Hugging Face's logo

jzsues
/
baby-llava-qwen1.5-4b-chat-siglip-debug

Text Generation
Transformers
Safetensors
llava-qwen2
conversational
Inference Endpoints
Model card Files Community
jzsues commited on
Commit
b2fd62e
•
1 Parent(s): 9630ade

Upload folder using huggingface_hub

Browse files
Files changed (24) hide show
  1. checkpoint-500/added_tokens.json +5 -0
  2. checkpoint-500/config.json +38 -0
  3. checkpoint-500/generation_config.json +12 -0
  4. checkpoint-500/latest +1 -0
  5. checkpoint-500/merges.txt +0 -0
  6. checkpoint-500/model-00001-of-00002.safetensors +3 -0
  7. checkpoint-500/model-00002-of-00002.safetensors +3 -0
  8. checkpoint-500/model.safetensors.index.json +942 -0
  9. checkpoint-500/rng_state_0.pth +3 -0
  10. checkpoint-500/rng_state_1.pth +3 -0
  11. checkpoint-500/rng_state_2.pth +3 -0
  12. checkpoint-500/rng_state_3.pth +3 -0
  13. checkpoint-500/rng_state_4.pth +3 -0
  14. checkpoint-500/rng_state_5.pth +3 -0
  15. checkpoint-500/rng_state_6.pth +3 -0
  16. checkpoint-500/rng_state_7.pth +3 -0
  17. checkpoint-500/scheduler.pt +3 -0
  18. checkpoint-500/special_tokens_map.json +20 -0
  19. checkpoint-500/tokenizer.json +0 -0
  20. checkpoint-500/tokenizer_config.json +44 -0
  21. checkpoint-500/trainer_state.json +3521 -0
  22. checkpoint-500/training_args.bin +3 -0
  23. checkpoint-500/vocab.json +0 -0
  24. checkpoint-500/zero_to_fp32.py +604 -0
checkpoint-500/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
checkpoint-500/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen1.5-4B-Chat",
3
+ "architectures": [
4
+ "LlavaQwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2560,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 6912,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "mm_hidden_size": 1152,
16
+ "mm_patch_merge_type": "flat",
17
+ "mm_projector_lr": null,
18
+ "mm_projector_type": "mlp2x_gelu",
19
+ "mm_vision_select_feature": "patch",
20
+ "mm_vision_select_layer": -2,
21
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
22
+ "model_type": "llava-qwen2",
23
+ "num_attention_heads": 20,
24
+ "num_hidden_layers": 40,
25
+ "num_key_value_heads": 20,
26
+ "pad_image_to_square": true,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_theta": 5000000.0,
29
+ "sliding_window": 32768,
30
+ "tie_word_embeddings": false,
31
+ "tokenizer_model_max_length": 2048,
32
+ "tokenizer_padding_side": "right",
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.39.0.dev0",
35
+ "use_cache": false,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936
38
+ }
checkpoint-500/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "top_p": 0.8,
11
+ "transformers_version": "4.39.0.dev0"
12
+ }
checkpoint-500/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step500
checkpoint-500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d42c9a0d1343fd8613ddca2362db61fede834428f496d48611fa42b8473eaa3
3
+ size 4989973456
checkpoint-500/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44708f4d12cd97337b132613785ab026c27c15d3b6727513081d847746d47964
3
+ size 3786358064
checkpoint-500/model.safetensors.index.json ADDED
@@ -0,0 +1,942 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8776205440
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
437
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
439
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
442
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
446
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
449
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
450
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
451
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
452
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
454
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
458
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
459
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
460
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
461
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
462
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
463
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
464
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
465
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
468
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
469
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
470
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
471
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
472
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
473
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
474
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
475
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
476
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
477
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
478
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
480
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
481
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
482
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
483
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
484
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
485
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
486
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
487
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
488
+ "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
489
+ "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
490
+ "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
491
+ "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
492
+ "model.norm.weight": "model-00002-of-00002.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00002.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
760
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
761
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
762
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
763
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
764
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
765
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
766
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
767
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
768
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00002-of-00002.safetensors",
769
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00002-of-00002.safetensors",
770
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00002-of-00002.safetensors",
771
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00002-of-00002.safetensors",
772
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00002.safetensors",
773
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00002.safetensors",
774
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00002.safetensors",
775
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00002.safetensors",
776
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
777
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
778
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
779
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
780
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
781
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
782
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
783
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
784
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00002-of-00002.safetensors",
785
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00002-of-00002.safetensors",
786
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00002-of-00002.safetensors",
787
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00002-of-00002.safetensors",
788
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00002.safetensors",
789
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00002.safetensors",
790
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00002.safetensors",
791
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00002.safetensors",
792
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
793
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
794
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
795
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
796
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
797
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
798
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
799
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
800
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00002-of-00002.safetensors",
801
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00002-of-00002.safetensors",
802
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00002-of-00002.safetensors",
803
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00002-of-00002.safetensors",
804
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00002.safetensors",
805
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00002.safetensors",
806
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00002.safetensors",
807
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00002.safetensors",
808
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
809
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
810
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
811
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
812
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
813
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
814
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
815
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
816
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
817
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
818
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
819
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
820
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
821
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
822
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
823
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
824
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
825
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
826
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
827
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
828
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
829
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
830
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
831
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
832
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
833
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
834
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
835
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
836
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
837
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
838
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
839
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
840
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
841
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
842
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
843
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
844
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
845
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
846
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
847
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
848
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
849
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
850
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
851
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
852
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
853
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
854
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
855
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
856
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
857
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
858
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
859
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
860
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
861
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
862
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
863
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
864
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
865
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
866
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
867
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
868
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
869
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
870
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
871
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
872
