.7593242638541352e-06,
2558
+ "loss": 0.0519,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 2.45,
2563
+ "learning_rate": 1.7243116672634264e-06,
2564
+ "loss": 0.0238,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 2.45,
2569
+ "learning_rate": 1.6896180785763594e-06,
2570
+ "loss": 0.0245,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 2.46,
2575
+ "learning_rate": 1.6552448351474305e-06,
2576
+ "loss": 0.0086,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 2.47,
2581
+ "learning_rate": 1.6211932619825932e-06,
2582
+ "loss": 0.0185,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 2.47,
2587
+ "learning_rate": 1.587464671688187e-06,
2588
+ "loss": 0.0133,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 2.48,
2593
+ "learning_rate": 1.5540603644203423e-06,
2594
+ "loss": 0.0241,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 2.48,
2599
+ "learning_rate": 1.520981627834851e-06,
2600
+ "loss": 0.0219,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 2.49,
2605
+ "learning_rate": 1.4882297370375388e-06,
2606
+ "loss": 0.0271,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 2.49,
2611
+ "learning_rate": 1.4558059545351144e-06,
2612
+ "loss": 0.0196,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 2.5,
2617
+ "learning_rate": 1.423711530186498e-06,
2618
+ "loss": 0.0187,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 2.51,
2623
+ "learning_rate": 1.3919477011546423e-06,
2624
+ "loss": 0.0491,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 2.51,
2629
+ "learning_rate": 1.360515691858847e-06,
2630
+ "loss": 0.0382,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 2.52,
2635
+ "learning_rate": 1.3294167139275594e-06,
2636
+ "loss": 0.013,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 2.52,
2641
+ "learning_rate": 1.298651966151665e-06,
2642
+ "loss": 0.0238,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 2.53,
2647
+ "learning_rate": 1.2682226344382798e-06,
2648
+ "loss": 0.0184,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 2.53,
2653
+ "learning_rate": 1.2381298917650408e-06,
2654
+ "loss": 0.0185,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 2.54,
2659
+ "learning_rate": 1.2083748981348832e-06,
2660
+ "loss": 0.0241,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 2.55,
2665
+ "learning_rate": 1.1789588005313257e-06,
2666
+ "loss": 0.0102,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 2.55,
2671
+ "learning_rate": 1.1498827328742623e-06,
2672
+ "loss": 0.0132,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 2.56,
2677
+ "learning_rate": 1.121147815976248e-06,
2678
+ "loss": 0.0263,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 2.56,
2683
+ "learning_rate": 1.0927551574992967e-06,
2684
+ "loss": 0.0345,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 2.57,
2689
+ "learning_rate": 1.0647058519121822e-06,
2690
+ "loss": 0.0209,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 2.57,
2695
+ "learning_rate": 1.0370009804482483e-06,
2696
+ "loss": 0.0501,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 2.58,
2701
+ "learning_rate": 1.009641611063732e-06,
2702
+ "loss": 0.0189,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 2.59,
2707
+ "learning_rate": 9.82628798396592e-07,
2708
+ "loss": 0.0417,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 2.59,
