Hugging Face's logo

nkkbr
/
ViCA-5p

Safetensors
llava
Model card Files
xet
 Community
nkkbr commited on
Commit
cbeb994
·
1 Parent(s): 6181eb7

Initial commit

Browse files
Files changed (25) hide show
  1. added_tokens.json +6 -0
  2. config.json +222 -0
  3. generation_config.json +14 -0
  4. latest +1 -0
  5. merges.txt +0 -0
  6. model-00001-of-00004.safetensors +3 -0
  7. model-00002-of-00004.safetensors +3 -0
  8. model-00003-of-00004.safetensors +3 -0
  9. model-00004-of-00004.safetensors +3 -0
  10. model.safetensors.index.json +772 -0
  11. rng_state_0.pth +3 -0
  12. rng_state_1.pth +3 -0
  13. rng_state_2.pth +3 -0
  14. rng_state_3.pth +3 -0
  15. rng_state_4.pth +3 -0
  16. rng_state_5.pth +3 -0
  17. rng_state_6.pth +3 -0
  18. rng_state_7.pth +3 -0
  19. special_tokens_map.json +20 -0
  20. tokenizer.json +0 -0
  21. tokenizer_config.json +53 -0
  22. trainer_state.json +3626 -0
  23. training_args.bin +3 -0
  24. vocab.json +0 -0
  25. zero_to_fp32.py +587 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
config.json ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lmms-lab/LLaVA-Video-7B-Qwen2",
3
+ "add_faster_video": false,
4
+ "add_time_instruction": true,
5
+ "architectures": [
6
+ "LlavaQwenForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 151643,
10
+ "eos_token_id": 151645,
11
+ "faster_token_stride": 10,
12
+ "force_sample": true,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 3584,
15
+ "ignore_index": -100,
16
+ "image_aspect_ratio": "anyres_max_9",
17
+ "image_crop_resolution": null,
18
+ "image_grid_pinpoints": [
19
+ [
20
+ 384,
21
+ 384
22
+ ],
23
+ [
24
+ 384,
25
+ 768
26
+ ],
27
+ [
28
+ 384,
29
+ 1152
30
+ ],
31
+ [
32
+ 384,
33
+ 1536
34
+ ],
35
+ [
36
+ 384,
37
+ 1920
38
+ ],
39
+ [
40
+ 384,
41
+ 2304
42
+ ],
43
+ [
44
+ 768,
45
+ 384
46
+ ],
47
+ [
48
+ 768,
49
+ 768
50
+ ],
51
+ [
52
+ 768,
53
+ 1152
54
+ ],
55
+ [
56
+ 768,
57
+ 1536
58
+ ],
59
+ [
60
+ 768,
61
+ 1920
62
+ ],
63
+ [
64
+ 768,
65
+ 2304
66
+ ],
67
+ [
68
+ 1152,
69
+ 384
70
+ ],
71
+ [
72
+ 1152,
73
+ 768
74
+ ],
75
+ [
76
+ 1152,
77
+ 1152
78
+ ],
79
+ [
80
+ 1152,
81
+ 1536
82
+ ],
83
+ [
84
+ 1152,
85
+ 1920
86
+ ],
87
+ [
88
+ 1152,
89
+ 2304
90
+ ],
91
+ [
92
+ 1536,
93
+ 384
94
+ ],
95
+ [
96
+ 1536,
97
+ 768
98
+ ],
99
+ [
100
+ 1536,
101
+ 1152
102
+ ],
103
+ [
104
+ 1536,
105
+ 1536
106
+ ],
107
+ [
108
+ 1536,
109
+ 1920
110
+ ],
111
+ [
112
+ 1536,
113
+ 2304
114
+ ],
115
+ [
116
+ 1920,
117
+ 384
118
+ ],
119
+ [
120
+ 1920,
121
+ 768
122
+ ],
123
+ [
124
+ 1920,
125
+ 1152
126
+ ],
127
+ [
128
+ 1920,
129
+ 1536
130
+ ],
131
+ [
132
+ 1920,
133
+ 1920
134
+ ],
135
+ [
136
+ 1920,
137
+ 2304
138
+ ],
139
+ [
140
+ 2304,
141
+ 384
142
+ ],
143
+ [
144
+ 2304,
145
+ 768
146
+ ],
147
+ [
148
+ 2304,
149
+ 1152
150
+ ],
151
+ [
152
+ 2304,
153
+ 1536
154
+ ],
155
+ [
156
+ 2304,
157
+ 1920
158
+ ],
159
+ [
160
+ 2304,
161
+ 2304
162
+ ]
163
+ ],
164
+ "image_split_resolution": null,
165
+ "image_token_index": 151646,
166
+ "initializer_range": 0.02,
167
+ "intermediate_size": 18944,
168
+ "max_position_embeddings": 32768,
169
+ "max_window_layers": 28,
170
+ "mm_hidden_size": 1152,
171
+ "mm_newline_position": "grid",
172
+ "mm_patch_merge_type": "spatial_unpad",
173
+ "mm_projector_lr": null,
174
+ "mm_projector_type": "mlp2x_gelu",
175
+ "mm_resampler_type": null,
176
+ "mm_spatial_pool_mode": "bilinear",
177
+ "mm_spatial_pool_stride": 2,
178
+ "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
179
+ "mm_use_im_patch_token": false,
180
+ "mm_use_im_start_end": false,
181
+ "mm_vision_select_feature": "patch",
182
+ "mm_vision_select_layer": -2,
183
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
184
+ "mm_vision_tower_lr": 2e-06,
185
+ "model_type": "llava",
186
+ "num_attention_heads": 28,
187
+ "num_hidden_layers": 28,
188
+ "num_key_value_heads": 4,
189
+ "pos_skipping_range": 4096,
190
+ "projector_hidden_act": "gelu",
191
+ "rms_norm_eps": 1e-06,
192
+ "rope_scaling": null,
193
+ "rope_theta": 1000000.0,
194
+ "sliding_window": 131072,
195
+ "text_config": {
196
+ "model_type": "llama"
197
+ },
198
+ "tie_word_embeddings": false,
199
+ "tokenizer_model_max_length": 32768,
200
+ "tokenizer_padding_side": "right",
201
+ "torch_dtype": "bfloat16",
202
+ "transformers_version": "4.40.0",
203
+ "use_cache": false,
204
+ "use_mm_proj": true,
205
+ "use_pos_skipping": false,
206
+ "use_sliding_window": false,
207
+ "vision_config": {
208
+ "hidden_size": 1024,
209
+ "image_size": 336,
210
+ "intermediate_size": 4096,
211
+ "model_type": "clip_vision_model",
212
+ "num_attention_heads": 16,
213
+ "num_hidden_layers": 24,
214
+ "patch_size": 14,
215
+ "projection_dim": 768,
216
+ "vocab_size": 32000
217
+ },
218
+ "vision_feature_layer": -2,
219
+ "vision_feature_select_strategy": "default",
220
+ "vision_tower_pretrained": null,
221
+ "vocab_size": 152064
222
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.40.0"
14
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step515
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853975681bded7417798cfdb00d6d68f804ab808521c5e70eda09fb530727a37
3
+ size 4877668032
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a66d6f6b275d84d24ccfb1464bde9c14b2b80749b082f1ee12b1d664bdf7a0b9
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79680fcf26f51b3926014019862b48511cc19b485af553d1aacb2b38f18f0eda
3
+ size 4994571904
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97273487ea01f6ccfa9c5b17eb122a977e77b3f3e656811c6678f0d5720043ba
3
+ size 1255812224
model.safetensors.index.json ADDED
@@ -0,0 +1,772 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060697664
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.image_newline": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
346
+ "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
347
+ "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
348
+ "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
349
+ "model.norm.weight": "model-00003-of-00004.safetensors",
350
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
351
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
352
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
353
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
354
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
355
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
356
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
357
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
358
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
359
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
360
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
361
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
362
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
363
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
364
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
365
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
366
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
367
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
368
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
369
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
370
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
371
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
372
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
373
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
374
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
375
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
760
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
761
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
762
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
763
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
764
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
765
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
766
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
767
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
768
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
769
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
770
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
771
+ }
772
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b3c6f2db9f50108f2e51dec816343d2907b4c1118633a9b219028a69c9edcb
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f67d551c62104bb78104d72ef653d80f9523d200faf55153faf34af87a68f2a
3
+ size 15984
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7dc7406851a9b637546e2d7c7e97165b0d6a1196dc06d39b0c8a84fdee0d0f
3
+ size 15984
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d673bd65354e6dd01931805be1907fe8ba44e5c3205781b57546ad9ebaef407
3
+ size 15984
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f420d27a0fac0bc6f1f4884ff839dbd9dcb9d9a8add2f89cf4006c3ac0de87
3
+ size 15984
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6ff342e777fddbce01471106edf85225d14d3d21552247ecee1e5623a4506b
3
+ size 15984
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e36fa824756fe5d8ebe764c4a3ef2ede4d907993ae79e182bfb5b735b31b1206
3
+ size 15984
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b3c8474578c15fcd3fcaabe90a3c16f18ae30ea33804c432305a99a2b3a4ef
3
+ size 15984
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "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'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 32768,
47
+ "pad_token": "<|endoftext|>",
48
+ "padding_side": "right",
49
+ "processor_class": "LlavaProcessor",
50
+ "split_special_tokens": false,
51
+ "tokenizer_class": "Qwen2Tokenizer",
52
+ "unk_token": null
53
+ }
trainer_state.json ADDED
@@ -0,0 +1,3626 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.05012165450121654,
5
+ "eval_steps": 500,
6
+ "global_step": 515,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 9.732360097323601e-05,
13
+ "grad_norm": 16.13226202148005,
14
+ "learning_rate": 3.2362459546925574e-08,
15
+ "loss": 1.1997,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.00019464720194647202,
20
+ "grad_norm": 15.765097511926365,
21
+ "learning_rate": 6.472491909385115e-08,
22
+ "loss": 1.384,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.00029197080291970805,
27
+ "grad_norm": 16.64113665586635,
28