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
873
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
874
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
875
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
876
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
877
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
878
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
879
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
880
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
881
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
882
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
883
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
884
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
885
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
886
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
887
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
888
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
889
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
890
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
891
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
892
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
893
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
894
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
895
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
896
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
897
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
898
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
899
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
900
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
901
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
902
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
903
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
904
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
905
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
906
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
907
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
908
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
909
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
910
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
911
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
912
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
913
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
914
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
915
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
916
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
917
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
918
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
919
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
920
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
921
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
922
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
923
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
924
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
925
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
926
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
927
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
928
+ "model.vision_tower.vision_tower.vision_model.head.attention.in_proj_bias": "model-00002-of-00002.safetensors",
929
+ "model.vision_tower.vision_tower.vision_model.head.attention.in_proj_weight": "model-00002-of-00002.safetensors",
930
+ "model.vision_tower.vision_tower.vision_model.head.attention.out_proj.bias": "model-00002-of-00002.safetensors",
931
+ "model.vision_tower.vision_tower.vision_model.head.attention.out_proj.weight": "model-00002-of-00002.safetensors",
932
+ "model.vision_tower.vision_tower.vision_model.head.layernorm.bias": "model-00002-of-00002.safetensors",
933
+ "model.vision_tower.vision_tower.vision_model.head.layernorm.weight": "model-00002-of-00002.safetensors",
934
+ "model.vision_tower.vision_tower.vision_model.head.mlp.fc1.bias": "model-00002-of-00002.safetensors",
935
+ "model.vision_tower.vision_tower.vision_model.head.mlp.fc1.weight": "model-00002-of-00002.safetensors",
936
+ "model.vision_tower.vision_tower.vision_model.head.mlp.fc2.bias": "model-00002-of-00002.safetensors",
937
+ "model.vision_tower.vision_tower.vision_model.head.mlp.fc2.weight": "model-00002-of-00002.safetensors",
938
+ "model.vision_tower.vision_tower.vision_model.head.probe": "model-00002-of-00002.safetensors",
939
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
940
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors"
941
+ }
942
+ }
checkpoint-500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349bdce0d7d746fca96725586680f25fcbe87b25649c2f407a9868dd5e3a4df9
3
+ size 15984
checkpoint-500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed436dfc3c083a2c0f7e071eb5d99ac2c2e4d95be18d4b1d9deadc19ac3e28a9
3
+ size 15984
checkpoint-500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f07e5c5bf1c99414ba24cb405aeb8506c21efe99d8211bd74d31e418c44d33
3
+ size 15984
checkpoint-500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15560fae09681c4bc9ee053742fc9659fab006ce125f3b1f411e63cc10cfec7
3
+ size 15984
checkpoint-500/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178e194724cafa7b1fb7d70ea540a3acd5724b87ae900765c2ef5583a45a9453
3
+ size 15984
checkpoint-500/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ccc3fcf9139d4cfdbb927c6fd37fd97d7d2ef7b5aa6c45963be65cfb60b6639
3
+ size 15984
checkpoint-500/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91101508f9bca1ebc0bc4cd93ab62f34dbb722cc9abf588ad771206d72450c84
3
+ size 15984
checkpoint-500/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:095bb04188e7d87cdbcbb73499807e7b094425676f2175b9771b1ab083ab2095
3
+ size 15984
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6db28339d778a9fa9e164b59d9e8f9a923a54206cb1879e6f0b06268d9c3978
3
+ size 1064
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 2048,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,3521 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.09628345850182939,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 20.216445284675434,
14
+ "learning_rate": 1.282051282051282e-07,
15
+ "loss": 1.9775,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 23.911595589639173,
21
+ "learning_rate": 2.564102564102564e-07,
22
+ "loss": 2.1666,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 23.589768673301773,
28
+ "learning_rate": 3.846153846153847e-07,
29
+ "loss": 1.9854,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0,
34
+ "grad_norm": 24.568648529053654,
35
+ "learning_rate": 5.128205128205128e-07,
36
+ "loss": 2.2656,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.0,
41
+ "grad_norm": 24.549288858256404,
42
+ "learning_rate": 6.41025641025641e-07,
43
+ "loss": 1.9927,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "grad_norm": 23.110487979033767,
49
+ "learning_rate": 7.692307692307694e-07,
50
+ "loss": 2.1646,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "grad_norm": 21.9015150661795,
56
+ "learning_rate": 8.974358974358975e-07,
57
+ "loss": 2.129,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.0,
62
+ "grad_norm": 19.501364965637194,
63
+ "learning_rate": 1.0256410256410257e-06,
64
+ "loss": 1.9416,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.0,
69
+ "grad_norm": 17.453575658521874,
70
+ "learning_rate": 1.153846153846154e-06,
71
+ "loss": 1.9497,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.0,
76
+ "grad_norm": 15.607773385934923,
77
+ "learning_rate": 1.282051282051282e-06,
78
+ "loss": 2.0166,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.0,
83
+ "grad_norm": 13.464353749675528,
84
+ "learning_rate": 1.4102564102564104e-06,
85
+ "loss": 1.8781,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.0,
90
+ "grad_norm": 13.97360564518581,
91
+ "learning_rate": 1.5384615384615387e-06,
92
+ "loss": 1.9095,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.0,
97
+ "grad_norm": 10.992113441163921,
98
+ "learning_rate": 1.6666666666666667e-06,
99
+ "loss": 1.6395,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.0,
104
+ "grad_norm": 11.552028290409154,
105
+ "learning_rate": 1.794871794871795e-06,
106
+ "loss": 1.5434,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.0,
111
+ "grad_norm": 8.311907698101182,
112
+ "learning_rate": 1.9230769230769234e-06,
113
+ "loss": 1.5281,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.0,
118
+ "grad_norm": 6.678981025513341,
119
+ "learning_rate": 2.0512820512820513e-06,
120
+ "loss": 1.4648,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.0,
125
+ "grad_norm": 1.0588935799454995,
126
+ "learning_rate": 2.1794871794871797e-06,
127
+ "loss": 0.7232,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.0,
132
+ "grad_norm": 4.903466856108649,
133
+ "learning_rate": 2.307692307692308e-06,
134
+ "loss": 1.2737,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.0,
139
+ "grad_norm": 4.685212001248653,
140
+ "learning_rate": 2.435897435897436e-06,
141
+ "loss": 1.3402,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.0,
146
+ "grad_norm": 4.245435062932411,
147
+ "learning_rate": 2.564102564102564e-06,
148
+ "loss": 1.3337,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.0,
153
+ "grad_norm": 4.158382292780615,
154
+ "learning_rate": 2.6923076923076923e-06,
155
+ "loss": 1.3811,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.0,
160
+ "grad_norm": 4.186622696017208,
161
+ "learning_rate": 2.8205128205128207e-06,
162
+ "loss": 1.2546,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.0,
167
+ "grad_norm": 3.517891507093355,
168
+ "learning_rate": 2.948717948717949e-06,
169
+ "loss": 1.18,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.0,
174
+ "grad_norm": 3.1001253598950638,
175
+ "learning_rate": 3.0769230769230774e-06,
176
+ "loss": 1.3383,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.0,
181
+ "grad_norm": 1.2465679665413227,
182
+ "learning_rate": 3.205128205128206e-06,
183
+ "loss": 0.832,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.01,
188
+ "grad_norm": 3.0120421636293195,
189
+ "learning_rate": 3.3333333333333333e-06,
190
+ "loss": 1.3458,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.01,
195
+ "grad_norm": 1.4484948949766845,
196
+ "learning_rate": 3.4615384615384617e-06,
197
+ "loss": 0.8444,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.01,
202
+ "grad_norm": 3.1110997732647743,
203
+ "learning_rate": 3.58974358974359e-06,
204
+ "loss": 1.2984,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.01,
209
+ "grad_norm": 2.755277848262445,
210
+ "learning_rate": 3.7179487179487184e-06,
211
+ "loss": 1.2309,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.01,
216
+ "grad_norm": 2.860582982001812,
217
+ "learning_rate": 3.846153846153847e-06,
218
+ "loss": 1.2708,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.01,
223
+ "grad_norm": 2.5897985578473377,
224
+ "learning_rate": 3.974358974358974e-06,
225
+ "loss": 1.2035,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.01,
230
+ "grad_norm": 2.5495914062962792,
231
+ "learning_rate": 4.102564102564103e-06,
232
+ "loss": 1.1789,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.01,
237
+ "grad_norm": 2.389696878446986,
238
+ "learning_rate": 4.230769230769231e-06,
239
+ "loss": 1.2519,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.01,
244
+ "grad_norm": 2.076541587027184,
245
+ "learning_rate": 4.358974358974359e-06,
246
+ "loss": 1.1727,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.01,
251
+ "grad_norm": 1.6797871781763094,
252
+ "learning_rate": 4.487179487179488e-06,
253
+ "loss": 0.792,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.01,
258
+ "grad_norm": 2.1243426876134257,
259
+ "learning_rate": 4.615384615384616e-06,
260
+ "loss": 1.1818,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.01,
265
+ "grad_norm": 2.299174657545576,
266
+ "learning_rate": 4.743589743589744e-06,
267
+ "loss": 1.2307,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.01,
272
+ "grad_norm": 2.0371458205650415,
273
+ "learning_rate": 4.871794871794872e-06,
274
+ "loss": 1.1005,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.01,
279
+ "grad_norm": 2.2455222878601098,
280
+ "learning_rate": 5e-06,
281
+ "loss": 1.1864,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.01,
286
+ "grad_norm": 2.1266583614163515,
287
+ "learning_rate": 5.128205128205128e-06,
288
+ "loss": 1.15,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.01,
293
+ "grad_norm": 2.089620655737586,
294
+ "learning_rate": 5.256410256410257e-06,
295
+ "loss": 1.1877,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.01,
300
+ "grad_norm": 2.197147361182619,
301
+ "learning_rate": 5.384615384615385e-06,
302
+ "loss": 1.1843,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.01,