2713
+ "learning_rate": 9.559635837258653e-07,
2714
+ "loss": 0.0193,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 2.6,
2719
+ "learning_rate": 9.296469949315157e-07,
2720
+ "loss": 0.0289,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 2.6,
2725
+ "learning_rate": 9.036800464548157e-07,
2726
+ "loss": 0.0153,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 2.61,
2731
+ "learning_rate": 8.780637392592494e-07,
2732
+ "loss": 0.0299,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 2.61,
2737
+ "learning_rate": 8.527990607919145e-07,
2738
+ "loss": 0.007,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 2.62,
2743
+ "learning_rate": 8.278869849454718e-07,
2744
+ "loss": 0.009,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 2.63,
2749
+ "learning_rate": 8.033284720205947e-07,
2750
+ "loss": 0.0157,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 2.63,
2755
+ "learning_rate": 7.791244686889587e-07,
2756
+ "loss": 0.0273,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 2.64,
2761
+ "learning_rate": 7.552759079567418e-07,
2762
+ "loss": 0.025,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 2.64,
2767
+ "learning_rate": 7.317837091286706e-07,
2768
+ "loss": 0.0317,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 2.65,
2773
+ "learning_rate": 7.086487777725682e-07,
2774
+ "loss": 0.0272,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 2.66,
2779
+ "learning_rate": 6.858720056844614e-07,
2780
+ "loss": 0.0229,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 2.66,
2785
+ "learning_rate": 6.634542708541936e-07,
2786
+ "loss": 0.0216,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 2.67,
2791
+ "learning_rate": 6.413964374315851e-07,
2792
+ "loss": 0.0481,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 2.67,
2797
+ "learning_rate": 6.196993556931242e-07,
2798
+ "loss": 0.0217,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 2.68,
2803
+ "learning_rate": 5.983638620091858e-07,
2804
+ "loss": 0.0253,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 2.68,
2809
+ "learning_rate": 5.77390778811796e-07,
2810
+ "loss": 0.0394,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 2.69,
2815
+ "learning_rate": 5.567809145629244e-07,
2816
+ "loss": 0.0303,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 2.7,
2821
+ "learning_rate": 5.365350637233236e-07,
2822
+ "loss": 0.0258,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 2.7,
2827
+ "learning_rate": 5.166540067219072e-07,
2828
+ "loss": 0.0324,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 2.71,
2833
+ "learning_rate": 4.971385099256609e-07,
2834
+ "loss": 0.0459,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 2.71,
2839
+ "learning_rate": 4.779893256100987e-07,
2840
+ "loss": 0.0171,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 2.72,
2845
+ "learning_rate": 4.592071919302743e-07,
2846
+ "loss": 0.0189,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 2.72,
2851
+ "learning_rate": 4.407928328923194e-07,
2852
+ "loss": 0.0348,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 2.73,
2857
+ "learning_rate": 4.227469583255328e-07,
2858
+ "loss": 0.025,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 2.74,
2863
+ "learning_rate": 4.0507026385502747e-07,
2864