+ "learning_rate": 9.70873786407767e-08,
29
+ "loss": 1.2291,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.00038929440389294404,
34
+ "grad_norm": 20.34864047521242,
35
+ "learning_rate": 1.294498381877023e-07,
36
+ "loss": 0.9025,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.00048661800486618007,
41
+ "grad_norm": 28.710711096046108,
42
+ "learning_rate": 1.6181229773462782e-07,
43
+ "loss": 1.0305,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.0005839416058394161,
48
+ "grad_norm": 21.945801992582915,
49
+ "learning_rate": 1.941747572815534e-07,
50
+ "loss": 1.0979,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.0006812652068126521,
55
+ "grad_norm": 23.947905905644966,
56
+ "learning_rate": 2.26537216828479e-07,
57
+ "loss": 1.1909,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.0007785888077858881,
62
+ "grad_norm": 19.835016686730835,
63
+ "learning_rate": 2.588996763754046e-07,
64
+ "loss": 1.2083,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.0008759124087591241,
69
+ "grad_norm": 16.926846352507788,
70
+ "learning_rate": 2.9126213592233014e-07,
71
+ "loss": 1.2369,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.0009732360097323601,
76
+ "grad_norm": 21.349924470647284,
77
+ "learning_rate": 3.2362459546925565e-07,
78
+ "loss": 1.0052,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.0010705596107055961,
83
+ "grad_norm": 25.127579741628022,
84
+ "learning_rate": 3.5598705501618125e-07,
85
+ "loss": 1.2631,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.0011678832116788322,
90
+ "grad_norm": 12.524049131196549,
91
+ "learning_rate": 3.883495145631068e-07,
92
+ "loss": 1.0884,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.001265206812652068,
97
+ "grad_norm": 20.706648432487587,
98
+ "learning_rate": 4.207119741100324e-07,
99
+ "loss": 1.1469,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.0013625304136253042,
104
+ "grad_norm": 17.655230197318655,
105
+ "learning_rate": 4.53074433656958e-07,
106
+ "loss": 1.2922,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.00145985401459854,
111
+ "grad_norm": 16.550170455008725,
112
+ "learning_rate": 4.854368932038835e-07,
113
+ "loss": 1.1792,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.0015571776155717761,
118
+ "grad_norm": 24.456798845425887,
119
+ "learning_rate": 5.177993527508092e-07,
120
+ "loss": 1.0804,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.0016545012165450122,
125
+ "grad_norm": 14.659117460865279,
126
+ "learning_rate": 5.501618122977346e-07,
127
+ "loss": 1.0973,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.0017518248175182481,
132
+ "grad_norm": 15.324823146378344,
133
+ "learning_rate": 5.825242718446603e-07,
134
+ "loss": 0.9791,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.0018491484184914842,
139
+ "grad_norm": 12.483869597287145,
140
+ "learning_rate": 6.148867313915858e-07,
141
+ "loss": 1.0829,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.0019464720194647203,
146
+ "grad_norm": 11.921211994178957,
147
+ "learning_rate": 6.472491909385113e-07,
148
+ "loss": 0.6862,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.0020437956204379564,
153
+ "grad_norm": 14.53279456676939,
154
+ "learning_rate": 6.79611650485437e-07,
155
+ "loss": 0.7814,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.0021411192214111923,
160
+ "grad_norm": 15.68359520937104,
161
+ "learning_rate": 7.119741100323625e-07,
162
+ "loss": 0.883,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.002238442822384428,
167
+ "grad_norm": 14.062468532950906,
168
+ "learning_rate": 7.443365695792882e-07,
169
+ "loss": 1.0087,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.0023357664233576644,
174
+ "grad_norm": 11.150778403716444,
175
+ "learning_rate": 7.766990291262136e-07,
176
+ "loss": 0.4884,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.0024330900243309003,
181
+ "grad_norm": 7.740982223602688,
182
+ "learning_rate": 8.090614886731392e-07,
183
+ "loss": 0.8543,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.002530413625304136,
188
+ "grad_norm": 6.4338060169141915,
189
+ "learning_rate": 8.414239482200648e-07,
190
+ "loss": 0.7948,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.002627737226277372,
195
+ "grad_norm": 6.227022582398367,
196
+ "learning_rate": 8.737864077669904e-07,
197
+ "loss": 0.7814,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.0027250608272506084,
202
+ "grad_norm": 7.989531820662516,
203
+ "learning_rate": 9.06148867313916e-07,
204
+ "loss": 0.5645,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.0028223844282238442,
209
+ "grad_norm": 6.4745089193753,
210
+ "learning_rate": 9.385113268608415e-07,
211
+ "loss": 0.6802,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.00291970802919708,
216
+ "grad_norm": 8.23650018531745,
217
+ "learning_rate": 9.70873786407767e-07,
218
+ "loss": 0.6218,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.0030170316301703164,
223
+ "grad_norm": 4.915479010119541,
224
+ "learning_rate": 1.0032362459546926e-06,
225
+ "loss": 0.8879,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.0031143552311435523,
230
+ "grad_norm": 4.288138757396447,
231
+ "learning_rate": 1.0355987055016184e-06,
232
+ "loss": 0.5917,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.003211678832116788,
237
+ "grad_norm": 4.230901102531741,
238
+ "learning_rate": 1.0679611650485437e-06,
239
+ "loss": 0.7373,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.0033090024330900245,
244
+ "grad_norm": 4.714303656539792,
245
+ "learning_rate": 1.1003236245954693e-06,
246
+ "loss": 0.5886,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.0034063260340632603,
251
+ "grad_norm": 4.1204943469600925,
252
+ "learning_rate": 1.132686084142395e-06,
253
+ "loss": 0.5991,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.0035036496350364962,
258
+ "grad_norm": 3.124375547961107,
259
+ "learning_rate": 1.1650485436893206e-06,
260
+ "loss": 0.432,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.0036009732360097325,
265
+ "grad_norm": 3.741153837090354,
266
+ "learning_rate": 1.197411003236246e-06,
267
+ "loss": 0.6379,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.0036982968369829684,
272
+ "grad_norm": 3.7740270813504506,
273
+ "learning_rate": 1.2297734627831717e-06,
274
+ "loss": 0.5595,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.0037956204379562043,
279
+ "grad_norm": 4.783986424289694,
280
+ "learning_rate": 1.2621359223300972e-06,
281
+ "loss": 0.8717,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.0038929440389294406,
286
+ "grad_norm": 4.242597978097827,
287
+ "learning_rate": 1.2944983818770226e-06,
288
+ "loss": 0.6632,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.0039902676399026765,
293
+ "grad_norm": 4.309602952976607,
294
+ "learning_rate": 1.3268608414239483e-06,
295
+ "loss": 0.7191,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.004087591240875913,
300
+ "grad_norm": 4.136462382872819,
301
+ "learning_rate": 1.359223300970874e-06,
302
+ "loss": 0.6782,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.004184914841849148,
307
+ "grad_norm": 4.2148643401229,
308
+ "learning_rate": 1.3915857605177997e-06,
309
+ "loss": 0.8932,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.0042822384428223845,
314
+ "grad_norm": 3.829331188520966,
315
+ "learning_rate": 1.423948220064725e-06,
316
+ "loss": 0.4697,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.004379562043795621,
321
+ "grad_norm": 3.4564347781684557,
322
+ "learning_rate": 1.4563106796116506e-06,
323
+ "loss": 0.3377,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.004476885644768856,
328
+ "grad_norm": 3.319649807488789,
329
+ "learning_rate": 1.4886731391585763e-06,
330
+ "loss": 0.4589,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.0045742092457420926,
335
+ "grad_norm": 3.8856546910308034,
336
+ "learning_rate": 1.5210355987055017e-06,
337
+ "loss": 0.8413,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.004671532846715329,
342
+ "grad_norm": 3.7955924171570605,
343
+ "learning_rate": 1.5533980582524272e-06,
344
+ "loss": 0.588,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.004768856447688564,
349
+ "grad_norm": 4.5762685715882805,
350
+ "learning_rate": 1.585760517799353e-06,
351
+ "loss": 0.6472,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.004866180048661801,
356
+ "grad_norm": 4.284420204063246,
357
+ "learning_rate": 1.6181229773462783e-06,
358
+ "loss": 0.5233,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.004963503649635037,
363
+ "grad_norm": 4.0399534913964645,
364
+ "learning_rate": 1.650485436893204e-06,
365
+ "loss": 0.6737,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.005060827250608272,
370
+ "grad_norm": 4.850258079033273,
371
+ "learning_rate": 1.6828478964401297e-06,
372
+ "loss": 0.5017,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.005158150851581509,
377
+ "grad_norm": 3.289730774319516,
378
+ "learning_rate": 1.715210355987055e-06,
379
+ "loss": 0.6378,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.005255474452554744,
384
+ "grad_norm": 3.116783938182044,
385
+ "learning_rate": 1.7475728155339808e-06,
386
+ "loss": 0.5681,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.00535279805352798,
391
+ "grad_norm": 3.5896487509946677,
392
+ "learning_rate": 1.7799352750809063e-06,
393
+ "loss": 0.5222,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.005450121654501217,
398
+ "grad_norm": 3.3627737905222146,
399
+ "learning_rate": 1.812297734627832e-06,
400
+ "loss": 0.351,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.005547445255474452,
405
+ "grad_norm": 3.405981770724818,
406
+ "learning_rate": 1.8446601941747574e-06,
407
+ "loss": 0.5832,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.0056447688564476885,
412
+ "grad_norm": 3.231134680455488,
413
+ "learning_rate": 1.877022653721683e-06,
414
+ "loss": 0.5558,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.005742092457420925,
419
+ "grad_norm": 4.2963387449464605,
420
+ "learning_rate": 1.9093851132686085e-06,
421
+ "loss": 0.7544,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.00583941605839416,
426
+ "grad_norm": 3.3678084152804315,
427
+ "learning_rate": 1.941747572815534e-06,