307
+ "grad_norm": 1.1442985310608946,
308
+ "learning_rate": 5.512820512820514e-06,
309
+ "loss": 0.8406,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.01,
314
+ "grad_norm": 2.2343649074177634,
315
+ "learning_rate": 5.641025641025641e-06,
316
+ "loss": 1.2641,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.01,
321
+ "grad_norm": 2.2274293780592904,
322
+ "learning_rate": 5.769230769230769e-06,
323
+ "loss": 1.2005,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.01,
328
+ "grad_norm": 2.1702020802705553,
329
+ "learning_rate": 5.897435897435898e-06,
330
+ "loss": 1.2,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.01,
335
+ "grad_norm": 2.2728644356062087,
336
+ "learning_rate": 6.025641025641026e-06,
337
+ "loss": 1.1639,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.01,
342
+ "grad_norm": 2.296917779568054,
343
+ "learning_rate": 6.153846153846155e-06,
344
+ "loss": 1.1447,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.01,
349
+ "grad_norm": 2.1847920179158975,
350
+ "learning_rate": 6.282051282051282e-06,
351
+ "loss": 1.1049,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.01,
356
+ "grad_norm": 2.305602717661454,
357
+ "learning_rate": 6.410256410256412e-06,
358
+ "loss": 1.1454,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.01,
363
+ "grad_norm": 1.8163614577368297,
364
+ "learning_rate": 6.538461538461539e-06,
365
+ "loss": 1.1534,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.01,
370
+ "grad_norm": 2.0156958103382907,
371
+ "learning_rate": 6.666666666666667e-06,
372
+ "loss": 1.1014,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.01,
377
+ "grad_norm": 2.2061600271142927,
378
+ "learning_rate": 6.794871794871796e-06,
379
+ "loss": 1.1111,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.01,
384
+ "grad_norm": 2.0514290811875346,
385
+ "learning_rate": 6.923076923076923e-06,
386
+ "loss": 1.2195,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.01,
391
+ "grad_norm": 2.009350847624063,
392
+ "learning_rate": 7.051282051282053e-06,
393
+ "loss": 1.1672,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.01,
398
+ "grad_norm": 1.9383085189275544,
399
+ "learning_rate": 7.17948717948718e-06,
400
+ "loss": 1.1329,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.01,
405
+ "grad_norm": 2.231367175822086,
406
+ "learning_rate": 7.307692307692308e-06,
407
+ "loss": 1.1168,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.01,
412
+ "grad_norm": 2.0008003220100643,
413
+ "learning_rate": 7.435897435897437e-06,
414
+ "loss": 1.2286,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.01,
419
+ "grad_norm": 1.8980157371763204,
420
+ "learning_rate": 7.564102564102564e-06,
421
+ "loss": 1.0885,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.01,
426
+ "grad_norm": 1.9742084904113024,
427
+ "learning_rate": 7.692307692307694e-06,
428
+ "loss": 1.1383,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.01,
433
+ "grad_norm": 2.130005401042239,
434
+ "learning_rate": 7.820512820512822e-06,
435
+ "loss": 1.1859,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.01,
440
+ "grad_norm": 1.986055300283839,
441
+ "learning_rate": 7.948717948717949e-06,
442
+ "loss": 1.1223,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.01,
447
+ "grad_norm": 1.901481096038548,
448
+ "learning_rate": 8.076923076923077e-06,
449
+ "loss": 1.0932,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.01,
454
+ "grad_norm": 2.125815394626458,
455
+ "learning_rate": 8.205128205128205e-06,
456
+ "loss": 1.2282,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.01,
461
+ "grad_norm": 1.9414092406206,
462
+ "learning_rate": 8.333333333333334e-06,
463
+ "loss": 1.1273,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.01,
468
+ "grad_norm": 1.9746610829599591,
469
+ "learning_rate": 8.461538461538462e-06,
470
+ "loss": 1.048,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.01,
475
+ "grad_norm": 2.154415501683974,
476
+ "learning_rate": 8.58974358974359e-06,
477
+ "loss": 1.0115,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.01,
482
+ "grad_norm": 1.868695894296507,
483
+ "learning_rate": 8.717948717948719e-06,
484
+ "loss": 1.1381,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.01,
489
+ "grad_norm": 1.8811818709807824,
490
+ "learning_rate": 8.846153846153847e-06,
491
+ "loss": 1.1031,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.01,
496
+ "grad_norm": 2.3006046265407827,
497
+ "learning_rate": 8.974358974358976e-06,
498
+ "loss": 1.1062,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.01,
503
+ "grad_norm": 2.1699669644056137,
504
+ "learning_rate": 9.102564102564104e-06,
505
+ "loss": 1.1372,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.01,
510
+ "grad_norm": 1.8731108123220086,
511
+ "learning_rate": 9.230769230769232e-06,
512
+ "loss": 1.043,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.01,
517
+ "grad_norm": 2.1143191194853337,
518
+ "learning_rate": 9.358974358974359e-06,
519
+ "loss": 1.2095,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.01,
524
+ "grad_norm": 1.9506052984256566,
525
+ "learning_rate": 9.487179487179487e-06,
526
+ "loss": 1.1677,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.01,
531
+ "grad_norm": 2.004755199707491,
532
+ "learning_rate": 9.615384615384616e-06,
533
+ "loss": 1.1288,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.01,
538
+ "grad_norm": 2.2712419994719104,
539
+ "learning_rate": 9.743589743589744e-06,
540
+ "loss": 1.1489,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.01,
545
+ "grad_norm": 1.9915382414879983,
546
+ "learning_rate": 9.871794871794872e-06,
547
+ "loss": 1.1356,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.02,
552
+ "grad_norm": 1.8655506688742343,
553
+ "learning_rate": 1e-05,
554
+ "loss": 1.0524,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.02,
559
+ "grad_norm": 2.1482093297445575,
560
+ "learning_rate": 1.012820512820513e-05,
561
+ "loss": 0.9386,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.02,
566
+ "grad_norm": 1.9215954323448314,
567
+ "learning_rate": 1.0256410256410256e-05,
568
+ "loss": 1.1801,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.02,
573
+ "grad_norm": 1.9081067065165245,
574
+ "learning_rate": 1.0384615384615386e-05,
575
+ "loss": 1.0638,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.02,
580
+ "grad_norm": 1.9407275778581317,
581
+ "learning_rate": 1.0512820512820514e-05,
582
+ "loss": 1.1074,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.02,
587
+ "grad_norm": 2.025638661080253,
588
+ "learning_rate": 1.0641025641025643e-05,
589
+ "loss": 1.0776,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.02,
594
+ "grad_norm": 1.919914713517629,
595
+ "learning_rate": 1.076923076923077e-05,
596
+ "loss": 1.0189,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.02,
601
+ "grad_norm": 2.1903909968624977,
602
+ "learning_rate": 1.0897435897435898e-05,
603
+ "loss": 1.1085,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.02,
608
+ "grad_norm": 2.17664798755956,
609
+ "learning_rate": 1.1025641025641028e-05,
610
+ "loss": 1.0529,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.02,
615
+ "grad_norm": 2.113038538305221,
616
+ "learning_rate": 1.1153846153846154e-05,
617
+ "loss": 1.1169,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.02,
622
+ "grad_norm": 2.0486185050480894,
623
+ "learning_rate": 1.1282051282051283e-05,
624
+ "loss": 1.1889,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.02,
629
+ "grad_norm": 2.045888088194733,
630
+ "learning_rate": 1.1410256410256411e-05,
631
+ "loss": 1.1538,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.02,
636
+ "grad_norm": 1.7806490104735406,
637
+ "learning_rate": 1.1538461538461538e-05,
638
+ "loss": 1.0914,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.02,
643
+ "grad_norm": 2.1971405645771527,
644
+ "learning_rate": 1.1666666666666668e-05,
645
+ "loss": 1.048,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.02,
650
+ "grad_norm": 2.002750992348389,
651
+ "learning_rate": 1.1794871794871796e-05,
652
+ "loss": 1.0975,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.02,
657
+ "grad_norm": 2.187960188699195,
658
+ "learning_rate": 1.1923076923076925e-05,
659
+ "loss": 1.0906,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.02,
664
+ "grad_norm": 2.0174873060151857,
665
+ "learning_rate": 1.2051282051282051e-05,
666
+ "loss": 1.0992,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.02,
671
+ "grad_norm": 2.0443319007612852,
672
+ "learning_rate": 1.217948717948718e-05,
673
+ "loss": 1.082,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.02,
678
+ "grad_norm": 1.2748628196945109,
679
+ "learning_rate": 1.230769230769231e-05,
680
+ "loss": 0.7718,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.02,
685
+ "grad_norm": 1.896137442216524,
686
+ "learning_rate": 1.2435897435897436e-05,
687
+ "loss": 1.1549,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.02,
692
+ "grad_norm": 1.95843096706086,
693
+ "learning_rate": 1.2564102564102565e-05,
694
+ "loss": 1.128,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.02,
699
+ "grad_norm": 2.0686480210411657,
700
+ "learning_rate": 1.2692307692307693e-05,
701
+ "loss": 1.1249,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.02,
706
+ "grad_norm": 1.9404669088500452,
707
+ "learning_rate": 1.2820512820512823e-05,
708
+ "loss": 1.115,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.02,
713
+ "grad_norm": 1.8653249453155127,
714
+ "learning_rate": 1.294871794871795e-05,
715
+ "loss": 1.1051,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.02,
720
+ "grad_norm": 2.10107543117975,
721
+ "learning_rate": 1.3076923076923078e-05,
722
+ "loss": 1.0875,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.02,
727
+ "grad_norm": 1.8747249569118767,
728
+ "learning_rate": 1.3205128205128207e-05,
729
+ "loss": 1.0451,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.02,
734
+ "grad_norm": 1.9850084346269088,
735
+ "learning_rate": 1.3333333333333333e-05,
736
+ "loss": 1.0689,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.02,
741
+ "grad_norm": 2.049123340018695,
742
+ "learning_rate": 1.3461538461538463e-05,
743
+ "loss": 1.0905,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.02,
748
+ "grad_norm": 2.1264307975036925,
749
+ "learning_rate": 1.3589743589743592e-05,
750
+ "loss": 1.1224,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.02,
755
+ "grad_norm": 2.0502742046299907,
756
+ "learning_rate": 1.3717948717948718e-05,
757
+ "loss": 1.0915,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.02,
762
+ "grad_norm": 1.8303440971792886,
763
+ "learning_rate": 1.3846153846153847e-05,
764
+ "loss": 1.0949,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.02,
769
+ "grad_norm": 2.2313836077753413,
770
+ "learning_rate": 1.3974358974358975e-05,
771
+ "loss": 1.0429,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.02,
776
+ "grad_norm": 1.8919532863183655,
777
+ "learning_rate": 1.4102564102564105e-05,
778
+ "loss": 1.0763,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.02,
783
+ "grad_norm": 2.0704343058304526,
784
+ "learning_rate": 1.4230769230769232e-05,
785
+ "loss": 1.1657,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.02,
790
+ "grad_norm": 2.430724552963001,
791
+ "learning_rate": 1.435897435897436e-05,
792
+ "loss": 1.0815,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.02,
797
+ "grad_norm": 1.1085720824994245,
798
+ "learning_rate": 1.4487179487179489e-05,
799
+ "loss": 0.866,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.02,
804
+ "grad_norm": 1.8279405733949405,
805
+ "learning_rate": 1.4615384615384615e-05,
806
+ "loss": 1.0434,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.02,
811
+ "grad_norm": 1.9381964085003,
812
+ "learning_rate": 1.4743589743589745e-05,
813
+ "loss": 1.0764,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.02,
818
+ "grad_norm": 0.9487925657079459,
819
+ "learning_rate": 1.4871794871794874e-05,
820
+ "loss": 0.7605,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.02,
825
+ "grad_norm": 2.1860059019926847,
826
+ "learning_rate": 1.5000000000000002e-05,
827
+ "loss": 1.0553,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.02,
832
+ "grad_norm": 1.9458206802695046,
833
+ "learning_rate": 1.5128205128205129e-05,
834
+ "loss": 1.048,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.02,
839
+ "grad_norm": 1.835280245148161,
840
+ "learning_rate": 1.5256410256410257e-05,
841
+ "loss": 1.055,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.02,
846
+ "grad_norm": 2.0496294448787333,
847
+ "learning_rate": 1.5384615384615387e-05,
848
+ "loss": 1.1847,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.02,
853
+ "grad_norm": 2.218142247887536,