+ "loss": 0.0209,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 2.74,
2869
+ "learning_rate": 3.877634308749079e-07,
2870
+ "loss": 0.0148,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 2.75,
2875
+ "learning_rate": 3.708271265220087e-07,
2876
+ "loss": 0.0341,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 2.75,
2881
+ "learning_rate": 3.5426200365017207e-07,
2882
+ "loss": 0.0276,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 2.76,
2887
+ "learning_rate": 3.380687008050909e-07,
2888
+ "loss": 0.0399,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 2.76,
2893
+ "learning_rate": 3.222478421996877e-07,
2894
+ "loss": 0.0305,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 2.77,
2899
+ "learning_rate": 3.0680003769005153e-07,
2900
+ "loss": 0.0256,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 2.78,
2905
+ "learning_rate": 2.9172588275193536e-07,
2906
+ "loss": 0.0242,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 2.78,
2911
+ "learning_rate": 2.770259584577972e-07,
2912
+ "loss": 0.0326,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 2.79,
2917
+ "learning_rate": 2.627008314544044e-07,
2918
+ "loss": 0.0226,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 2.79,
2923
+ "learning_rate": 2.4875105394098654e-07,
2924
+ "loss": 0.0133,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 2.8,
2929
+ "learning_rate": 2.3517716364795384e-07,
2930
+ "loss": 0.031,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 2.8,
2935
+ "learning_rate": 2.2197968381616807e-07,
2936
+ "loss": 0.051,
2937
+ "step": 488
2938
+ },
2939
+ {
2940
+ "epoch": 2.81,
2941
+ "learning_rate": 2.091591231767709e-07,
2942
+ "loss": 0.024,
2943
+ "step": 489
2944
+ },
2945
+ {
2946
+ "epoch": 2.82,
2947
+ "learning_rate": 1.967159759315751e-07,
2948
+ "loss": 0.0332,
2949
+ "step": 490
2950
+ },
2951
+ {
2952
+ "epoch": 2.82,
2953
+ "learning_rate": 1.846507217340121e-07,
2954
+ "loss": 0.0238,
2955
+ "step": 491
2956
+ },
2957
+ {
2958
+ "epoch": 2.83,
2959
+ "learning_rate": 1.7296382567064674e-07,
2960
+ "loss": 0.0211,
2961
+ "step": 492
2962
+ },
2963
+ {
2964
+ "epoch": 2.83,
2965
+ "learning_rate": 1.6165573824324486e-07,
2966
+ "loss": 0.0383,
2967
+ "step": 493
2968
+ },
2969
+ {
2970
+ "epoch": 2.84,
2971
+ "learning_rate": 1.5072689535141072e-07,
2972
+ "loss": 0.027,
2973
+ "step": 494
2974
+ },
2975
+ {
2976
+ "epoch": 2.84,
2977
+ "learning_rate": 1.401777182757813e-07,
2978
+ "loss": 0.0172,
2979
+ "step": 495
2980
+ },
2981
+ {
2982
+ "epoch": 2.85,
2983
+ "learning_rate": 1.3000861366179064e-07,
2984
+ "loss": 0.0083,
2985
+ "step": 496
2986
+ },
2987
+ {
2988
+ "epoch": 2.86,
2989
+ "learning_rate": 1.2021997350399107e-07,
2990
+ "loss": 0.0141,
2991
+ "step": 497
2992
+ },
2993
+ {
2994
+ "epoch": 2.86,
2995
+ "learning_rate": 1.1081217513094211e-07,
2996
+ "loss": 0.0296,
2997
+ "step": 498
2998
+ },
2999
+ {
3000
+ "epoch": 2.87,
3001
+ "learning_rate": 1.0178558119067316e-07,
3002
+ "loss": 0.0302,
3003
+ "step": 499
3004
+ },
3005
+ {
3006
+ "epoch": 2.87,
3007
+ "learning_rate": 9.314053963669245e-08,
3008
+ "loss": 0.0088,
3009
+ "step": 500
3010
+ },
3011
+ {
3012
+ "epoch": 2.88,
3013
+ "learning_rate": 8.487738371458443e-08,
3014
+ "loss": 0.0135,
3015
+ "step": 501
3016
+ },
3017
+ {
3018
+ "epoch": 2.89,
3019
+ "learning_rate": 7.699643194915784e-08,