428
+ "loss": 0.554,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.0059367396593673965,
433
+ "grad_norm": 3.635756089652443,
434
+ "learning_rate": 1.9741100323624596e-06,
435
+ "loss": 0.5312,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.006034063260340633,
440
+ "grad_norm": 3.91764256649437,
441
+ "learning_rate": 2.006472491909385e-06,
442
+ "loss": 0.4329,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.006131386861313868,
447
+ "grad_norm": 3.4866607421863565,
448
+ "learning_rate": 2.0388349514563107e-06,
449
+ "loss": 0.4453,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.006228710462287105,
454
+ "grad_norm": 2.9369425143161147,
455
+ "learning_rate": 2.0711974110032367e-06,
456
+ "loss": 0.467,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.006326034063260341,
461
+ "grad_norm": 3.0906723589687024,
462
+ "learning_rate": 2.103559870550162e-06,
463
+ "loss": 0.3917,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.006423357664233576,
468
+ "grad_norm": 3.5121616512799747,
469
+ "learning_rate": 2.1359223300970874e-06,
470
+ "loss": 0.6428,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.006520681265206813,
475
+ "grad_norm": 3.470270871630247,
476
+ "learning_rate": 2.1682847896440134e-06,
477
+ "loss": 0.586,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.006618004866180049,
482
+ "grad_norm": 2.8689679430782498,
483
+ "learning_rate": 2.2006472491909385e-06,
484
+ "loss": 0.2938,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.006715328467153284,
489
+ "grad_norm": 4.115573400175418,
490
+ "learning_rate": 2.2330097087378645e-06,
491
+ "loss": 0.3855,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.006812652068126521,
496
+ "grad_norm": 3.903319335204406,
497
+ "learning_rate": 2.26537216828479e-06,
498
+ "loss": 0.6272,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.006909975669099757,
503
+ "grad_norm": 2.649165320750572,
504
+ "learning_rate": 2.297734627831715e-06,
505
+ "loss": 0.5229,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.0070072992700729924,
510
+ "grad_norm": 2.8543884488184235,
511
+ "learning_rate": 2.330097087378641e-06,
512
+ "loss": 0.4006,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.007104622871046229,
517
+ "grad_norm": 2.9817247056794134,
518
+ "learning_rate": 2.3624595469255667e-06,
519
+ "loss": 0.2331,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.007201946472019465,
524
+ "grad_norm": 3.592880940053797,
525
+ "learning_rate": 2.394822006472492e-06,
526
+ "loss": 0.4889,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.0072992700729927005,
531
+ "grad_norm": 2.89844013224274,
532
+ "learning_rate": 2.427184466019418e-06,
533
+ "loss": 0.4711,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.007396593673965937,
538
+ "grad_norm": 2.6071345596032134,
539
+ "learning_rate": 2.4595469255663434e-06,
540
+ "loss": 0.4844,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.007493917274939173,
545
+ "grad_norm": 2.9053930844585776,
546
+ "learning_rate": 2.491909385113269e-06,
547
+ "loss": 0.5163,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.0075912408759124085,
552
+ "grad_norm": 3.4016540038418115,
553
+ "learning_rate": 2.5242718446601945e-06,
554
+ "loss": 0.5852,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.007688564476885645,
559
+ "grad_norm": 2.7133170026932887,
560
+ "learning_rate": 2.55663430420712e-06,
561
+ "loss": 0.4934,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.007785888077858881,
566
+ "grad_norm": 3.2321439410345585,
567
+ "learning_rate": 2.588996763754045e-06,
568
+ "loss": 0.62,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.007883211678832117,
573
+ "grad_norm": 2.6835948161160545,
574
+ "learning_rate": 2.621359223300971e-06,
575
+ "loss": 0.4689,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.007980535279805353,
580
+ "grad_norm": 4.716894934604404,
581
+ "learning_rate": 2.6537216828478967e-06,
582
+ "loss": 0.3364,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.00807785888077859,
587
+ "grad_norm": 2.6507857723180646,
588
+ "learning_rate": 2.686084142394822e-06,
589
+ "loss": 0.3785,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.008175182481751826,
594
+ "grad_norm": 2.356714630861861,
595
+ "learning_rate": 2.718446601941748e-06,
596
+ "loss": 0.2591,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.00827250608272506,
601
+ "grad_norm": 2.755477478688418,
602
+ "learning_rate": 2.7508090614886734e-06,
603
+ "loss": 0.4762,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.008369829683698296,
608
+ "grad_norm": 3.7771581783688837,
609
+ "learning_rate": 2.7831715210355993e-06,
610
+ "loss": 0.4627,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.008467153284671533,
615
+ "grad_norm": 2.8568450908810257,
616
+ "learning_rate": 2.8155339805825245e-06,
617
+ "loss": 0.4322,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.008564476885644769,
622
+ "grad_norm": 2.914756058289183,
623
+ "learning_rate": 2.84789644012945e-06,
624
+ "loss": 0.4835,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.008661800486618005,
629
+ "grad_norm": 2.414182197047686,
630
+ "learning_rate": 2.880258899676376e-06,
631
+ "loss": 0.493,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.008759124087591242,
636
+ "grad_norm": 2.8597853736106975,
637
+ "learning_rate": 2.912621359223301e-06,
638
+ "loss": 0.6063,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.008856447688564476,
643
+ "grad_norm": 2.4567808863650007,
644
+ "learning_rate": 2.9449838187702267e-06,
645
+ "loss": 0.5874,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.008953771289537713,
650
+ "grad_norm": 2.819434031784131,
651
+ "learning_rate": 2.9773462783171527e-06,
652
+ "loss": 0.552,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.009051094890510949,
657
+ "grad_norm": 1.9840396387462764,
658
+ "learning_rate": 3.0097087378640778e-06,
659
+ "loss": 0.3736,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.009148418491484185,
664
+ "grad_norm": 2.52047300259283,
665
+ "learning_rate": 3.0420711974110033e-06,
666
+ "loss": 0.407,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.009245742092457421,
671
+ "grad_norm": 3.140839526692518,
672
+ "learning_rate": 3.0744336569579293e-06,
673
+ "loss": 0.6513,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.009343065693430658,
678
+ "grad_norm": 3.1368865731879554,
679
+ "learning_rate": 3.1067961165048544e-06,
680
+ "loss": 0.4804,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.009440389294403892,
685
+ "grad_norm": 2.6987222968513196,
686
+ "learning_rate": 3.13915857605178e-06,
687
+ "loss": 0.4228,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.009537712895377129,
692
+ "grad_norm": 2.5779408707034026,
693
+ "learning_rate": 3.171521035598706e-06,
694
+ "loss": 0.4654,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.009635036496350365,
699
+ "grad_norm": 2.5189587792888934,
700
+ "learning_rate": 3.2038834951456315e-06,
701
+ "loss": 0.5465,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.009732360097323601,
706
+ "grad_norm": 2.457408493992738,
707
+ "learning_rate": 3.2362459546925567e-06,
708
+ "loss": 0.5077,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.009829683698296838,
713
+ "grad_norm": 2.445932328031196,
714
+ "learning_rate": 3.2686084142394826e-06,
715
+ "loss": 0.492,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.009927007299270074,
720
+ "grad_norm": 2.3199141960061915,
721
+ "learning_rate": 3.300970873786408e-06,
722
+ "loss": 0.4432,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.010024330900243308,
727
+ "grad_norm": 3.88769555780582,
728
+ "learning_rate": 3.3333333333333333e-06,
729
+ "loss": 0.3684,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.010121654501216545,
734
+ "grad_norm": 2.63905676146042,
735
+ "learning_rate": 3.3656957928802593e-06,
736
+ "loss": 0.4238,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.010218978102189781,
741
+ "grad_norm": 3.0073749174392885,
742
+ "learning_rate": 3.398058252427185e-06,
743
+ "loss": 0.4655,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.010316301703163017,
748
+ "grad_norm": 2.613524831872459,
749
+ "learning_rate": 3.43042071197411e-06,
750
+ "loss": 0.4948,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.010413625304136254,
755
+ "grad_norm": 2.4293628733346764,
756
+ "learning_rate": 3.462783171521036e-06,
757
+ "loss": 0.3717,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.010510948905109488,
762
+ "grad_norm": 3.3036504610837016,
763
+ "learning_rate": 3.4951456310679615e-06,
764
+ "loss": 0.4939,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.010608272506082725,
769
+ "grad_norm": 2.6808221933664846,
770
+ "learning_rate": 3.5275080906148866e-06,
771
+ "loss": 0.4809,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.01070559610705596,
776
+ "grad_norm": 2.853958419293739,
777
+ "learning_rate": 3.5598705501618126e-06,
778
+ "loss": 0.4066,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.010802919708029197,
783
+ "grad_norm": 5.3412930378250145,
784
+ "learning_rate": 3.592233009708738e-06,
785
+ "loss": 0.3599,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.010900243309002433,
790
+ "grad_norm": 2.983669976646381,
791
+ "learning_rate": 3.624595469255664e-06,
792
+ "loss": 0.6187,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.01099756690997567,
797
+ "grad_norm": 3.388543821878077,
798
+ "learning_rate": 3.6569579288025893e-06,
799
+ "loss": 0.717,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.011094890510948904,
804
+ "grad_norm": 3.0720120062792127,
805
+ "learning_rate": 3.689320388349515e-06,
806
+ "loss": 0.5057,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.01119221411192214,
811
+ "grad_norm": 2.521868238475485,
812
+ "learning_rate": 3.721682847896441e-06,
813
+ "loss": 0.4308,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.011289537712895377,
818
+ "grad_norm": 2.641085251645149,
819
+ "learning_rate": 3.754045307443366e-06,
820
+ "loss": 0.4047,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.011386861313868613,
825
+ "grad_norm": 2.6936547530255828,
826
+ "learning_rate": 3.7864077669902915e-06,
827