854
+ "learning_rate": 1.5512820512820516e-05,
855
+ "loss": 1.0944,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.02,
860
+ "grad_norm": 2.4654880331995055,
861
+ "learning_rate": 1.5641025641025644e-05,
862
+ "loss": 1.1229,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.02,
867
+ "grad_norm": 1.9292976768956316,
868
+ "learning_rate": 1.576923076923077e-05,
869
+ "loss": 1.0633,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.02,
874
+ "grad_norm": 1.9404361588446972,
875
+ "learning_rate": 1.5897435897435897e-05,
876
+ "loss": 1.0854,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.02,
881
+ "grad_norm": 1.9362855000410057,
882
+ "learning_rate": 1.602564102564103e-05,
883
+ "loss": 1.0061,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.02,
888
+ "grad_norm": 2.083318365558794,
889
+ "learning_rate": 1.6153846153846154e-05,
890
+ "loss": 1.0612,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.02,
895
+ "grad_norm": 2.122373700349859,
896
+ "learning_rate": 1.6282051282051282e-05,
897
+ "loss": 0.9871,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.02,
902
+ "grad_norm": 2.359431021405571,
903
+ "learning_rate": 1.641025641025641e-05,
904
+ "loss": 1.0635,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.02,
909
+ "grad_norm": 1.0429268801216616,
910
+ "learning_rate": 1.653846153846154e-05,
911
+ "loss": 0.8406,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.03,
916
+ "grad_norm": 2.394181875364715,
917
+ "learning_rate": 1.6666666666666667e-05,
918
+ "loss": 1.0533,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.03,
923
+ "grad_norm": 2.0279839342385624,
924
+ "learning_rate": 1.6794871794871796e-05,
925
+ "loss": 1.1405,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.03,
930
+ "grad_norm": 2.133411698576336,
931
+ "learning_rate": 1.6923076923076924e-05,
932
+ "loss": 1.1123,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.03,
937
+ "grad_norm": 2.0961335815701654,
938
+ "learning_rate": 1.7051282051282053e-05,
939
+ "loss": 1.1525,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.03,
944
+ "grad_norm": 2.0054012186334265,
945
+ "learning_rate": 1.717948717948718e-05,
946
+ "loss": 1.0072,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.03,
951
+ "grad_norm": 1.9954089428486153,
952
+ "learning_rate": 1.730769230769231e-05,
953
+ "loss": 0.9954,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.03,
958
+ "grad_norm": 1.9266633957752657,
959
+ "learning_rate": 1.7435897435897438e-05,
960
+ "loss": 1.0307,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.03,
965
+ "grad_norm": 2.0235377885233734,
966
+ "learning_rate": 1.7564102564102566e-05,
967
+ "loss": 1.0939,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.03,
972
+ "grad_norm": 2.0175192551390526,
973
+ "learning_rate": 1.7692307692307694e-05,
974
+ "loss": 1.0717,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.03,
979
+ "grad_norm": 1.0342136013306582,
980
+ "learning_rate": 1.7820512820512823e-05,
981
+ "loss": 0.808,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.03,
986
+ "grad_norm": 2.428830129959296,
987
+ "learning_rate": 1.794871794871795e-05,
988
+ "loss": 1.082,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.03,
993
+ "grad_norm": 1.9642876987686577,
994
+ "learning_rate": 1.807692307692308e-05,
995
+ "loss": 1.1122,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.03,
1000
+ "grad_norm": 2.027656601747293,
1001
+ "learning_rate": 1.8205128205128208e-05,
1002
+ "loss": 1.0719,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.03,
1007
+ "grad_norm": 2.183894708322355,
1008
+ "learning_rate": 1.8333333333333333e-05,
1009
+ "loss": 1.1253,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.03,
1014
+ "grad_norm": 2.062043365070345,
1015
+ "learning_rate": 1.8461538461538465e-05,
1016
+ "loss": 1.0173,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.03,
1021
+ "grad_norm": 2.033473969787848,
1022
+ "learning_rate": 1.8589743589743593e-05,
1023
+ "loss": 1.1215,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.03,
1028
+ "grad_norm": 2.062919227268133,
1029
+ "learning_rate": 1.8717948717948718e-05,
1030
+ "loss": 0.9471,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.03,
1035
+ "grad_norm": 2.070479749634218,
1036
+ "learning_rate": 1.8846153846153846e-05,
1037
+ "loss": 1.1518,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.03,
1042
+ "grad_norm": 1.9754065164309047,
1043
+ "learning_rate": 1.8974358974358975e-05,
1044
+ "loss": 1.0442,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.03,
1049
+ "grad_norm": 2.13339324208887,
1050
+ "learning_rate": 1.9102564102564106e-05,
1051
+ "loss": 1.0118,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.03,
1056
+ "grad_norm": 2.369137183205933,
1057
+ "learning_rate": 1.923076923076923e-05,
1058
+ "loss": 1.092,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.03,
1063
+ "grad_norm": 2.1638382502455435,
1064
+ "learning_rate": 1.935897435897436e-05,
1065
+ "loss": 0.9977,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.03,
1070
+ "grad_norm": 2.1783663043501296,
1071
+ "learning_rate": 1.9487179487179488e-05,
1072
+ "loss": 1.0939,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.03,
1077
+ "grad_norm": 1.9497922494089797,
1078
+ "learning_rate": 1.9615384615384617e-05,
1079
+ "loss": 1.0152,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.03,
1084
+ "grad_norm": 2.0547723801429747,
1085
+ "learning_rate": 1.9743589743589745e-05,
1086
+ "loss": 1.0223,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.03,
1091
+ "grad_norm": 2.070242647096933,
1092
+ "learning_rate": 1.9871794871794873e-05,
1093
+ "loss": 0.9549,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.03,
1098
+ "grad_norm": 1.9301029883856002,
1099
+ "learning_rate": 2e-05,
1100
+ "loss": 1.0594,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.03,
1105
+ "grad_norm": 2.1096159037163598,
1106
+ "learning_rate": 1.9999998054972106e-05,
1107
+ "loss": 1.0369,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.03,
1112
+ "grad_norm": 2.1245553998838536,
1113
+ "learning_rate": 1.9999992219889184e-05,
1114
+ "loss": 0.9525,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.03,
1119
+ "grad_norm": 2.131488635617247,
1120
+ "learning_rate": 1.99999824947535e-05,
1121
+ "loss": 1.0323,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.03,
1126
+ "grad_norm": 2.363965004377438,
1127
+ "learning_rate": 1.9999968879568835e-05,
1128
+ "loss": 1.0856,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.03,
1133
+ "grad_norm": 2.0585329850283522,
1134
+ "learning_rate": 1.9999951374340493e-05,
1135
+ "loss": 1.0892,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.03,
1140
+ "grad_norm": 1.9750564938392907,
1141
+ "learning_rate": 1.9999929979075278e-05,
1142
+ "loss": 1.0452,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.03,
1147
+ "grad_norm": 2.141328684995138,
1148
+ "learning_rate": 1.999990469378151e-05,
1149
+ "loss": 1.1101,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.03,
1154
+ "grad_norm": 1.031433061724888,
1155
+ "learning_rate": 1.9999875518469033e-05,
1156
+ "loss": 0.799,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.03,
1161
+ "grad_norm": 2.4065812716730095,
1162
+ "learning_rate": 1.9999842453149192e-05,
1163
+ "loss": 1.0711,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.03,
1168
+ "grad_norm": 2.202667832906497,
1169
+ "learning_rate": 1.999980549783485e-05,
1170
+ "loss": 0.994,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.03,
1175
+ "grad_norm": 2.129957736688869,
1176
+ "learning_rate": 1.9999764652540382e-05,
1177
+ "loss": 1.0424,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.03,
1182
+ "grad_norm": 2.32808847121314,
1183
+ "learning_rate": 1.9999719917281682e-05,
1184
+ "loss": 1.1104,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.03,
1189
+ "grad_norm": 2.402682209687328,
1190
+ "learning_rate": 1.9999671292076145e-05,
1191
+ "loss": 1.1413,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.03,
1196
+ "grad_norm": 2.1985356868714634,
1197
+ "learning_rate": 1.9999618776942692e-05,
1198
+ "loss": 1.0147,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.03,
1203
+ "grad_norm": 2.174198937460871,
1204
+ "learning_rate": 1.999956237190175e-05,
1205
+ "loss": 1.0795,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.03,
1210
+ "grad_norm": 2.5202206051237606,
1211
+ "learning_rate": 1.9999502076975257e-05,
1212
+ "loss": 0.9901,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.03,
1217
+ "grad_norm": 2.1957807846109967,
1218
+ "learning_rate": 1.9999437892186673e-05,
1219
+ "loss": 0.9667,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.03,
1224
+ "grad_norm": 1.9569728406033189,
1225
+ "learning_rate": 1.9999369817560967e-05,
1226
+ "loss": 1.0522,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.03,
1231
+ "grad_norm": 2.245962863895941,
1232
+ "learning_rate": 1.9999297853124614e-05,
1233
+ "loss": 1.0186,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.03,
1238
+ "grad_norm": 2.413279476262106,
1239
+ "learning_rate": 1.9999221998905613e-05,
1240
+ "loss": 1.0631,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.03,
1245
+ "grad_norm": 2.076972357794391,
1246
+ "learning_rate": 1.9999142254933476e-05,
1247
+ "loss": 1.0691,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.03,
1252
+ "grad_norm": 1.972083747779467,
1253
+ "learning_rate": 1.9999058621239217e-05,
1254
+ "loss": 1.0699,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.03,
1259
+ "grad_norm": 2.1755848177736334,
1260
+ "learning_rate": 1.9998971097855372e-05,
1261
+ "loss": 1.1303,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.03,
1266
+ "grad_norm": 1.9839915727644544,
1267
+ "learning_rate": 1.999887968481599e-05,
1268
+ "loss": 1.0598,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.03,
1273
+ "grad_norm": 2.0373868712914938,
1274
+ "learning_rate": 1.9998784382156622e-05,
1275
+ "loss": 1.0762,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.04,
1280
+ "grad_norm": 2.0029728344755298,
1281
+ "learning_rate": 1.9998685189914356e-05,
1282
+ "loss": 1.1297,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.04,
1287
+ "grad_norm": 1.9387023208997487,
1288
+ "learning_rate": 1.999858210812777e-05,
1289
+ "loss": 0.9651,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.04,
1294
+ "grad_norm": 2.1732843858578414,
1295
+ "learning_rate": 1.9998475136836966e-05,
1296
+ "loss": 1.0479,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.04,
1301
+ "grad_norm": 1.954541614593413,
1302
+ "learning_rate": 1.999836427608355e-05,
1303
+ "loss": 0.9924,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.04,
1308
+ "grad_norm": 1.9489826509232497,
1309
+ "learning_rate": 1.9998249525910656e-05,
1310
+ "loss": 1.0869,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.04,
1315
+ "grad_norm": 1.762474252467788,
1316
+ "learning_rate": 1.999813088636292e-05,
1317
+ "loss": 0.9219,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.04,
1322
+ "grad_norm": 2.0627539245716164,
1323
+ "learning_rate": 1.999800835748649e-05,
1324
+ "loss": 1.0559,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.04,
1329
+ "grad_norm": 2.137164696299313,
1330
+ "learning_rate": 1.9997881939329034e-05,
1331
+ "loss": 1.0711,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.04,
1336
+ "grad_norm": 2.102050244558165,
1337
+ "learning_rate": 1.9997751631939724e-05,
1338
+ "loss": 1.0547,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.04,
1343
+ "grad_norm": 1.9560280671941297,
1344
+ "learning_rate": 1.999761743536926e-05,
1345
+ "loss": 1.0285,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.04,
1350
+ "grad_norm": 2.2056335755059853,
1351
+ "learning_rate": 1.9997479349669836e-05,
1352
+ "loss": 1.039,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.04,
1357
+ "grad_norm": 1.857852624351155,
1358
+ "learning_rate": 1.999733737489517e-05,
1359
+ "loss": 1.0525,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.04,
1364
+ "grad_norm": 2.1149817844051846,
1365
+ "learning_rate": 1.9997191511100498e-05,
1366
+ "loss": 1.1631,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.04,
1371
+ "grad_norm": 2.1742104034580874,
1372
+ "learning_rate": 1.9997041758342554e-05,
1373
+ "loss": 1.0704,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.04,
1378
+ "grad_norm": 1.92170752202666,
1379
+ "learning_rate": 1.9996888116679597e-05,
1380
+ "loss": 1.0977,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.04,
1385
+ "grad_norm": 1.8760103416157878,
1386
+ "learning_rate": 1.999673058617139e-05,
1387
+ "loss": 1.0593,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.04,
1392
+ "grad_norm": 2.239018605486002,
1393
+ "learning_rate": 1.9996569166879215e-05,