3020
+ "loss": 0.0134,
3021
+ "step": 502
3022
+ },
3023
+ {
3024
+ "epoch": 2.89,
3025
+ "learning_rate": 6.949798813217002e-08,
3026
+ "loss": 0.015,
3027
+ "step": 503
3028
+ },
3029
+ {
3030
+ "epoch": 2.9,
3031
+ "learning_rate": 6.238234131061616e-08,
3032
+ "loss": 0.0207,
3033
+ "step": 504
3034
+ },
3035
+ {
3036
+ "epoch": 2.9,
3037
+ "learning_rate": 5.5649765775586115e-08,
3038
+ "loss": 0.0349,
3039
+ "step": 505
3040
+ },
3041
+ {
3042
+ "epoch": 2.91,
3043
+ "learning_rate": 4.930052105169281e-08,
3044
+ "loss": 0.0161,
3045
+ "step": 506
3046
+ },
3047
+ {
3048
+ "epoch": 2.91,
3049
+ "learning_rate": 4.333485188706577e-08,
3050
+ "loss": 0.0304,
3051
+ "step": 507
3052
+ },
3053
+ {
3054
+ "epoch": 2.92,
3055
+ "learning_rate": 3.7752988243919817e-08,
3056
+ "loss": 0.0251,
3057
+ "step": 508
3058
+ },
3059
+ {
3060
+ "epoch": 2.93,
3061
+ "learning_rate": 3.255514528968884e-08,
3062
+ "loss": 0.0222,
3063
+ "step": 509
3064
+ },
3065
+ {
3066
+ "epoch": 2.93,
3067
+ "learning_rate": 2.774152338873126e-08,
3068
+ "loss": 0.0306,
3069
+ "step": 510
3070
+ },
3071
+ {
3072
+ "epoch": 2.94,
3073
+ "learning_rate": 2.3312308094607382e-08,
3074
+ "loss": 0.0265,
3075
+ "step": 511
3076
+ },
3077
+ {
3078
+ "epoch": 2.94,
3079
+ "learning_rate": 1.9267670142926187e-08,
3080
+ "loss": 0.0152,
3081
+ "step": 512
3082
+ },
3083
+ {
3084
+ "epoch": 2.95,
3085
+ "learning_rate": 1.5607765444762834e-08,
3086
+ "loss": 0.0399,
3087
+ "step": 513
3088
+ },
3089
+ {
3090
+ "epoch": 2.95,
3091
+ "learning_rate": 1.2332735080651248e-08,
3092
+ "loss": 0.0236,
3093
+ "step": 514
3094
+ },
3095
+ {
3096
+ "epoch": 2.96,
3097
+ "learning_rate": 9.442705295145127e-09,
3098
+ "loss": 0.0134,
3099
+ "step": 515
3100
+ },
3101
+ {
3102
+ "epoch": 2.97,
3103
+ "learning_rate": 6.937787491947401e-09,
3104
+ "loss": 0.029,
3105
+ "step": 516
3106
+ },
3107
+ {
3108
+ "epoch": 2.97,
3109
+ "learning_rate": 4.818078229622547e-09,
3110
+ "loss": 0.0269,
3111
+ "step": 517
3112
+ },
3113
+ {
3114
+ "epoch": 2.98,
3115
+ "learning_rate": 3.083659217871793e-09,
3116
+ "loss": 0.0098,
3117
+ "step": 518
3118
+ },
3119
+ {
3120
+ "epoch": 2.98,
3121
+ "learning_rate": 1.7345973143789717e-09,
3122
+ "loss": 0.0165,
3123
+ "step": 519
3124
+ },
3125
+ {
3126
+ "epoch": 2.99,
3127
+ "learning_rate": 7.709445222403578e-10,
3128
+ "loss": 0.0374,
3129
+ "step": 520
3130
+ },
3131
+ {
3132
+ "epoch": 2.99,
3133
+ "learning_rate": 1.9273798795627074e-10,
3134
+ "loss": 0.0208,
3135
+ "step": 521
3136
+ },
3137
+ {
3138
+ "epoch": 3.0,
3139
+ "learning_rate": 0.0,
3140
+ "loss": 0.0177,
3141
+ "step": 522
3142
+ },
3143
+ {
3144
+ "epoch": 3.0,
3145
+ "step": 522,
3146
+ "total_flos": 6390936502272.0,
3147
+ "train_loss": 0.05829430425760847,
3148
+ "train_runtime": 3021.6544,
3149
+ "train_samples_per_second": 5.515,
3150
+ "train_steps_per_second": 0.173
3151
+ }
3152
+ ],
3153
+ "logging_steps": 1.0,
3154
+ "max_steps": 522,
3155
+ "num_input_tokens_seen": 0,
3156
+ "num_train_epochs": 3,
3157
+ "save_steps": 1100,
3158
+ "total_flos": 6390936502272.0,
3159
+ "train_batch_size": 4,
3160
+ "trial_name": null,
3161
+ "trial_params": null
3162
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d965959ddef291da6215cebd8fef66371d876604acdbbba3c6274649a873c5e
3
+ size 6331