+ "loss": 0.5548,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.01148418491484185,
832
+ "grad_norm": 5.599830434139348,
833
+ "learning_rate": 3.818770226537217e-06,
834
+ "loss": 0.5338,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.011581508515815086,
839
+ "grad_norm": 2.6372065340185378,
840
+ "learning_rate": 3.851132686084142e-06,
841
+ "loss": 0.4833,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.01167883211678832,
846
+ "grad_norm": 2.555049765563167,
847
+ "learning_rate": 3.883495145631068e-06,
848
+ "loss": 0.4295,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.011776155717761557,
853
+ "grad_norm": 2.22725048478721,
854
+ "learning_rate": 3.915857605177994e-06,
855
+ "loss": 0.4074,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.011873479318734793,
860
+ "grad_norm": 3.0093045583939984,
861
+ "learning_rate": 3.948220064724919e-06,
862
+ "loss": 0.7168,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.01197080291970803,
867
+ "grad_norm": 2.8800338131191223,
868
+ "learning_rate": 3.980582524271845e-06,
869
+ "loss": 0.3826,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.012068126520681266,
874
+ "grad_norm": 2.3197904571086974,
875
+ "learning_rate": 4.01294498381877e-06,
876
+ "loss": 0.2584,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.012165450121654502,
881
+ "grad_norm": 2.929540360888414,
882
+ "learning_rate": 4.045307443365696e-06,
883
+ "loss": 0.4617,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.012262773722627737,
888
+ "grad_norm": 2.5602803735383137,
889
+ "learning_rate": 4.0776699029126215e-06,
890
+ "loss": 0.2561,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.012360097323600973,
895
+ "grad_norm": 2.676345297957673,
896
+ "learning_rate": 4.1100323624595475e-06,
897
+ "loss": 0.2996,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.01245742092457421,
902
+ "grad_norm": 1.9047794610871986,
903
+ "learning_rate": 4.1423948220064734e-06,
904
+ "loss": 0.3475,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.012554744525547445,
909
+ "grad_norm": 2.9014607006450555,
910
+ "learning_rate": 4.1747572815533986e-06,
911
+ "loss": 0.4748,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.012652068126520682,
916
+ "grad_norm": 2.2992367182815987,
917
+ "learning_rate": 4.207119741100324e-06,
918
+ "loss": 0.3465,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.012749391727493918,
923
+ "grad_norm": 2.668874383033437,
924
+ "learning_rate": 4.23948220064725e-06,
925
+ "loss": 0.6119,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.012846715328467153,
930
+ "grad_norm": 2.69106703615133,
931
+ "learning_rate": 4.271844660194175e-06,
932
+ "loss": 0.4743,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.012944038929440389,
937
+ "grad_norm": 2.972314561813759,
938
+ "learning_rate": 4.304207119741101e-06,
939
+ "loss": 0.5766,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.013041362530413625,
944
+ "grad_norm": 2.7487017428059635,
945
+ "learning_rate": 4.336569579288027e-06,
946
+ "loss": 0.5818,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.013138686131386862,
951
+ "grad_norm": 3.1117207482379663,
952
+ "learning_rate": 4.368932038834952e-06,
953
+ "loss": 0.6468,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.013236009732360098,
958
+ "grad_norm": 2.781796948090657,
959
+ "learning_rate": 4.401294498381877e-06,
960
+ "loss": 0.7209,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.013333333333333334,
965
+ "grad_norm": 2.5480533986327556,
966
+ "learning_rate": 4.433656957928803e-06,
967
+ "loss": 0.5907,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.013430656934306569,
972
+ "grad_norm": 2.054397852683208,
973
+ "learning_rate": 4.466019417475729e-06,
974
+ "loss": 0.4079,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.013527980535279805,
979
+ "grad_norm": 2.2564046621809037,
980
+ "learning_rate": 4.498381877022654e-06,
981
+ "loss": 0.4,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.013625304136253041,
986
+ "grad_norm": 2.8739841159071022,
987
+ "learning_rate": 4.53074433656958e-06,
988
+ "loss": 0.5819,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.013722627737226278,
993
+ "grad_norm": 2.6418540847993657,
994
+ "learning_rate": 4.563106796116505e-06,
995
+ "loss": 0.589,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.013819951338199514,
1000
+ "grad_norm": 2.431908870746442,
1001
+ "learning_rate": 4.59546925566343e-06,
1002
+ "loss": 0.5468,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.013917274939172749,
1007
+ "grad_norm": 4.44933942542394,
1008
+ "learning_rate": 4.627831715210356e-06,
1009
+ "loss": 0.3846,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.014014598540145985,
1014
+ "grad_norm": 2.2469929628351126,
1015
+ "learning_rate": 4.660194174757282e-06,
1016
+ "loss": 0.3047,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.014111922141119221,
1021
+ "grad_norm": 2.8361034502388205,
1022
+ "learning_rate": 4.6925566343042074e-06,
1023
+ "loss": 0.4186,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.014209245742092457,
1028
+ "grad_norm": 2.485184255788147,
1029
+ "learning_rate": 4.724919093851133e-06,
1030
+ "loss": 0.455,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.014306569343065694,
1035
+ "grad_norm": 2.677307495548506,
1036
+ "learning_rate": 4.7572815533980585e-06,
1037
+ "loss": 0.6346,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.01440389294403893,
1042
+ "grad_norm": 2.9440091029213034,
1043
+ "learning_rate": 4.789644012944984e-06,
1044
+ "loss": 0.4961,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.014501216545012165,
1049
+ "grad_norm": 2.6810327828724723,
1050
+ "learning_rate": 4.82200647249191e-06,
1051
+ "loss": 0.3754,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.014598540145985401,
1056
+ "grad_norm": 2.519257002697837,
1057
+ "learning_rate": 4.854368932038836e-06,
1058
+ "loss": 0.249,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.014695863746958637,
1063
+ "grad_norm": 2.8041238457488578,
1064
+ "learning_rate": 4.886731391585761e-06,
1065
+ "loss": 0.3117,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.014793187347931874,
1070
+ "grad_norm": 2.363481194731433,
1071
+ "learning_rate": 4.919093851132687e-06,
1072
+ "loss": 0.3325,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.01489051094890511,
1077
+ "grad_norm": 3.078347599868747,
1078
+ "learning_rate": 4.951456310679612e-06,
1079
+ "loss": 0.3569,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.014987834549878346,
1084
+ "grad_norm": 3.2926461094535515,
1085
+ "learning_rate": 4.983818770226538e-06,
1086
+ "loss": 0.716,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.01508515815085158,
1091
+ "grad_norm": 2.340052421830345,
1092
+ "learning_rate": 5.016181229773464e-06,
1093
+ "loss": 0.2642,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.015182481751824817,
1098
+ "grad_norm": 1.8915730140906823,
1099
+ "learning_rate": 5.048543689320389e-06,
1100
+ "loss": 0.3523,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.015279805352798053,
1105
+ "grad_norm": 4.2448533254564484,
1106
+ "learning_rate": 5.080906148867314e-06,
1107
+ "loss": 0.5185,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.01537712895377129,
1112
+ "grad_norm": 2.1172922256300333,
1113
+ "learning_rate": 5.11326860841424e-06,
1114
+ "loss": 0.3341,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.015474452554744526,
1119
+ "grad_norm": 2.7414250631657113,
1120
+ "learning_rate": 5.145631067961165e-06,
1121
+ "loss": 0.5965,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.015571776155717762,
1126
+ "grad_norm": 1.977804344185745,
1127
+ "learning_rate": 5.17799352750809e-06,
1128
+ "loss": 0.239,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.015669099756690997,
1133
+ "grad_norm": 2.771807640315191,
1134
+ "learning_rate": 5.210355987055017e-06,
1135
+ "loss": 0.4122,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.015766423357664233,
1140
+ "grad_norm": 1.9977073642008174,
1141
+ "learning_rate": 5.242718446601942e-06,
1142
+ "loss": 0.3423,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.01586374695863747,
1147
+ "grad_norm": 3.222730527079622,
1148
+ "learning_rate": 5.275080906148867e-06,
1149
+ "loss": 0.5647,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.015961070559610706,
1154
+ "grad_norm": 2.95441646694508,
1155
+ "learning_rate": 5.307443365695793e-06,
1156
+ "loss": 0.5198,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.016058394160583942,
1161
+ "grad_norm": 2.3346384576429116,
1162
+ "learning_rate": 5.3398058252427185e-06,
1163
+ "loss": 0.3516,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.01615571776155718,
1168
+ "grad_norm": 2.089159587923689,
1169
+ "learning_rate": 5.372168284789644e-06,
1170
+ "loss": 0.3704,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.016253041362530415,
1175
+ "grad_norm": 2.8135820638465088,
1176
+ "learning_rate": 5.4045307443365705e-06,
1177
+ "loss": 0.3729,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.01635036496350365,
1182
+ "grad_norm": 2.991259557993277,
1183
+ "learning_rate": 5.436893203883496e-06,
1184
+ "loss": 0.5622,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.016447688564476887,
1189
+ "grad_norm": 3.1512644455187857,
1190
+ "learning_rate": 5.4692556634304216e-06,
1191
+ "loss": 0.5915,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.01654501216545012,
1196
+ "grad_norm": 2.616126184062516,
1197
+ "learning_rate": 5.501618122977347e-06,
1198
+ "loss": 0.4252,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.016642335766423356,
1203
+ "grad_norm": 1.9958281517625203,
1204
+ "learning_rate": 5.533980582524272e-06,
1205
+ "loss": 0.3704,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.016739659367396593,
1210
+ "grad_norm": 2.470731302334384,
1211
+ "learning_rate": 5.566343042071199e-06,
1212
+ "loss": 0.4373,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.01683698296836983,
1217
+ "grad_norm": 2.583270308023139,
1218
+ "learning_rate": 5.598705501618124e-06,
1219
+ "loss": 0.4125,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.016934306569343065,
1224
+ "grad_norm": 1.9644684632241667,
1225
+ "learning_rate": 5.631067961165049e-06,