1394
+ "loss": 1.1451,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.04,
1399
+ "grad_norm": 1.9680194040337873,
1400
+ "learning_rate": 1.9996403858865867e-05,
1401
+ "loss": 1.1002,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.04,
1406
+ "grad_norm": 1.8952136254504348,
1407
+ "learning_rate": 1.9996234662195653e-05,
1408
+ "loss": 1.13,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.04,
1413
+ "grad_norm": 1.7805244417146453,
1414
+ "learning_rate": 1.9996061576934388e-05,
1415
+ "loss": 1.088,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.04,
1420
+ "grad_norm": 1.8466727506858036,
1421
+ "learning_rate": 1.9995884603149403e-05,
1422
+ "loss": 1.0727,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.04,
1427
+ "grad_norm": 1.8297374299414597,
1428
+ "learning_rate": 1.9995703740909542e-05,
1429
+ "loss": 0.9719,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.04,
1434
+ "grad_norm": 1.8430958263907924,
1435
+ "learning_rate": 1.9995518990285166e-05,
1436
+ "loss": 1.0023,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.04,
1441
+ "grad_norm": 2.0008787877943846,
1442
+ "learning_rate": 1.9995330351348135e-05,
1443
+ "loss": 1.1435,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.04,
1448
+ "grad_norm": 1.767812451189823,
1449
+ "learning_rate": 1.999513782417184e-05,
1450
+ "loss": 0.988,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.04,
1455
+ "grad_norm": 1.9499593819305316,
1456
+ "learning_rate": 1.999494140883117e-05,
1457
+ "loss": 1.0819,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.04,
1462
+ "grad_norm": 1.9273733720896404,
1463
+ "learning_rate": 1.9994741105402533e-05,
1464
+ "loss": 0.9283,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.04,
1469
+ "grad_norm": 2.045214086540413,
1470
+ "learning_rate": 1.9994536913963852e-05,
1471
+ "loss": 1.0441,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.04,
1476
+ "grad_norm": 1.9323194027489348,
1477
+ "learning_rate": 1.999432883459455e-05,
1478
+ "loss": 1.0739,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.04,
1483
+ "grad_norm": 1.78702758065982,
1484
+ "learning_rate": 1.9994116867375574e-05,
1485
+ "loss": 1.0648,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.04,
1490
+ "grad_norm": 1.999325292321686,
1491
+ "learning_rate": 1.9993901012389386e-05,
1492
+ "loss": 1.0197,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.04,
1497
+ "grad_norm": 1.9750895391330754,
1498
+ "learning_rate": 1.999368126971995e-05,
1499
+ "loss": 1.0378,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.04,
1504
+ "grad_norm": 2.0645995523227865,
1505
+ "learning_rate": 1.9993457639452748e-05,
1506
+ "loss": 1.0636,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.04,
1511
+ "grad_norm": 2.0348647174788024,
1512
+ "learning_rate": 1.999323012167477e-05,
1513
+ "loss": 1.0233,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.04,
1518
+ "grad_norm": 1.955566109346601,
1519
+ "learning_rate": 1.999299871647453e-05,
1520
+ "loss": 1.1114,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.04,
1525
+ "grad_norm": 2.0108878112553326,
1526
+ "learning_rate": 1.9992763423942038e-05,
1527
+ "loss": 1.0761,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.04,
1532
+ "grad_norm": 1.9661856223780965,
1533
+ "learning_rate": 1.999252424416883e-05,
1534
+ "loss": 1.1253,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.04,
1539
+ "grad_norm": 2.1696126303119874,
1540
+ "learning_rate": 1.9992281177247942e-05,
1541
+ "loss": 1.0375,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.04,
1546
+ "grad_norm": 1.2041115439000005,
1547
+ "learning_rate": 1.999203422327393e-05,
1548
+ "loss": 0.8076,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.04,
1553
+ "grad_norm": 1.9028998749132995,
1554
+ "learning_rate": 1.9991783382342867e-05,
1555
+ "loss": 1.0468,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.04,
1560
+ "grad_norm": 2.2722564344114153,
1561
+ "learning_rate": 1.9991528654552326e-05,
1562
+ "loss": 1.066,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.04,
1567
+ "grad_norm": 2.1410050185723164,
1568
+ "learning_rate": 1.9991270040001396e-05,
1569
+ "loss": 1.0753,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.04,
1574
+ "grad_norm": 2.0921277876178137,
1575
+ "learning_rate": 1.9991007538790686e-05,
1576
+ "loss": 1.0768,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.04,
1581
+ "grad_norm": 2.0882235349073617,
1582
+ "learning_rate": 1.9990741151022302e-05,
1583
+ "loss": 1.0978,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.04,
1588
+ "grad_norm": 1.9414030643468547,
1589
+ "learning_rate": 1.9990470876799876e-05,
1590
+ "loss": 1.002,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.04,
1595
+ "grad_norm": 2.17093585650916,
1596
+ "learning_rate": 1.9990196716228546e-05,
1597
+ "loss": 1.0542,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.04,
1602
+ "grad_norm": 1.955440445323398,
1603
+ "learning_rate": 1.998991866941496e-05,
1604
+ "loss": 1.0849,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.04,
1609
+ "grad_norm": 2.0226531291514176,
1610
+ "learning_rate": 1.9989636736467278e-05,
1611
+ "loss": 1.1224,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.04,
1616
+ "grad_norm": 2.2336914840149285,
1617
+ "learning_rate": 1.9989350917495177e-05,
1618
+ "loss": 1.0551,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.04,
1623
+ "grad_norm": 2.046392279697416,
1624
+ "learning_rate": 1.9989061212609845e-05,
1625
+ "loss": 1.0738,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.04,
1630
+ "grad_norm": 2.248695264268023,
1631
+ "learning_rate": 1.998876762192397e-05,
1632
+ "loss": 1.019,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.04,
1637
+ "grad_norm": 2.3362932243579713,
1638
+ "learning_rate": 1.9988470145551765e-05,
1639
+ "loss": 1.0555,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.05,
1644
+ "grad_norm": 2.149028179411019,
1645
+ "learning_rate": 1.9988168783608955e-05,
1646
+ "loss": 1.0529,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.05,
1651
+ "grad_norm": 1.8633459882398478,
1652
+ "learning_rate": 1.9987863536212765e-05,
1653
+ "loss": 1.0074,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.05,
1658
+ "grad_norm": 2.0594450846907373,
1659
+ "learning_rate": 1.9987554403481938e-05,
1660
+ "loss": 0.966,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.05,
1665
+ "grad_norm": 1.9956893021238926,
1666
+ "learning_rate": 1.9987241385536732e-05,
1667
+ "loss": 1.0367,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.05,
1672
+ "grad_norm": 2.025631177166738,
1673
+ "learning_rate": 1.9986924482498907e-05,
1674
+ "loss": 1.0407,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.05,
1679
+ "grad_norm": 2.0369291335090365,
1680
+ "learning_rate": 1.998660369449175e-05,
1681
+ "loss": 1.0408,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.05,
1686
+ "grad_norm": 1.9777103589259433,
1687
+ "learning_rate": 1.998627902164004e-05,
1688
+ "loss": 1.0964,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.05,
1693
+ "grad_norm": 0.9884611294066915,
1694
+ "learning_rate": 1.998595046407008e-05,
1695
+ "loss": 0.7983,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.05,
1700
+ "grad_norm": 2.0510845934246746,
1701
+ "learning_rate": 1.998561802190968e-05,
1702
+ "loss": 1.0129,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.05,
1707
+ "grad_norm": 2.4092760114986467,
1708
+ "learning_rate": 1.9985281695288165e-05,
1709
+ "loss": 1.076,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.05,
1714
+ "grad_norm": 1.9933609047274952,
1715
+ "learning_rate": 1.998494148433636e-05,
1716
+ "loss": 1.0225,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.05,
1721
+ "grad_norm": 1.0232974321656905,
1722
+ "learning_rate": 1.9984597389186618e-05,
1723
+ "loss": 0.829,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.05,
1728
+ "grad_norm": 2.0605065022696967,
1729
+ "learning_rate": 1.9984249409972794e-05,
1730
+ "loss": 0.9931,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.05,
1735
+ "grad_norm": 2.2454749233665545,
1736
+ "learning_rate": 1.9983897546830243e-05,
1737
+ "loss": 1.0803,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.05,
1742
+ "grad_norm": 1.8431535853254453,
1743
+ "learning_rate": 1.998354179989585e-05,
1744
+ "loss": 0.983,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.05,
1749
+ "grad_norm": 1.8566618675252857,
1750
+ "learning_rate": 1.9983182169308004e-05,
1751
+ "loss": 0.9921,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.05,
1756
+ "grad_norm": 1.9375277651998517,
1757
+ "learning_rate": 1.9982818655206602e-05,
1758
+ "loss": 1.0113,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.05,
1763
+ "grad_norm": 1.9572548426006255,
1764
+ "learning_rate": 1.9982451257733047e-05,
1765
+ "loss": 1.1174,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.05,
1770
+ "grad_norm": 2.0028626956048434,
1771
+ "learning_rate": 1.9982079977030267e-05,
1772
+ "loss": 1.1028,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.05,
1777
+ "grad_norm": 1.96219145866627,
1778
+ "learning_rate": 1.9981704813242685e-05,
1779
+ "loss": 1.0566,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.05,
1784
+ "grad_norm": 2.072795047778876,
1785
+ "learning_rate": 1.9981325766516248e-05,
1786
+ "loss": 1.0744,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.05,
1791
+ "grad_norm": 2.036098657993234,
1792
+ "learning_rate": 1.9980942836998404e-05,
1793
+ "loss": 1.0763,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.05,
1798
+ "grad_norm": 2.1388481294252855,
1799
+ "learning_rate": 1.9980556024838116e-05,
1800
+ "loss": 1.1613,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.05,
1805
+ "grad_norm": 2.067974800297108,
1806
+ "learning_rate": 1.9980165330185857e-05,
1807
+ "loss": 0.998,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.05,
1812
+ "grad_norm": 1.8790643051942517,
1813
+ "learning_rate": 1.9979770753193605e-05,
1814
+ "loss": 0.996,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.05,
1819
+ "grad_norm": 1.9559433697812194,
1820
+ "learning_rate": 1.9979372294014854e-05,
1821
+ "loss": 1.0239,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.05,
1826
+ "grad_norm": 1.9308127181761399,
1827
+ "learning_rate": 1.9978969952804613e-05,
1828
+ "loss": 1.1269,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.05,
1833
+ "grad_norm": 1.924957556737311,
1834
+ "learning_rate": 1.9978563729719386e-05,
1835
+ "loss": 1.0322,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.05,
1840
+ "grad_norm": 2.119914670588116,
1841
+ "learning_rate": 1.99781536249172e-05,
1842
+ "loss": 1.111,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.05,
1847
+ "grad_norm": 2.2814838916359177,
1848
+ "learning_rate": 1.9977739638557593e-05,
1849
+ "loss": 0.9882,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.05,
1854
+ "grad_norm": 1.9764920210183117,
1855
+ "learning_rate": 1.99773217708016e-05,
1856
+ "loss": 1.0747,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.05,
1861
+ "grad_norm": 1.8237059936330955,
1862
+ "learning_rate": 1.997690002181178e-05,
1863
+ "loss": 1.0228,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.05,
1868
+ "grad_norm": 1.7957594475273144,
1869
+ "learning_rate": 1.9976474391752192e-05,
1870
+ "loss": 0.9876,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.05,
1875
+ "grad_norm": 1.9980073321283007,
1876
+ "learning_rate": 1.997604488078841e-05,
1877
+ "loss": 1.0911,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.05,
1882
+ "grad_norm": 2.0146788024415074,
1883
+ "learning_rate": 1.9975611489087516e-05,
1884
+ "loss": 1.022,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.05,
1889
+ "grad_norm": 2.1844582382911173,
1890
+ "learning_rate": 1.9975174216818097e-05,
1891
+ "loss": 1.0328,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.05,
1896
+ "grad_norm": 2.117333899762936,
1897
+ "learning_rate": 1.997473306415026e-05,
1898
+ "loss": 0.9903,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.05,
1903
+ "grad_norm": 1.8007107570814573,
1904
+ "learning_rate": 1.997428803125562e-05,
1905
+ "loss": 0.9672,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.05,
1910
+ "grad_norm": 2.094142577887572,
1911
+ "learning_rate": 1.9973839118307286e-05,
1912
+ "loss": 1.0761,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.05,
1917
+ "grad_norm": 1.9921256605922988,
1918
+ "learning_rate": 1.9973386325479897e-05,
1919
+ "loss": 1.0929,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.05,
1924
+ "grad_norm": 1.7196271013592903,
1925
+ "learning_rate": 1.9972929652949587e-05,
1926
+ "loss": 0.989,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.05,
1931
+ "grad_norm": 1.878734015541386,
1932
+ "learning_rate": 1.9972469100894005e-05,
1933
+ "loss": 1.0751,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.05,
1938
+ "grad_norm": 1.9232024443567461,
1939
+ "learning_rate": 1.9972004669492313e-05,
1940
+ "loss": 1.0705,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.05,
1945
+ "grad_norm": 1.2481706461115407,
1946
+ "learning_rate": 1.997153635892517e-05,
1947
+ "loss": 0.8429,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.05,
1952
+ "grad_norm": 1.8327598842861688,
1953
+ "learning_rate": 1.9971064169374755e-05,
1954
+ "loss": 1.0771,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.05,
1959
+ "grad_norm": 1.7554713225318588,
1960
+ "learning_rate": 1.9970588101024754e-05,
1961
+ "loss": 1.0262,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.05,
1966
+ "grad_norm": 2.1469666455805716,
1967
+ "learning_rate": 1.9970108154060357e-05,
1968
+ "loss": 1.0043,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.05,
1973
+ "grad_norm": 1.67449508407844,
1974
+ "learning_rate": 1.9969624328668267e-05,
1975
+ "loss": 0.9486,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.05,
1980
+ "grad_norm": 1.8820097189830565,
1981
+ "learning_rate": 1.9969136625036694e-05,
1982
+ "loss": 1.0906,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.05,
1987
+ "grad_norm": 2.1303500190062223,
1988
+ "learning_rate": 1.996864504335536e-05,
1989
+ "loss": 1.1237,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.05,
1994
+ "grad_norm": 1.780586955227666,
1995
+ "learning_rate": 1.9968149583815494e-05,
1996
+ "loss": 1.003,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.05,
2001
+ "grad_norm": 1.7489913602886422,
2002
+ "learning_rate": 1.996765024660983e-05,
2003
+ "loss": 0.9842,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.06,
2008
+ "grad_norm": 2.0155100896265767,
2009
+ "learning_rate": 1.996714703193261e-05,
2010
+ "loss": 1.0557,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.06,
2015
+ "grad_norm": 1.9438109572777202,
2016
+ "learning_rate": 1.996663993997959e-05,
2017
+ "loss": 0.9971,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.06,
2022
+ "grad_norm": 1.0728126863662977,
2023
+ "learning_rate": 1.9966128970948038e-05,
2024
+ "loss": 0.8342,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.06,
2029
+ "grad_norm": 1.9934840280210313,
2030
+ "learning_rate": 1.9965614125036712e-05,
2031
+ "loss": 1.0524,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.06,
2036
+ "grad_norm": 2.0936769507538386,
2037
+ "learning_rate": 1.9965095402445898e-05,
2038
+ "loss": 1.1212,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.06,
2043
+ "grad_norm": 1.9745427712772865,
2044
+ "learning_rate": 1.996457280337738e-05,
2045
+ "loss": 1.0978,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.06,
2050
+ "grad_norm": 1.9179177319145042,
2051
+ "learning_rate": 1.996404632803445e-05,
2052
+ "loss": 1.0146,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.06,
2057
+ "grad_norm": 2.052073495470475,
2058
+ "learning_rate": 1.9963515976621914e-05,
2059
+ "loss": 1.0465,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.06,
2064
+ "grad_norm": 1.8225286684088682,
2065
+ "learning_rate": 1.996298174934608e-05,
2066
+ "loss": 1.1047,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.06,
2071
+ "grad_norm": 1.7580289784696486,
2072
+ "learning_rate": 1.996244364641476e-05,
2073
+ "loss": 0.9965,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.06,
2078
+ "grad_norm": 2.0161159763669554,
2079
+ "learning_rate": 1.996190166803729e-05,
2080
+ "loss": 1.1507,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.06,
2085
+ "grad_norm": 1.8172911318254807,
2086
+ "learning_rate": 1.996135581442449e-05,
2087
+ "loss": 1.0353,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.06,
2092
+ "grad_norm": 1.8747317892295494,
2093
+ "learning_rate": 1.996080608578871e-05,
2094
+ "loss": 1.0875,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.06,
2099
+ "grad_norm": 2.0573127120786463,
2100
+ "learning_rate": 1.9960252482343797e-05,
2101
+ "loss": 1.0821,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.06,
2106
+ "grad_norm": 1.900633660421174,
2107
+ "learning_rate": 1.9959695004305097e-05,
2108
+ "loss": 1.0045,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.06,
2113
+ "grad_norm": 1.7491633697794904,
2114
+ "learning_rate": 1.995913365188948e-05,
2115
+ "loss": 1.0168,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.06,
2120
+ "grad_norm": 1.05599591440065,
2121
+ "learning_rate": 1.9958568425315316e-05,
2122
+ "loss": 0.9449,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.06,
2127
+ "grad_norm": 1.8883190997093964,
2128
+ "learning_rate": 1.9957999324802473e-05,
2129
+ "loss": 1.0428,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.06,
2134
+ "grad_norm": 1.720295899770073,
2135
+ "learning_rate": 1.9957426350572345e-05,
2136
+ "loss": 0.9482,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.06,
2141
+ "grad_norm": 1.9816495220080403,
2142
+ "learning_rate": 1.995684950284781e-05,
2143
+ "loss": 1.0557,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.06,
2148
+ "grad_norm": 1.92187930498817,
2149
+ "learning_rate": 1.9956268781853277e-05,
2150
+ "loss": 1.0582,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.06,
2155
+ "grad_norm": 1.795117789160023,
2156
+ "learning_rate": 1.9955684187814644e-05,
2157
+ "loss": 1.0761,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.06,
2162
+ "grad_norm": 1.9245112528044024,
2163
+ "learning_rate": 1.9955095720959318e-05,
2164
+ "loss": 1.1684,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.06,
2169
+ "grad_norm": 0.9632462029062842,
2170
+ "learning_rate": 1.9954503381516225e-05,
2171
+ "loss": 0.7674,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.06,
2176
+ "grad_norm": 1.9219486581712448,
2177
+ "learning_rate": 1.995390716971578e-05,
2178
+ "loss": 1.0211,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.06,
2183
+ "grad_norm": 1.9147529258042912,
2184
+ "learning_rate": 1.9953307085789916e-05,
2185
+ "loss": 1.0947,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.06,
2190
+ "grad_norm": 1.023656325583728,
2191
+ "learning_rate": 1.995270312997207e-05,
2192
+ "loss": 0.8131,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.06,
2197
+ "grad_norm": 1.7903741102627215,
2198
+ "learning_rate": 1.9952095302497185e-05,
2199
+ "loss": 0.9933,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.06,
2204
+ "grad_norm": 2.02294327217036,
2205
+ "learning_rate": 1.9951483603601703e-05,
2206
+ "loss": 0.9262,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.06,
2211
+ "grad_norm": 1.7932331946119509,
2212
+ "learning_rate": 1.9950868033523584e-05,
2213
+ "loss": 1.0388,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.06,
2218
+ "grad_norm": 1.9016906199071297,
2219
+ "learning_rate": 1.9950248592502286e-05,
2220
+ "loss": 1.0161,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.06,
2225
+ "grad_norm": 1.9496588477478443,
2226
+ "learning_rate": 1.994962528077878e-05,
2227
+ "loss": 1.0056,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.06,
2232
+ "grad_norm": 1.7857218614144716,
2233
+ "learning_rate": 1.9948998098595526e-05,
2234
+ "loss": 1.0717,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.06,
2239
+ "grad_norm": 2.2058906093436734,
2240
+ "learning_rate": 1.9948367046196513e-05,
2241
+ "loss": 1.0229,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.06,
2246
+ "grad_norm": 1.8833597215221982,
2247
+ "learning_rate": 1.9947732123827218e-05,
2248
+ "loss": 1.0789,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.06,
2253
+ "grad_norm": 1.0603717639007564,
2254
+ "learning_rate": 1.994709333173463e-05,
2255
+ "loss": 0.8642,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.06,
2260
+ "grad_norm": 2.033922433865109,
2261
+ "learning_rate": 1.994645067016725e-05,
2262
+ "loss": 1.0365,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.06,
2267
+ "grad_norm": 1.870516832634325,
2268
+ "learning_rate": 1.9945804139375066e-05,
2269
+ "loss": 0.9902,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.06,
2274
+ "grad_norm": 0.9861030358173385,
2275
+ "learning_rate": 1.9945153739609588e-05,
2276
+ "loss": 0.7725,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.06,
2281
+ "grad_norm": 1.9496791073979263,
2282
+ "learning_rate": 1.9944499471123824e-05,
2283
+ "loss": 1.0054,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.06,
2288
+ "grad_norm": 2.0447227654810196,
2289
+ "learning_rate": 1.9943841334172288e-05,
2290
+ "loss": 1.1126,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.06,
2295
+ "grad_norm": 2.24213973693733,
2296
+ "learning_rate": 1.9943179329010997e-05,
2297
+ "loss": 1.0988,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.06,
2302
+ "grad_norm": 1.8596491661660886,
2303
+ "learning_rate": 1.994251345589748e-05,
2304
+ "loss": 1.0312,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.06,
2309
+ "grad_norm": 1.9170393207754506,
2310
+ "learning_rate": 1.9941843715090758e-05,
2311
+ "loss": 1.0078,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.06,
2316
+ "grad_norm": 1.8284329304637323,
2317
+ "learning_rate": 1.994117010685137e-05,
2318
+ "loss": 0.9095,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.06,
2323
+ "grad_norm": 1.9552073759311999,
2324
+ "learning_rate": 1.9940492631441352e-05,
2325
+ "loss": 1.0652,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.06,
2330
+ "grad_norm": 2.0132724055989812,
2331
+ "learning_rate": 1.9939811289124246e-05,
2332
+ "loss": 1.0849,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.06,
2337
+ "grad_norm": 2.087593794800754,
2338
+ "learning_rate": 1.9939126080165093e-05,
2339
+ "loss": 1.0264,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.06,
2344
+ "grad_norm": 1.8617360148956503,
2345
+ "learning_rate": 1.9938437004830453e-05,
2346
+ "loss": 1.0128,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.06,
2351
+ "grad_norm": 1.6487974768481515,
2352
+ "learning_rate": 1.9937744063388365e-05,
2353
+ "loss": 0.924,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.06,
2358
+ "grad_norm": 1.8887708831775187,
2359
+ "learning_rate": 1.9937047256108405e-05,
2360
+ "loss": 0.9823,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.06,
2365
+ "grad_norm": 2.035534616225895,
2366
+ "learning_rate": 1.9936346583261622e-05,
2367
+ "loss": 1.0182,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.07,
2372
+ "grad_norm": 1.969898654916401,
2373
+ "learning_rate": 1.9935642045120585e-05,
2374
+ "loss": 1.0657,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.07,
2379
+ "grad_norm": 2.009217417503386,
2380
+ "learning_rate": 1.9934933641959367e-05,
2381
+ "loss": 0.9853,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.07,
2386
+ "grad_norm": 1.8124399073403066,
2387
+ "learning_rate": 1.9934221374053538e-05,
2388
+ "loss": 0.9696,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.07,
2393
+ "grad_norm": 1.9066949773049553,
2394
+ "learning_rate": 1.9933505241680176e-05,
2395
+ "loss": 1.1261,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.07,
2400
+ "grad_norm": 1.843104252573575,
2401
+ "learning_rate": 1.9932785245117852e-05,
2402
+ "loss": 1.0277,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.07,
2407
+ "grad_norm": 2.0257800926544487,
2408
+ "learning_rate": 1.9932061384646662e-05,
2409
+ "loss": 1.056,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.07,
2414
+ "grad_norm": 1.069660038019677,
2415
+ "learning_rate": 1.993133366054818e-05,
2416
+ "loss": 0.8464,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.07,
2421
+ "grad_norm": 2.047929245583957,
2422
+ "learning_rate": 1.9930602073105503e-05,
2423
+ "loss": 1.0297,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.07,
2428
+ "grad_norm": 1.7804271272628047,
2429
+ "learning_rate": 1.9929866622603217e-05,
2430
+ "loss": 0.9681,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.07,
2435
+ "grad_norm": 1.8036059077290953,
2436
+ "learning_rate": 1.992912730932742e-05,
2437
+ "loss": 1.0982,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.07,
2442
+ "grad_norm": 2.1577273526751513,
2443
+ "learning_rate": 1.992838413356571e-05,
2444
+ "loss": 1.0578,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.07,
2449
+ "grad_norm": 1.9351592416164614,
2450
+ "learning_rate": 1.992763709560718e-05,
2451
+ "loss": 1.0799,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.07,
2456
+ "grad_norm": 1.7613887958883605,
2457
+ "learning_rate": 1.992688619574244e-05,
2458
+ "loss": 1.118,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.07,
2463
+ "grad_norm": 1.7710807310053625,
2464
+ "learning_rate": 1.9926131434263587e-05,
2465
+ "loss": 1.0957,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.07,