1226
+ "loss": 0.3522,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.0170316301703163,
1231
+ "grad_norm": 2.4207097357376046,
1232
+ "learning_rate": 5.663430420711975e-06,
1233
+ "loss": 0.3579,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.017128953771289538,
1238
+ "grad_norm": 2.3511041847292034,
1239
+ "learning_rate": 5.6957928802589e-06,
1240
+ "loss": 0.5412,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.017226277372262774,
1245
+ "grad_norm": 2.274427899539275,
1246
+ "learning_rate": 5.728155339805825e-06,
1247
+ "loss": 0.5353,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.01732360097323601,
1252
+ "grad_norm": 2.133749284526256,
1253
+ "learning_rate": 5.760517799352752e-06,
1254
+ "loss": 0.4392,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.017420924574209247,
1259
+ "grad_norm": 2.3097462109285787,
1260
+ "learning_rate": 5.792880258899677e-06,
1261
+ "loss": 0.4442,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.017518248175182483,
1266
+ "grad_norm": 2.2128802818602056,
1267
+ "learning_rate": 5.825242718446602e-06,
1268
+ "loss": 0.5635,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.017615571776155716,
1273
+ "grad_norm": 2.103405792854256,
1274
+ "learning_rate": 5.857605177993528e-06,
1275
+ "loss": 0.4533,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.017712895377128952,
1280
+ "grad_norm": 2.0565661990183597,
1281
+ "learning_rate": 5.889967637540453e-06,
1282
+ "loss": 0.3806,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.01781021897810219,
1287
+ "grad_norm": 2.179649872267064,
1288
+ "learning_rate": 5.9223300970873785e-06,
1289
+ "loss": 0.3842,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.017907542579075425,
1294
+ "grad_norm": 3.8333244047199146,
1295
+ "learning_rate": 5.954692556634305e-06,
1296
+ "loss": 0.3876,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.01800486618004866,
1301
+ "grad_norm": 2.2893517217095716,
1302
+ "learning_rate": 5.9870550161812304e-06,
1303
+ "loss": 0.4781,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.018102189781021898,
1308
+ "grad_norm": 1.6022498167897639,
1309
+ "learning_rate": 6.0194174757281556e-06,
1310
+ "loss": 0.2306,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.018199513381995134,
1315
+ "grad_norm": 2.32863493589546,
1316
+ "learning_rate": 6.0517799352750815e-06,
1317
+ "loss": 0.5139,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.01829683698296837,
1322
+ "grad_norm": 2.0789478938631314,
1323
+ "learning_rate": 6.084142394822007e-06,
1324
+ "loss": 0.2824,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.018394160583941607,
1329
+ "grad_norm": 1.7544615955949223,
1330
+ "learning_rate": 6.116504854368932e-06,
1331
+ "loss": 0.4172,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.018491484184914843,
1336
+ "grad_norm": 1.931043696572374,
1337
+ "learning_rate": 6.148867313915859e-06,
1338
+ "loss": 0.3584,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.01858880778588808,
1343
+ "grad_norm": 2.467258437370788,
1344
+ "learning_rate": 6.181229773462784e-06,
1345
+ "loss": 0.462,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.018686131386861315,
1350
+ "grad_norm": 2.1541091684996965,
1351
+ "learning_rate": 6.213592233009709e-06,
1352
+ "loss": 0.3967,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.01878345498783455,
1357
+ "grad_norm": 2.2330486922808395,
1358
+ "learning_rate": 6.245954692556635e-06,
1359
+ "loss": 0.5316,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.018880778588807785,
1364
+ "grad_norm": 2.3498262097642395,
1365
+ "learning_rate": 6.27831715210356e-06,
1366
+ "loss": 0.4815,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.01897810218978102,
1371
+ "grad_norm": 1.7045092076002246,
1372
+ "learning_rate": 6.310679611650487e-06,
1373
+ "loss": 0.3,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.019075425790754257,
1378
+ "grad_norm": 2.5703331850837023,
1379
+ "learning_rate": 6.343042071197412e-06,
1380
+ "loss": 0.4143,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.019172749391727494,
1385
+ "grad_norm": 2.6940646171495133,
1386
+ "learning_rate": 6.375404530744337e-06,
1387
+ "loss": 0.5463,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.01927007299270073,
1392
+ "grad_norm": 2.4185580273524847,
1393
+ "learning_rate": 6.407766990291263e-06,
1394
+ "loss": 0.5215,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.019367396593673966,
1399
+ "grad_norm": 2.6509824694985946,
1400
+ "learning_rate": 6.440129449838188e-06,
1401
+ "loss": 0.5286,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.019464720194647202,
1406
+ "grad_norm": 2.4807219128312767,
1407
+ "learning_rate": 6.472491909385113e-06,
1408
+ "loss": 0.3996,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.01956204379562044,
1413
+ "grad_norm": 2.651883834043772,
1414
+ "learning_rate": 6.50485436893204e-06,
1415
+ "loss": 0.3499,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.019659367396593675,
1420
+ "grad_norm": 2.670759179984812,
1421
+ "learning_rate": 6.537216828478965e-06,
1422
+ "loss": 0.552,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.01975669099756691,
1427
+ "grad_norm": 2.51305850829245,
1428
+ "learning_rate": 6.56957928802589e-06,
1429
+ "loss": 0.3806,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.019854014598540148,
1434
+ "grad_norm": 2.435954851305265,
1435
+ "learning_rate": 6.601941747572816e-06,
1436
+ "loss": 0.6093,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.01995133819951338,
1441
+ "grad_norm": 2.091315833022872,
1442
+ "learning_rate": 6.6343042071197415e-06,
1443
+ "loss": 0.3573,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.020048661800486617,
1448
+ "grad_norm": 2.205515437184344,
1449
+ "learning_rate": 6.666666666666667e-06,
1450
+ "loss": 0.2892,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.020145985401459853,
1455
+ "grad_norm": 2.314981932930035,
1456
+ "learning_rate": 6.6990291262135935e-06,
1457
+ "loss": 0.4184,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.02024330900243309,
1462
+ "grad_norm": 1.9102474885146974,
1463
+ "learning_rate": 6.731391585760519e-06,
1464
+ "loss": 0.2287,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.020340632603406326,
1469
+ "grad_norm": 1.9408029275065433,
1470
+ "learning_rate": 6.763754045307444e-06,
1471
+ "loss": 0.3958,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.020437956204379562,
1476
+ "grad_norm": 2.1006467731485823,
1477
+ "learning_rate": 6.79611650485437e-06,
1478
+ "loss": 0.3764,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.0205352798053528,
1483
+ "grad_norm": 2.0927447282795146,
1484
+ "learning_rate": 6.828478964401295e-06,
1485
+ "loss": 0.531,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.020632603406326035,
1490
+ "grad_norm": 3.4830081465453633,
1491
+ "learning_rate": 6.86084142394822e-06,
1492
+ "loss": 0.4887,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.02072992700729927,
1497
+ "grad_norm": 2.253360993066953,
1498
+ "learning_rate": 6.893203883495147e-06,
1499
+ "loss": 0.4587,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.020827250608272507,
1504
+ "grad_norm": 3.3751096354443852,
1505
+ "learning_rate": 6.925566343042072e-06,
1506
+ "loss": 0.3427,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.020924574209245744,
1511
+ "grad_norm": 1.9729713112803993,
1512
+ "learning_rate": 6.957928802588997e-06,
1513
+ "loss": 0.384,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.021021897810218976,
1518
+ "grad_norm": 2.761285167796522,
1519
+ "learning_rate": 6.990291262135923e-06,
1520
+ "loss": 0.3512,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.021119221411192213,
1525
+ "grad_norm": 2.431882400442612,
1526
+ "learning_rate": 7.022653721682848e-06,
1527
+ "loss": 0.3971,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.02121654501216545,
1532
+ "grad_norm": 3.659254877088116,
1533
+ "learning_rate": 7.055016181229773e-06,
1534
+ "loss": 0.4115,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.021313868613138685,
1539
+ "grad_norm": 2.5501534359714655,
1540
+ "learning_rate": 7.0873786407767e-06,
1541
+ "loss": 0.4963,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.02141119221411192,
1546
+ "grad_norm": 4.296894309260591,
1547
+ "learning_rate": 7.119741100323625e-06,
1548
+ "loss": 0.5203,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.021508515815085158,
1553
+ "grad_norm": 2.5489854552137237,
1554
+ "learning_rate": 7.152103559870551e-06,
1555
+ "loss": 0.4343,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.021605839416058394,
1560
+ "grad_norm": 2.00955207958064,
1561
+ "learning_rate": 7.184466019417476e-06,
1562
+ "loss": 0.3603,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.02170316301703163,
1567
+ "grad_norm": 2.2675038932590224,
1568
+ "learning_rate": 7.2168284789644015e-06,
1569
+ "loss": 0.3968,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.021800486618004867,
1574
+ "grad_norm": 2.4690586331753277,
1575
+ "learning_rate": 7.249190938511328e-06,
1576
+ "loss": 0.5883,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.021897810218978103,
1581
+ "grad_norm": 2.141328682063472,
1582
+ "learning_rate": 7.2815533980582534e-06,
1583
+ "loss": 0.3547,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.02199513381995134,
1588
+ "grad_norm": 2.223927434368622,
1589
+ "learning_rate": 7.3139158576051786e-06,
1590
+ "loss": 0.5031,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.022092457420924576,
1595
+ "grad_norm": 2.8602320319532346,
1596
+ "learning_rate": 7.3462783171521046e-06,
1597
+ "loss": 0.4226,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.02218978102189781,
1602
+ "grad_norm": 2.8852449405031835,
1603
+ "learning_rate": 7.37864077669903e-06,
1604
+ "loss": 0.4298,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.022287104622871045,
1609
+ "grad_norm": 1.7370522944561966,
1610
+ "learning_rate": 7.411003236245955e-06,
1611
+ "loss": 0.3827,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.02238442822384428,
1616
+ "grad_norm": 2.3907908463140584,
1617
+ "learning_rate": 7.443365695792882e-06,
1618
+ "loss": 0.4139,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.022481751824817518,