2470
+ "grad_norm": 2.1014264167112024,
2471
+ "learning_rate": 1.9925372811464232e-05,
2472
+ "loss": 1.0916,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.07,
2477
+ "grad_norm": 1.695271742923848,
2478
+ "learning_rate": 1.9924610327639482e-05,
2479
+ "loss": 0.9742,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.07,
2484
+ "grad_norm": 1.946395684960528,
2485
+ "learning_rate": 1.992384398308595e-05,
2486
+ "loss": 1.0277,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.07,
2491
+ "grad_norm": 1.020284309819523,
2492
+ "learning_rate": 1.9923073778101743e-05,
2493
+ "loss": 0.8184,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.07,
2498
+ "grad_norm": 1.7877368746091395,
2499
+ "learning_rate": 1.9922299712986478e-05,
2500
+ "loss": 1.0512,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.07,
2505
+ "grad_norm": 1.9511674507474972,
2506
+ "learning_rate": 1.9921521788041273e-05,
2507
+ "loss": 0.9541,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.07,
2512
+ "grad_norm": 1.8548873026796064,
2513
+ "learning_rate": 1.9920740003568743e-05,
2514
+ "loss": 1.0032,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.07,
2519
+ "grad_norm": 2.369642361117581,
2520
+ "learning_rate": 1.9919954359873003e-05,
2521
+ "loss": 1.0463,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.07,
2526
+ "grad_norm": 1.6853151801856843,
2527
+ "learning_rate": 1.991916485725968e-05,
2528
+ "loss": 0.9586,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.07,
2533
+ "grad_norm": 2.121801973394243,
2534
+ "learning_rate": 1.991837149603589e-05,
2535
+ "loss": 1.007,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.07,
2540
+ "grad_norm": 1.8694623317506724,
2541
+ "learning_rate": 1.9917574276510256e-05,
2542
+ "loss": 1.0233,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.07,
2547
+ "grad_norm": 1.9936957782176836,
2548
+ "learning_rate": 1.99167731989929e-05,
2549
+ "loss": 1.11,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 0.07,
2554
+ "grad_norm": 2.044933129387799,
2555
+ "learning_rate": 1.9915968263795448e-05,
2556
+ "loss": 1.0585,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 0.07,
2561
+ "grad_norm": 1.9558810730478424,
2562
+ "learning_rate": 1.9915159471231025e-05,
2563
+ "loss": 0.9883,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 0.07,
2568
+ "grad_norm": 2.0169845204190078,
2569
+ "learning_rate": 1.9914346821614247e-05,
2570
+ "loss": 1.0129,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 0.07,
2575
+ "grad_norm": 2.0359412772425673,
2576
+ "learning_rate": 1.9913530315261252e-05,
2577
+ "loss": 1.0086,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 0.07,
2582
+ "grad_norm": 2.018034818878424,
2583
+ "learning_rate": 1.991270995248966e-05,
2584
+ "loss": 1.0717,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 0.07,
2589
+ "grad_norm": 1.9196933985110856,
2590
+ "learning_rate": 1.9911885733618594e-05,
2591
+ "loss": 1.0193,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 0.07,
2596
+ "grad_norm": 1.8924726827316862,
2597
+ "learning_rate": 1.9911057658968677e-05,
2598
+ "loss": 1.0684,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 0.07,
2603
+ "grad_norm": 1.957954173791168,
2604
+ "learning_rate": 1.9910225728862045e-05,
2605
+ "loss": 1.003,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 0.07,
2610
+ "grad_norm": 1.7327565474786015,
2611
+ "learning_rate": 1.9909389943622316e-05,
2612
+ "loss": 1.0367,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 0.07,
2617
+ "grad_norm": 2.1352232620719276,
2618
+ "learning_rate": 1.9908550303574617e-05,
2619
+ "loss": 1.1118,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 0.07,
2624
+ "grad_norm": 2.0787287987087506,
2625
+ "learning_rate": 1.990770680904557e-05,
2626
+ "loss": 1.0894,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 0.07,
2631
+ "grad_norm": 1.3620095751306678,
2632
+ "learning_rate": 1.9906859460363307e-05,
2633
+ "loss": 0.8552,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 0.07,
2638
+ "grad_norm": 1.9670341479798041,
2639
+ "learning_rate": 1.9906008257857447e-05,
2640
+ "loss": 0.9371,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 0.07,
2645
+ "grad_norm": 1.913167874526329,
2646
+ "learning_rate": 1.990515320185911e-05,
2647
+ "loss": 1.0643,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 0.07,
2652
+ "grad_norm": 1.9217382388951545,
2653
+ "learning_rate": 1.9904294292700917e-05,
2654
+ "loss": 1.0264,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 0.07,
2659
+ "grad_norm": 1.9352416915935249,
2660
+ "learning_rate": 1.9903431530716992e-05,
2661
+ "loss": 1.0726,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 0.07,
2666
+ "grad_norm": 2.032603191233027,
2667
+ "learning_rate": 1.9902564916242952e-05,
2668
+ "loss": 1.0659,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 0.07,
2673
+ "grad_norm": 1.9618668169033733,
2674
+ "learning_rate": 1.9901694449615917e-05,
2675
+ "loss": 1.0239,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 0.07,
2680
+ "grad_norm": 2.09195688744226,
2681
+ "learning_rate": 1.9900820131174503e-05,
2682
+ "loss": 1.0984,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 0.07,
2687
+ "grad_norm": 1.9234946021972024,
2688
+ "learning_rate": 1.989994196125882e-05,
2689
+ "loss": 1.0506,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 0.07,
2694
+ "grad_norm": 1.0991909496265084,
2695
+ "learning_rate": 1.989905994021049e-05,
2696
+ "loss": 0.8034,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 0.07,
2701
+ "grad_norm": 1.81014889387723,
2702
+ "learning_rate": 1.989817406837262e-05,
2703
+ "loss": 1.0006,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 0.07,
2708
+ "grad_norm": 0.993529462114099,
2709
+ "learning_rate": 1.989728434608981e-05,
2710
+ "loss": 0.8089,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 0.07,
2715
+ "grad_norm": 1.882727487143848,
2716
+ "learning_rate": 1.9896390773708182e-05,
2717
+ "loss": 1.0693,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 0.07,
2722
+ "grad_norm": 1.7729876511972384,
2723
+ "learning_rate": 1.9895493351575333e-05,
2724
+ "loss": 1.1044,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 0.07,
2729
+ "grad_norm": 1.8930447196671079,
2730
+ "learning_rate": 1.9894592080040364e-05,
2731
+ "loss": 1.0936,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 0.08,
2736
+ "grad_norm": 1.7141797791734572,
2737
+ "learning_rate": 1.9893686959453875e-05,
2738
+ "loss": 0.9307,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 0.08,
2743
+ "grad_norm": 2.0206681281369794,
2744
+ "learning_rate": 1.9892777990167967e-05,
2745
+ "loss": 1.0052,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 0.08,
2750
+ "grad_norm": 1.9601360739455025,
2751
+ "learning_rate": 1.9891865172536233e-05,
2752
+ "loss": 1.0426,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 0.08,
2757
+ "grad_norm": 1.6936067659027334,
2758
+ "learning_rate": 1.989094850691376e-05,
2759
+ "loss": 0.9326,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 0.08,
2764
+ "grad_norm": 1.856166304153269,
2765
+ "learning_rate": 1.989002799365714e-05,
2766
+ "loss": 0.9852,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 0.08,
2771
+ "grad_norm": 1.8367907200949016,
2772
+ "learning_rate": 1.9889103633124457e-05,
2773
+ "loss": 0.9592,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 0.08,
2778
+ "grad_norm": 2.007355585475035,
2779
+ "learning_rate": 1.9888175425675288e-05,
2780
+ "loss": 1.0117,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 0.08,
2785
+ "grad_norm": 1.8516073622878386,
2786
+ "learning_rate": 1.988724337167072e-05,
2787
+ "loss": 1.0603,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 0.08,
2792
+ "grad_norm": 1.216372170317351,
2793
+ "learning_rate": 1.9886307471473323e-05,
2794
+ "loss": 0.7921,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 0.08,
2799
+ "grad_norm": 1.9320279482943123,
2800
+ "learning_rate": 1.9885367725447162e-05,
2801
+ "loss": 1.0564,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 0.08,
2806
+ "grad_norm": 1.8561275651991433,
2807
+ "learning_rate": 1.9884424133957808e-05,
2808
+ "loss": 1.0022,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 0.08,
2813
+ "grad_norm": 1.912677537686615,
2814
+ "learning_rate": 1.9883476697372327e-05,
2815
+ "loss": 0.9387,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 0.08,
2820
+ "grad_norm": 1.0297626339996624,
2821
+ "learning_rate": 1.9882525416059273e-05,
2822
+ "loss": 0.8481,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 0.08,
2827
+ "grad_norm": 2.0247451338678344,
2828
+ "learning_rate": 1.98815702903887e-05,
2829
+ "loss": 0.9894,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 0.08,
2834
+ "grad_norm": 1.9871374845980427,
2835
+ "learning_rate": 1.9880611320732154e-05,
2836
+ "loss": 1.0576,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 0.08,
2841
+ "grad_norm": 1.9930155207385365,
2842
+ "learning_rate": 1.9879648507462687e-05,
2843
+ "loss": 0.9972,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 0.08,
2848
+ "grad_norm": 2.0646801640749652,
2849
+ "learning_rate": 1.9878681850954833e-05,
2850
+ "loss": 1.0854,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 0.08,
2855
+ "grad_norm": 1.8818333915154013,
2856
+ "learning_rate": 1.9877711351584628e-05,
2857
+ "loss": 1.0383,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 0.08,
2862
+ "grad_norm": 1.9722438634458774,
2863
+ "learning_rate": 1.98767370097296e-05,
2864
+ "loss": 1.0116,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 0.08,
2869
+ "grad_norm": 1.7066244506847275,
2870
+ "learning_rate": 1.987575882576878e-05,
2871
+ "loss": 1.0032,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 0.08,
2876
+ "grad_norm": 1.902672174295704,
2877
+ "learning_rate": 1.987477680008268e-05,
2878
+ "loss": 1.1152,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 0.08,
2883
+ "grad_norm": 1.7623694577336437,
2884
+ "learning_rate": 1.9873790933053316e-05,
2885
+ "loss": 0.9807,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 0.08,
2890
+ "grad_norm": 1.9894455403137112,
2891
+ "learning_rate": 1.9872801225064196e-05,
2892
+ "loss": 1.0516,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 0.08,
2897
+ "grad_norm": 2.1739518583820248,
2898
+ "learning_rate": 1.987180767650032e-05,
2899
+ "loss": 1.0914,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 0.08,
2904
+ "grad_norm": 1.7886753698199753,
2905
+ "learning_rate": 1.987081028774819e-05,
2906
+ "loss": 0.9163,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 0.08,
2911
+ "grad_norm": 1.1521609517012579,
2912
+ "learning_rate": 1.9869809059195787e-05,
2913
+ "loss": 0.8685,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 0.08,
2918
+ "grad_norm": 1.8376642390611246,
2919
+ "learning_rate": 1.9868803991232602e-05,
2920
+ "loss": 0.9614,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 0.08,
2925
+ "grad_norm": 1.8501436743338675,
2926
+ "learning_rate": 1.986779508424961e-05,
2927
+ "loss": 1.0526,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 0.08,
2932
+ "grad_norm": 1.6869946424617572,
2933
+ "learning_rate": 1.9866782338639278e-05,
2934
+ "loss": 1.0524,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 0.08,
2939
+ "grad_norm": 1.8153293231608487,
2940
+ "learning_rate": 1.986576575479557e-05,
2941
+ "loss": 1.0178,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 0.08,
2946
+ "grad_norm": 1.7274306454495725,
2947
+ "learning_rate": 1.9864745333113948e-05,
2948
+ "loss": 0.9729,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 0.08,
2953
+ "grad_norm": 1.939912973493156,
2954
+ "learning_rate": 1.986372107399136e-05,
2955
+ "loss": 1.0441,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 0.08,
2960
+ "grad_norm": 1.7856564272695379,
2961
+ "learning_rate": 1.9862692977826242e-05,
2962
+ "loss": 1.1091,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 0.08,
2967
+ "grad_norm": 1.8341112574380691,
2968
+ "learning_rate": 1.9861661045018537e-05,
2969
+ "loss": 0.8888,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 0.08,
2974
+ "grad_norm": 1.8561948420468832,
2975
+ "learning_rate": 1.9860625275969673e-05,
2976
+ "loss": 1.039,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 0.08,
2981
+ "grad_norm": 1.7934335505219023,
2982
+ "learning_rate": 1.9859585671082562e-05,
2983
+ "loss": 1.0336,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 0.08,
2988
+ "grad_norm": 1.8360599761712861,
2989
+ "learning_rate": 1.9858542230761622e-05,
2990
+ "loss": 1.0813,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 0.08,
2995
+ "grad_norm": 1.9867816840398522,
2996
+ "learning_rate": 1.985749495541276e-05,
2997
+ "loss": 1.0322,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 0.08,