1623
+ "grad_norm": 2.27581306432663,
1624
+ "learning_rate": 7.475728155339807e-06,
1625
+ "loss": 0.4736,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.022579075425790754,
1630
+ "grad_norm": 2.1861094823645675,
1631
+ "learning_rate": 7.508090614886732e-06,
1632
+ "loss": 0.4809,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.02267639902676399,
1637
+ "grad_norm": 1.9626208371421419,
1638
+ "learning_rate": 7.540453074433658e-06,
1639
+ "loss": 0.3436,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.022773722627737226,
1644
+ "grad_norm": 1.7092390993202267,
1645
+ "learning_rate": 7.572815533980583e-06,
1646
+ "loss": 0.3224,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.022871046228710463,
1651
+ "grad_norm": 3.0168693228526546,
1652
+ "learning_rate": 7.605177993527508e-06,
1653
+ "loss": 0.6366,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.0229683698296837,
1658
+ "grad_norm": 2.424919921496664,
1659
+ "learning_rate": 7.637540453074434e-06,
1660
+ "loss": 0.4483,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.023065693430656935,
1665
+ "grad_norm": 2.4586833984787626,
1666
+ "learning_rate": 7.66990291262136e-06,
1667
+ "loss": 0.4031,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.02316301703163017,
1672
+ "grad_norm": 2.092010230715883,
1673
+ "learning_rate": 7.702265372168284e-06,
1674
+ "loss": 0.4257,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.023260340632603408,
1679
+ "grad_norm": 2.3360188447701655,
1680
+ "learning_rate": 7.734627831715211e-06,
1681
+ "loss": 0.4684,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.02335766423357664,
1686
+ "grad_norm": 2.087175894606599,
1687
+ "learning_rate": 7.766990291262136e-06,
1688
+ "loss": 0.4272,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.023454987834549877,
1693
+ "grad_norm": 2.598684557686617,
1694
+ "learning_rate": 7.799352750809061e-06,
1695
+ "loss": 0.5401,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.023552311435523113,
1700
+ "grad_norm": 2.025117037181364,
1701
+ "learning_rate": 7.831715210355988e-06,
1702
+ "loss": 0.372,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.02364963503649635,
1707
+ "grad_norm": 2.2467324584398405,
1708
+ "learning_rate": 7.864077669902913e-06,
1709
+ "loss": 0.5891,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.023746958637469586,
1714
+ "grad_norm": 2.38036373195977,
1715
+ "learning_rate": 7.896440129449839e-06,
1716
+ "loss": 0.5133,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.023844282238442822,
1721
+ "grad_norm": 2.052700924442009,
1722
+ "learning_rate": 7.928802588996765e-06,
1723
+ "loss": 0.5161,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.02394160583941606,
1728
+ "grad_norm": 3.4299018810240254,
1729
+ "learning_rate": 7.96116504854369e-06,
1730
+ "loss": 0.5314,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.024038929440389295,
1735
+ "grad_norm": 1.3903956706369247,
1736
+ "learning_rate": 7.993527508090616e-06,
1737
+ "loss": 0.3539,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.02413625304136253,
1742
+ "grad_norm": 2.4599878810180873,
1743
+ "learning_rate": 8.02588996763754e-06,
1744
+ "loss": 0.4876,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.024233576642335768,
1749
+ "grad_norm": 2.4053308291912083,
1750
+ "learning_rate": 8.058252427184466e-06,
1751
+ "loss": 0.5185,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.024330900243309004,
1756
+ "grad_norm": 1.6624263546342495,
1757
+ "learning_rate": 8.090614886731393e-06,
1758
+ "loss": 0.2909,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.024428223844282237,
1763
+ "grad_norm": 2.4091367373679597,
1764
+ "learning_rate": 8.122977346278318e-06,
1765
+ "loss": 0.6192,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.024525547445255473,
1770
+ "grad_norm": 2.4595313520548427,
1771
+ "learning_rate": 8.155339805825243e-06,
1772
+ "loss": 0.3444,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.02462287104622871,
1777
+ "grad_norm": 2.3200411140153174,
1778
+ "learning_rate": 8.18770226537217e-06,
1779
+ "loss": 0.6112,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.024720194647201946,
1784
+ "grad_norm": 2.029624875741936,
1785
+ "learning_rate": 8.220064724919095e-06,
1786
+ "loss": 0.4524,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.024817518248175182,
1791
+ "grad_norm": 1.8862765408033388,
1792
+ "learning_rate": 8.25242718446602e-06,
1793
+ "loss": 0.2173,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.02491484184914842,
1798
+ "grad_norm": 2.575687620331568,
1799
+ "learning_rate": 8.284789644012947e-06,
1800
+ "loss": 0.4599,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.025012165450121655,
1805
+ "grad_norm": 2.373530485379713,
1806
+ "learning_rate": 8.317152103559872e-06,
1807
+ "loss": 0.5326,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.02510948905109489,
1812
+ "grad_norm": 2.4086353319447262,
1813
+ "learning_rate": 8.349514563106797e-06,
1814
+ "loss": 0.6275,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.025206812652068127,
1819
+ "grad_norm": 2.1075725625285697,
1820
+ "learning_rate": 8.381877022653722e-06,
1821
+ "loss": 0.44,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.025304136253041364,
1826
+ "grad_norm": 2.0285700798989614,
1827
+ "learning_rate": 8.414239482200647e-06,
1828
+ "loss": 0.3489,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.0254014598540146,
1833
+ "grad_norm": 2.5592973746241,
1834
+ "learning_rate": 8.446601941747573e-06,
1835
+ "loss": 0.4403,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.025498783454987836,
1840
+ "grad_norm": 2.470930078509074,
1841
+ "learning_rate": 8.4789644012945e-06,
1842
+ "loss": 0.4985,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.02559610705596107,
1847
+ "grad_norm": 2.099638103909556,
1848
+ "learning_rate": 8.511326860841424e-06,
1849
+ "loss": 0.4194,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.025693430656934305,
1854
+ "grad_norm": 1.6030834140551835,
1855
+ "learning_rate": 8.54368932038835e-06,
1856
+ "loss": 0.3382,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.02579075425790754,
1861
+ "grad_norm": 1.8960928547169034,
1862
+ "learning_rate": 8.576051779935276e-06,
1863
+ "loss": 0.2838,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.025888077858880778,
1868
+ "grad_norm": 2.4306930963261966,
1869
+ "learning_rate": 8.608414239482202e-06,
1870
+ "loss": 0.4956,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.025985401459854014,
1875
+ "grad_norm": 2.374430136325354,
1876
+ "learning_rate": 8.640776699029127e-06,
1877
+ "loss": 0.5083,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.02608272506082725,
1882
+ "grad_norm": 2.410095115145934,
1883
+ "learning_rate": 8.673139158576054e-06,
1884
+ "loss": 0.4247,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.026180048661800487,
1889
+ "grad_norm": 2.41271065696519,
1890
+ "learning_rate": 8.705501618122979e-06,
1891
+ "loss": 0.6946,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.026277372262773723,
1896
+ "grad_norm": 1.752688930628829,
1897
+ "learning_rate": 8.737864077669904e-06,
1898
+ "loss": 0.2662,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.02637469586374696,
1903
+ "grad_norm": 1.9842034213162434,
1904
+ "learning_rate": 8.770226537216829e-06,
1905
+ "loss": 0.3611,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.026472019464720196,
1910
+ "grad_norm": 2.4137979998327497,
1911
+ "learning_rate": 8.802588996763754e-06,
1912
+ "loss": 0.501,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.026569343065693432,
1917
+ "grad_norm": 2.929650064864996,
1918
+ "learning_rate": 8.834951456310681e-06,
1919
+ "loss": 0.6153,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.02666666666666667,
1924
+ "grad_norm": 2.281738020025263,
1925
+ "learning_rate": 8.867313915857606e-06,
1926
+ "loss": 0.5395,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.0267639902676399,
1931
+ "grad_norm": 2.1406726692627975,
1932
+ "learning_rate": 8.899676375404531e-06,
1933
+ "loss": 0.4039,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.026861313868613138,
1938
+ "grad_norm": 3.2366954201371523,
1939
+ "learning_rate": 8.932038834951458e-06,
1940
+ "loss": 0.5414,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.026958637469586374,
1945
+ "grad_norm": 2.1900667662872513,
1946
+ "learning_rate": 8.964401294498383e-06,
1947
+ "loss": 0.3815,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.02705596107055961,
1952
+ "grad_norm": 2.5301939091612216,
1953
+ "learning_rate": 8.996763754045308e-06,
1954
+ "loss": 0.8016,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.027153284671532846,
1959
+ "grad_norm": 2.2552758985680907,
1960
+ "learning_rate": 9.029126213592233e-06,
1961
+ "loss": 0.4133,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.027250608272506083,
1966
+ "grad_norm": 2.309545536997134,
1967
+ "learning_rate": 9.06148867313916e-06,
1968
+ "loss": 0.5346,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.02734793187347932,
1973
+ "grad_norm": 2.585578916644781,
1974
+ "learning_rate": 9.093851132686085e-06,
1975
+ "loss": 0.407,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.027445255474452555,
1980
+ "grad_norm": 1.8503464194025006,
1981
+ "learning_rate": 9.12621359223301e-06,
1982
+ "loss": 0.4674,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.02754257907542579,
1987
+ "grad_norm": 2.431490115980846,
1988
+ "learning_rate": 9.158576051779936e-06,
1989
+ "loss": 0.6026,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.027639902676399028,
1994
+ "grad_norm": 1.916233248702735,
1995
+ "learning_rate": 9.19093851132686e-06,
1996
+ "loss": 0.4949,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.027737226277372264,
2001
+ "grad_norm": 2.2160236640245072,
2002
+ "learning_rate": 9.223300970873788e-06,
2003
+ "loss": 0.4765,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.027834549878345497,
2008
+ "grad_norm": 2.0764827118780143,
2009
+ "learning_rate": 9.255663430420713e-06,
2010
+ "loss": 0.472,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.027931873479318733,
2015
+ "grad_norm": 2.638286661284288,
2016
+ "learning_rate": 9.288025889967638e-06,
2017
+ "loss": 0.6312,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.02802919708029197,
2022
+ "grad_norm": 1.940011273577467,
2023
+ "learning_rate": 9.320388349514565e-06,
2024
+ "loss": 0.4555,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.028126520681265206,
2029
+ "grad_norm": 1.8760624736314784,
2030
+ "learning_rate": 9.35275080906149e-06,
2031
+ "loss": 0.3625,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.028223844282238442,
2036
+ "grad_norm": 1.3468692859077058,
2037
+ "learning_rate": 9.385113268608415e-06,
2038
+ "loss": 0.2442,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.02832116788321168,
2043
+ "grad_norm": 2.1497394847504014,
2044
+ "learning_rate": 9.41747572815534e-06,
2045
+ "loss": 0.5227,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.028418491484184915,
2050
+ "grad_norm": 2.1233743171190014,
2051
+ "learning_rate": 9.449838187702267e-06,
2052
+ "loss": 0.6184,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.02851581508515815,
2057
+ "grad_norm": 2.337806183860394,
2058
+ "learning_rate": 9.482200647249192e-06,
2059
+ "loss": 0.5491,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.028613138686131388,
2064
+ "grad_norm": 2.015000594070385,
2065
+ "learning_rate": 9.514563106796117e-06,
2066
+ "loss": 0.5137,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.028710462287104624,
2071
+ "grad_norm": 2.0267324830753766,
2072
+ "learning_rate": 9.546925566343042e-06,
2073
+ "loss": 0.4117,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.02880778588807786,
2078
+ "grad_norm": 1.732639028192012,
2079
+ "learning_rate": 9.579288025889967e-06,
2080
+ "loss": 0.3156,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.028905109489051097,
2085
+ "grad_norm": 2.1204056159243923,
2086
+ "learning_rate": 9.611650485436894e-06,
2087
+ "loss": 0.6056,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.02900243309002433,
2092
+ "grad_norm": 1.7868071753968195,
2093
+ "learning_rate": 9.64401294498382e-06,
2094
+ "loss": 0.3417,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.029099756690997566,
2099
+ "grad_norm": 1.9477439300595292,
2100
+ "learning_rate": 9.676375404530746e-06,
2101
+ "loss": 0.3631,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.029197080291970802,
2106
+ "grad_norm": 1.7688147839655162,
2107
+ "learning_rate": 9.708737864077671e-06,
2108
+ "loss": 0.3605,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.029294403892944038,
2113
+ "grad_norm": 1.9162335597538034,
2114
+ "learning_rate": 9.741100323624596e-06,
2115
+ "loss": 0.2498,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.029391727493917275,
2120
+ "grad_norm": 2.9282579520055756,
2121
+ "learning_rate": 9.773462783171522e-06,
2122
+ "loss": 0.4286,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.02948905109489051,
2127
+ "grad_norm": 1.9744499285549086,
2128
+ "learning_rate": 9.805825242718447e-06,
2129
+ "loss": 0.3391,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.029586374695863747,
2134
+ "grad_norm": 2.2116032868392455,
2135
+ "learning_rate": 9.838187702265373e-06,
2136
+ "loss": 0.3414,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.029683698296836983,
2141
+ "grad_norm": 1.9159144570242486,
2142
+ "learning_rate": 9.870550161812299e-06,
2143
+ "loss": 0.2915,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.02978102189781022,
2148
+ "grad_norm": 2.671718838238437,
2149
+ "learning_rate": 9.902912621359224e-06,
2150
+ "loss": 0.79,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.029878345498783456,
2155
+ "grad_norm": 2.093937424199301,
2156
+ "learning_rate": 9.935275080906149e-06,
2157
+ "loss": 0.576,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.029975669099756692,
2162
+ "grad_norm": 1.895574286512308,
2163
+ "learning_rate": 9.967637540453076e-06,
2164
+ "loss": 0.4223,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.03007299270072993,
2169
+ "grad_norm": 2.142643554578675,
2170
+ "learning_rate": 1e-05,
2171
+ "loss": 0.4719,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.03017031630170316,
2176
+ "grad_norm": 2.2548613483238378,
2177
+ "learning_rate": 9.999999751573464e-06,
2178
+ "loss": 0.5547,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.030267639902676398,
2183
+ "grad_norm": 2.375146158639999,
2184
+ "learning_rate": 9.99999900629388e-06,
2185
+ "loss": 0.3864,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.030364963503649634,
2190
+ "grad_norm": 1.558937895217452,
2191
+ "learning_rate": 9.99999776416132e-06,
2192
+ "loss": 0.3409,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.03046228710462287,
2197
+ "grad_norm": 2.7508940543848115,
2198
+ "learning_rate": 9.99999602517591e-06,
2199
+ "loss": 0.3641,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.030559610705596107,
2204
+ "grad_norm": 2.228096737889712,
2205
+ "learning_rate": 9.99999378933782e-06,
2206
+ "loss": 0.6464,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.030656934306569343,
2211
+ "grad_norm": 1.5612763763472,
2212
+ "learning_rate": 9.999991056647274e-06,
2213
+ "loss": 0.3124,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.03075425790754258,
2218
+ "grad_norm": 2.3203527787434104,
2219
+ "learning_rate": 9.999987827104544e-06,
2220
+ "loss": 0.5893,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.030851581508515816,
2225
+ "grad_norm": 1.8472611567410342,
2226
+ "learning_rate": 9.999984100709951e-06,
2227
+ "loss": 0.3732,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.030948905109489052,
2232
+ "grad_norm": 2.269778108549014,
2233
+ "learning_rate": 9.999979877463866e-06,
2234
+ "loss": 0.5537,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.03104622871046229,
2239
+ "grad_norm": 2.381498581134022,
2240
+ "learning_rate": 9.999975157366705e-06,
2241
+ "loss": 0.7179,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.031143552311435525,
2246
+ "grad_norm": 1.7030655036823346,
2247
+ "learning_rate": 9.99996994041894e-06,
2248
+ "loss": 0.4256,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.031240875912408757,
2253
+ "grad_norm": 1.8361141038730153,
2254
+ "learning_rate": 9.999964226621089e-06,
2255
+ "loss": 0.4648,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.031338199513381994,
2260
+ "grad_norm": 1.7985459229558753,
2261
+ "learning_rate": 9.99995801597372e-06,
2262
+ "loss": 0.3031,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.031435523114355234,
2267
+ "grad_norm": 2.4309020119442915,
2268
+ "learning_rate": 9.99995130847745e-06,
2269
+ "loss": 0.5011,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.031532846715328466,
2274
+ "grad_norm": 2.048514022969095,
2275
+ "learning_rate": 9.999944104132944e-06,
2276
+ "loss": 0.6152,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.031630170316301706,
2281
+ "grad_norm": 1.8892667320795724,
2282
+ "learning_rate": 9.99993640294092e-06,
2283
+ "loss": 0.4738,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.03172749391727494,
2288
+ "grad_norm": 2.081179331819785,
2289
+ "learning_rate": 9.999928204902141e-06,
2290
+ "loss": 0.5192,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.03182481751824817,
2295
+ "grad_norm": 2.410280889073595,
2296
+ "learning_rate": 9.999919510017424e-06,
2297
+ "loss": 0.3314,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.03192214111922141,
2302
+ "grad_norm": 1.663034255724975,
2303
+ "learning_rate": 9.999910318287632e-06,
2304
+ "loss": 0.3342,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.032019464720194644,
2309
+ "grad_norm": 1.7874391345352068,
2310
+ "learning_rate": 9.999900629713679e-06,
2311
+ "loss": 0.3189,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.032116788321167884,
2316
+ "grad_norm": 2.1098429973097805,
2317
+ "learning_rate": 9.999890444296528e-06,
2318
+ "loss": 0.4561,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.03221411192214112,
2323
+ "grad_norm": 2.4678279265353558,
2324
+ "learning_rate": 9.999879762037187e-06,
2325
+ "loss": 0.5831,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.03231143552311436,
2330
+ "grad_norm": 1.6643716587630457,
2331
+ "learning_rate": 9.999868582936726e-06,
2332
+ "loss": 0.4371,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.03240875912408759,
2337
+ "grad_norm": 2.088466639768523,
2338
+ "learning_rate": 9.999856906996246e-06,
2339
+ "loss": 0.3904,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.03250608272506083,
2344
+ "grad_norm": 2.0023651443392256,
2345
+ "learning_rate": 9.999844734216914e-06,
2346
+ "loss": 0.4802,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.03260340632603406,
2351
+ "grad_norm": 2.161282844007076,
2352
+ "learning_rate": 9.99983206459994e-06,
2353
+ "loss": 0.5187,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.0327007299270073,
2358
+ "grad_norm": 2.10212671583593,
2359
+ "learning_rate": 9.999818898146576e-06,
2360
+ "loss": 0.4618,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.032798053527980535,
2365
+ "grad_norm": 2.2142899508809286,
2366
+ "learning_rate": 9.999805234858137e-06,
2367
+ "loss": 0.2387,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.032895377128953775,
2372
+ "grad_norm": 2.1084763484693023,
2373
+ "learning_rate": 9.999791074735981e-06,
2374
+ "loss": 0.5652,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.03299270072992701,
2379
+ "grad_norm": 2.261838498017328,
2380
+ "learning_rate": 9.99977641778151e-06,
2381
+ "loss": 0.7224,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.03309002433090024,
2386
+ "grad_norm": 1.612816030006559,
2387
+ "learning_rate": 9.999761263996184e-06,
2388
+ "loss": 0.377,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.03318734793187348,
2393
+ "grad_norm": 2.1209830295615832,
2394
+ "learning_rate": 9.999745613381507e-06,
2395
+ "loss": 0.614,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.03328467153284671,
2400
+ "grad_norm": 1.7938764015879674,
2401
+ "learning_rate": 9.999729465939036e-06,
2402
+ "loss": 0.3983,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.03338199513381995,
2407
+ "grad_norm": 1.943418875698731,
2408
+ "learning_rate": 9.999712821670375e-06,
2409
+ "loss": 0.4708,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.033479318734793186,