3002
+ "grad_norm": 1.9480167546900247,
3003
+ "learning_rate": 1.9856443845443364e-05,
3004
+ "loss": 1.0453,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 0.08,
3009
+ "grad_norm": 2.1140835883562086,
3010
+ "learning_rate": 1.9855388901262324e-05,
3011
+ "loss": 1.0198,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 0.08,
3016
+ "grad_norm": 2.064005705298389,
3017
+ "learning_rate": 1.9854330123280027e-05,
3018
+ "loss": 1.0869,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 0.08,
3023
+ "grad_norm": 1.6915389255562758,
3024
+ "learning_rate": 1.985326751190833e-05,
3025
+ "loss": 1.0063,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 0.08,
3030
+ "grad_norm": 1.8715414211034649,
3031
+ "learning_rate": 1.9852201067560607e-05,
3032
+ "loss": 0.9858,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 0.08,
3037
+ "grad_norm": 1.9636600893192735,
3038
+ "learning_rate": 1.9851130790651706e-05,
3039
+ "loss": 1.0528,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 0.08,
3044
+ "grad_norm": 1.966849427909118,
3045
+ "learning_rate": 1.9850056681597968e-05,
3046
+ "loss": 1.0915,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 0.08,
3051
+ "grad_norm": 1.9070631155194202,
3052
+ "learning_rate": 1.9848978740817234e-05,
3053
+ "loss": 1.0174,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 0.08,
3058
+ "grad_norm": 1.225217117866621,
3059
+ "learning_rate": 1.984789696872882e-05,
3060
+ "loss": 0.8672,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 0.08,
3065
+ "grad_norm": 2.038760319545761,
3066
+ "learning_rate": 1.9846811365753548e-05,
3067
+ "loss": 1.0013,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 0.08,
3072
+ "grad_norm": 2.022940013987618,
3073
+ "learning_rate": 1.9845721932313725e-05,
3074
+ "loss": 0.9708,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 0.08,
3079
+ "grad_norm": 1.7647463910730028,
3080
+ "learning_rate": 1.984462866883314e-05,
3081
+ "loss": 0.9222,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 0.08,
3086
+ "grad_norm": 1.866488318733101,
3087
+ "learning_rate": 1.9843531575737085e-05,
3088
+ "loss": 1.043,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 0.08,
3093
+ "grad_norm": 1.8603090234733615,
3094
+ "learning_rate": 1.9842430653452333e-05,
3095
+ "loss": 0.9491,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 0.09,
3100
+ "grad_norm": 1.8875785862623655,
3101
+ "learning_rate": 1.9841325902407144e-05,
3102
+ "loss": 0.9926,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 0.09,
3107
+ "grad_norm": 1.942175598283091,
3108
+ "learning_rate": 1.9840217323031278e-05,
3109
+ "loss": 0.9455,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 0.09,
3114
+ "grad_norm": 1.985476015117722,
3115
+ "learning_rate": 1.983910491575598e-05,
3116
+ "loss": 1.0879,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 0.09,
3121
+ "grad_norm": 1.7275782937334652,
3122
+ "learning_rate": 1.9837988681013977e-05,
3123
+ "loss": 1.0377,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 0.09,
3128
+ "grad_norm": 2.0112594657447027,
3129
+ "learning_rate": 1.9836868619239498e-05,
3130
+ "loss": 0.9808,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 0.09,
3135
+ "grad_norm": 1.839058814041238,
3136
+ "learning_rate": 1.9835744730868244e-05,
3137
+ "loss": 0.8538,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 0.09,
3142
+ "grad_norm": 2.157369191952226,
3143
+ "learning_rate": 1.9834617016337424e-05,
3144
+ "loss": 1.0736,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 0.09,
3149
+ "grad_norm": 2.15228050930449,
3150
+ "learning_rate": 1.9833485476085715e-05,
3151
+ "loss": 1.019,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 0.09,
3156
+ "grad_norm": 1.91857747393063,
3157
+ "learning_rate": 1.98323501105533e-05,
3158
+ "loss": 1.0517,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 0.09,
3163
+ "grad_norm": 1.027868590912365,
3164
+ "learning_rate": 1.983121092018184e-05,
3165
+ "loss": 0.793,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 0.09,
3170
+ "grad_norm": 1.773990990913634,
3171
+ "learning_rate": 1.9830067905414485e-05,
3172
+ "loss": 1.0535,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 0.09,
3177
+ "grad_norm": 1.7448900958278026,
3178
+ "learning_rate": 1.9828921066695876e-05,
3179
+ "loss": 1.0646,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 0.09,
3184
+ "grad_norm": 1.8842052222344852,
3185
+ "learning_rate": 1.982777040447214e-05,
3186
+ "loss": 0.9916,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 0.09,
3191
+ "grad_norm": 1.965498295082324,
3192
+ "learning_rate": 1.9826615919190886e-05,
3193
+ "loss": 1.0308,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 0.09,
3198
+ "grad_norm": 1.8825201063090378,
3199
+ "learning_rate": 1.9825457611301226e-05,
3200
+ "loss": 1.0029,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 0.09,
3205
+ "grad_norm": 2.0328819583947006,
3206
+ "learning_rate": 1.9824295481253735e-05,
3207
+ "loss": 1.07,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 0.09,
3212
+ "grad_norm": 1.0825105072372898,
3213
+ "learning_rate": 1.98231295295005e-05,
3214
+ "loss": 0.7738,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 0.09,
3219
+ "grad_norm": 1.8165626539270863,
3220
+ "learning_rate": 1.9821959756495075e-05,
3221
+ "loss": 1.0831,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 0.09,
3226
+ "grad_norm": 1.9422401630853525,
3227
+ "learning_rate": 1.982078616269251e-05,
3228
+ "loss": 1.0181,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 0.09,
3233
+ "grad_norm": 1.7945631288777881,
3234
+ "learning_rate": 1.981960874854934e-05,
3235
+ "loss": 0.946,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 0.09,
3240
+ "grad_norm": 1.997337758639312,
3241
+ "learning_rate": 1.9818427514523584e-05,
3242
+ "loss": 1.0037,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 0.09,
3247
+ "grad_norm": 1.9193241141993849,
3248
+ "learning_rate": 1.9817242461074757e-05,
3249
+ "loss": 1.0171,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 0.09,
3254
+ "grad_norm": 1.9978405533297976,
3255
+ "learning_rate": 1.981605358866384e-05,
3256
+ "loss": 1.0468,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 0.09,
3261
+ "grad_norm": 1.8804833385106348,
3262
+ "learning_rate": 1.9814860897753317e-05,
3263
+ "loss": 0.916,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 0.09,
3268
+ "grad_norm": 1.8028266192668139,
3269
+ "learning_rate": 1.981366438880715e-05,
3270
+ "loss": 1.0217,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 0.09,
3275
+ "grad_norm": 1.7132667749630526,
3276
+ "learning_rate": 1.9812464062290788e-05,
3277
+ "loss": 1.0445,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 0.09,
3282
+ "grad_norm": 1.9219672750165928,
3283
+ "learning_rate": 1.9811259918671168e-05,
3284
+ "loss": 1.031,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 0.09,
3289
+ "grad_norm": 1.8280416256736887,
3290
+ "learning_rate": 1.9810051958416697e-05,
3291
+ "loss": 1.0184,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 0.09,
3296
+ "grad_norm": 1.6689592882194266,
3297
+ "learning_rate": 1.9808840181997292e-05,
3298
+ "loss": 1.0227,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 0.09,
3303
+ "grad_norm": 1.900220242233606,
3304
+ "learning_rate": 1.9807624589884335e-05,
3305
+ "loss": 1.0608,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 0.09,
3310
+ "grad_norm": 1.6929314568440184,
3311
+ "learning_rate": 1.98064051825507e-05,
3312
+ "loss": 0.9899,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 0.09,
3317
+ "grad_norm": 1.651258459418155,
3318
+ "learning_rate": 1.980518196047074e-05,
3319
+ "loss": 0.9661,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 0.09,
3324
+ "grad_norm": 2.1874289610603563,
3325
+ "learning_rate": 1.9803954924120297e-05,
3326
+ "loss": 0.9393,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 0.09,
3331
+ "grad_norm": 1.8038819153786403,
3332
+ "learning_rate": 1.9802724073976695e-05,
3333
+ "loss": 0.9559,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 0.09,
3338
+ "grad_norm": 1.770721462261662,
3339
+ "learning_rate": 1.9801489410518736e-05,
3340
+ "loss": 0.9643,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 0.09,
3345
+ "grad_norm": 1.7367654491312072,
3346
+ "learning_rate": 1.9800250934226723e-05,
3347
+ "loss": 0.9443,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 0.09,
3352
+ "grad_norm": 1.9591444421711552,
3353
+ "learning_rate": 1.9799008645582424e-05,
3354
+ "loss": 0.9747,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 0.09,
3359
+ "grad_norm": 1.6828464935006877,
3360
+ "learning_rate": 1.979776254506909e-05,
3361
+ "loss": 0.9754,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 0.09,
3366
+ "grad_norm": 1.908226452531261,
3367
+ "learning_rate": 1.9796512633171476e-05,
3368
+ "loss": 1.1313,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 0.09,
3373
+ "grad_norm": 1.306422799793475,
3374
+ "learning_rate": 1.9795258910375787e-05,
3375
+ "loss": 0.8817,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 0.09,
3380
+ "grad_norm": 1.9053129529215438,
3381
+ "learning_rate": 1.979400137716974e-05,
3382
+ "loss": 1.0261,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 0.09,
3387
+ "grad_norm": 1.9080635923357674,
3388
+ "learning_rate": 1.979274003404252e-05,
3389
+ "loss": 0.9686,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 0.09,
3394
+ "grad_norm": 1.8037616024087626,
3395
+ "learning_rate": 1.9791474881484793e-05,
3396
+ "loss": 1.0324,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 0.09,
3401
+ "grad_norm": 1.8250327442496437,
3402
+ "learning_rate": 1.9790205919988714e-05,
3403
+ "loss": 1.0082,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 0.09,
3408
+ "grad_norm": 1.8511505666088204,
3409
+ "learning_rate": 1.9788933150047916e-05,
3410
+ "loss": 1.1118,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 0.09,
3415
+ "grad_norm": 1.8903056078178093,
3416
+ "learning_rate": 1.9787656572157515e-05,
3417
+ "loss": 1.0646,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 0.09,
3422
+ "grad_norm": 1.9195313614337501,
3423
+ "learning_rate": 1.97863761868141e-05,
3424
+ "loss": 1.0412,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 0.09,
3429
+ "grad_norm": 1.9799264468742026,
3430
+ "learning_rate": 1.9785091994515756e-05,
3431
+ "loss": 1.0861,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 0.09,
3436
+ "grad_norm": 1.6755241928671092,
3437
+ "learning_rate": 1.9783803995762033e-05,
3438
+ "loss": 0.9611,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 0.09,
3443
+ "grad_norm": 1.961898488303003,
3444
+ "learning_rate": 1.9782512191053982e-05,
3445
+ "loss": 1.0589,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 0.09,
3450
+ "grad_norm": 1.775413845673962,
3451
+ "learning_rate": 1.9781216580894108e-05,
3452
+ "loss": 1.0354,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 0.09,
3457
+ "grad_norm": 1.7928396588919673,
3458
+ "learning_rate": 1.977991716578642e-05,
3459
+ "loss": 1.0508,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 0.1,
3464
+ "grad_norm": 1.9412161829079344,
3465
+ "learning_rate": 1.9778613946236395e-05,
3466
+ "loss": 1.0015,
3467
+ "step": 494
3468
+ },
3469
+ {
3470
+ "epoch": 0.1,
3471
+ "grad_norm": 1.7096885758847509,
3472
+ "learning_rate": 1.9777306922750995e-05,
3473
+ "loss": 0.9801,
3474
+ "step": 495
3475
+ },
3476
+ {
3477
+ "epoch": 0.1,
3478
+ "grad_norm": 1.8191213564062976,
3479
+ "learning_rate": 1.9775996095838655e-05,
3480
+ "loss": 1.0899,
3481
+ "step": 496
3482
+ },
3483
+ {
3484
+ "epoch": 0.1,
3485
+ "grad_norm": 1.964813155629249,
3486
+ "learning_rate": 1.9774681466009295e-05,
3487
+ "loss": 1.053,
3488
+ "step": 497
3489
+ },
3490
+ {
3491
+ "epoch": 0.1,
3492
+ "grad_norm": 1.8601508656062495,
3493
+ "learning_rate": 1.9773363033774312e-05,
3494
+ "loss": 1.034,
3495
+ "step": 498
3496
+ },
3497
+ {
3498
+ "epoch": 0.1,
3499
+ "grad_norm": 1.5995716944146932,
3500
+ "learning_rate": 1.977204079964659e-05,
3501
+ "loss": 0.9518,
3502
+ "step": 499
3503
+ },
3504
+ {
3505
+ "epoch": 0.1,
3506
+ "grad_norm": 1.9695321697574193,
3507
+ "learning_rate": 1.977071476414048e-05,
3508
+ "loss": 0.9849,
3509
+ "step": 500
3510
+ }
3511
+ ],
3512
+ "logging_steps": 1.0,
3513
+ "max_steps": 5193,
3514
+ "num_input_tokens_seen": 0,
3515
+ "num_train_epochs": 1,
3516
+ "save_steps": 500,
3517
+ "total_flos": 678526663131136.0,
3518
+ "train_batch_size": 4,
3519
+ "trial_name": null,
3520
+ "trial_params": null
3521
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753ca89c616551aba38e20d12dc4b4b4f5d9b0fe72ebbc846089c9420b01c2cc
3
+ size 6904
checkpoint-500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)