2414
+ "grad_norm": 1.9787546900237571,
2415
+ "learning_rate": 9.99969568057718e-06,
2416
+ "loss": 0.578,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.033576642335766425,
2421
+ "grad_norm": 1.4798263726328331,
2422
+ "learning_rate": 9.99967804266115e-06,
2423
+ "loss": 0.394,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.03367396593673966,
2428
+ "grad_norm": 2.1936298043995484,
2429
+ "learning_rate": 9.99965990792404e-06,
2430
+ "loss": 0.6316,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.0337712895377129,
2435
+ "grad_norm": 2.2799650780195133,
2436
+ "learning_rate": 9.99964127636765e-06,
2437
+ "loss": 0.3985,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.03386861313868613,
2442
+ "grad_norm": 1.8519049219191819,
2443
+ "learning_rate": 9.999622147993837e-06,
2444
+ "loss": 0.3853,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.03396593673965937,
2449
+ "grad_norm": 1.5111895282974241,
2450
+ "learning_rate": 9.999602522804497e-06,
2451
+ "loss": 0.4201,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.0340632603406326,
2456
+ "grad_norm": 1.8605769784283237,
2457
+ "learning_rate": 9.99958240080158e-06,
2458
+ "loss": 0.5225,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.034160583941605836,
2463
+ "grad_norm": 1.6063240538866903,
2464
+ "learning_rate": 9.999561781987087e-06,
2465
+ "loss": 0.3165,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.034257907542579076,
2470
+ "grad_norm": 1.4751976204077173,
2471
+ "learning_rate": 9.999540666363068e-06,
2472
+ "loss": 0.3156,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.03435523114355231,
2477
+ "grad_norm": 2.1029966771511757,
2478
+ "learning_rate": 9.99951905393162e-06,
2479
+ "loss": 0.5336,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.03445255474452555,
2484
+ "grad_norm": 2.1419054642874267,
2485
+ "learning_rate": 9.99949694469489e-06,
2486
+ "loss": 0.5253,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.03454987834549878,
2491
+ "grad_norm": 2.169397271826959,
2492
+ "learning_rate": 9.999474338655075e-06,
2493
+ "loss": 0.5567,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.03464720194647202,
2498
+ "grad_norm": 2.2972412855327797,
2499
+ "learning_rate": 9.999451235814422e-06,
2500
+ "loss": 0.5233,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.034744525547445254,
2505
+ "grad_norm": 1.830377999961128,
2506
+ "learning_rate": 9.999427636175228e-06,
2507
+ "loss": 0.4297,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.034841849148418494,
2512
+ "grad_norm": 2.1217123292302875,
2513
+ "learning_rate": 9.999403539739837e-06,
2514
+ "loss": 0.3605,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.03493917274939173,
2519
+ "grad_norm": 2.001599625802253,
2520
+ "learning_rate": 9.999378946510642e-06,
2521
+ "loss": 0.5237,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.035036496350364967,
2526
+ "grad_norm": 1.6719956399048532,
2527
+ "learning_rate": 9.99935385649009e-06,
2528
+ "loss": 0.424,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.0351338199513382,
2533
+ "grad_norm": 1.5962062682133515,
2534
+ "learning_rate": 9.99932826968067e-06,
2535
+ "loss": 0.4228,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.03523114355231143,
2540
+ "grad_norm": 1.9754274750693919,
2541
+ "learning_rate": 9.999302186084929e-06,
2542
+ "loss": 0.4333,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.03532846715328467,
2547
+ "grad_norm": 1.8248617929879183,
2548
+ "learning_rate": 9.999275605705457e-06,
2549
+ "loss": 0.4985,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 0.035425790754257905,
2554
+ "grad_norm": 2.5923075514224982,
2555
+ "learning_rate": 9.999248528544895e-06,
2556
+ "loss": 0.4829,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 0.035523114355231145,
2561
+ "grad_norm": 1.9900801938638135,
2562
+ "learning_rate": 9.999220954605932e-06,
2563
+ "loss": 0.587,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 0.03562043795620438,
2568
+ "grad_norm": 1.731558772897005,
2569
+ "learning_rate": 9.999192883891314e-06,
2570
+ "loss": 0.3299,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 0.03571776155717762,
2575
+ "grad_norm": 2.339577788711278,
2576
+ "learning_rate": 9.999164316403823e-06,
2577
+ "loss": 0.4845,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 0.03581508515815085,
2582
+ "grad_norm": 1.9784113864985955,
2583
+ "learning_rate": 9.999135252146302e-06,
2584
+ "loss": 0.5776,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 0.03591240875912409,
2589
+ "grad_norm": 1.5555461256937277,
2590
+ "learning_rate": 9.999105691121638e-06,
2591
+ "loss": 0.3563,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 0.03600973236009732,
2596
+ "grad_norm": 1.7905677559908044,
2597
+ "learning_rate": 9.99907563333277e-06,
2598
+ "loss": 0.546,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 0.03610705596107056,
2603
+ "grad_norm": 2.0490894714600287,
2604
+ "learning_rate": 9.999045078782684e-06,
2605
+ "loss": 0.6836,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 0.036204379562043795,
2610
+ "grad_norm": 2.216601446334751,
2611
+ "learning_rate": 9.999014027474413e-06,
2612
+ "loss": 0.5237,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 0.036301703163017035,
2617
+ "grad_norm": 1.5937926342815392,
2618
+ "learning_rate": 9.998982479411047e-06,
2619
+ "loss": 0.3539,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 0.03639902676399027,
2624
+ "grad_norm": 2.3941848280266864,
2625
+ "learning_rate": 9.99895043459572e-06,
2626
+ "loss": 0.6249,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 0.0364963503649635,
2631
+ "grad_norm": 2.072859669066288,
2632
+ "learning_rate": 9.998917893031615e-06,
2633
+ "loss": 0.5415,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 0.03659367396593674,
2638
+ "grad_norm": 1.670908711065728,
2639
+ "learning_rate": 9.998884854721968e-06,
2640
+ "loss": 0.3034,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 0.03669099756690997,
2645
+ "grad_norm": 1.9880303784818283,
2646
+ "learning_rate": 9.998851319670057e-06,
2647
+ "loss": 0.5025,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 0.03678832116788321,
2652
+ "grad_norm": 1.3517666701087396,
2653
+ "learning_rate": 9.99881728787922e-06,
2654
+ "loss": 0.2775,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 0.036885644768856446,
2659
+ "grad_norm": 1.8952553535268069,
2660
+ "learning_rate": 9.998782759352839e-06,
2661
+ "loss": 0.5306,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 0.036982968369829686,
2666
+ "grad_norm": 1.8730537486024816,
2667
+ "learning_rate": 9.998747734094338e-06,
2668
+ "loss": 0.386,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 0.03708029197080292,
2673
+ "grad_norm": 2.058996056292158,
2674
+ "learning_rate": 9.998712212107205e-06,
2675
+ "loss": 0.5641,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 0.03717761557177616,
2680
+ "grad_norm": 1.9837834234853275,
2681
+ "learning_rate": 9.998676193394966e-06,
2682
+ "loss": 0.2628,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 0.03727493917274939,
2687
+ "grad_norm": 2.189700953999047,
2688
+ "learning_rate": 9.998639677961203e-06,
2689
+ "loss": 0.6024,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 0.03737226277372263,
2694
+ "grad_norm": 2.060696593716547,
2695
+ "learning_rate": 9.99860266580954e-06,
2696
+ "loss": 0.5377,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 0.037469586374695864,
2701
+ "grad_norm": 2.0831966609629227,
2702
+ "learning_rate": 9.99856515694366e-06,
2703
+ "loss": 0.5063,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 0.0375669099756691,
2708
+ "grad_norm": 2.2950496556846227,
2709
+ "learning_rate": 9.998527151367288e-06,
2710
+ "loss": 0.6484,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 0.037664233576642336,
2715
+ "grad_norm": 2.2597922123273873,
2716
+ "learning_rate": 9.9984886490842e-06,
2717
+ "loss": 0.6617,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 0.03776155717761557,
2722
+ "grad_norm": 2.071575887731456,
2723
+ "learning_rate": 9.99844965009822e-06,
2724
+ "loss": 0.5405,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 0.03785888077858881,
2729
+ "grad_norm": 2.004249587957457,
2730
+ "learning_rate": 9.99841015441323e-06,
2731
+ "loss": 0.4306,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 0.03795620437956204,
2736
+ "grad_norm": 1.9297023880727862,
2737
+ "learning_rate": 9.99837016203315e-06,
2738
+ "loss": 0.4083,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 0.03805352798053528,
2743
+ "grad_norm": 2.001337081282171,
2744
+ "learning_rate": 9.998329672961952e-06,
2745
+ "loss": 0.4999,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 0.038150851581508514,
2750
+ "grad_norm": 1.7630230797021285,
2751
+ "learning_rate": 9.998288687203665e-06,
2752
+ "loss": 0.4267,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 0.038248175182481754,
2757
+ "grad_norm": 1.4413546421147376,
2758
+ "learning_rate": 9.998247204762358e-06,
2759
+ "loss": 0.3028,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 0.03834549878345499,
2764
+ "grad_norm": 2.032450629241147,
2765
+ "learning_rate": 9.998205225642154e-06,
2766
+ "loss": 0.4216,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 0.03844282238442823,
2771
+ "grad_norm": 1.8288270303352272,
2772
+ "learning_rate": 9.998162749847224e-06,
2773
+ "loss": 0.451,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 0.03854014598540146,
2778
+ "grad_norm": 1.5869427581540143,
2779
+ "learning_rate": 9.998119777381791e-06,
2780
+ "loss": 0.4896,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 0.03863746958637469,
2785
+ "grad_norm": 1.9312614168983935,
2786
+ "learning_rate": 9.998076308250122e-06,
2787
+ "loss": 0.351,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 0.03873479318734793,
2792
+ "grad_norm": 2.182734939846557,
2793
+ "learning_rate": 9.99803234245654e-06,
2794
+ "loss": 0.4456,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 0.038832116788321165,
2799
+ "grad_norm": 1.6075130172605856,
2800
+ "learning_rate": 9.997987880005412e-06,
2801
+ "loss": 0.3333,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 0.038929440389294405,
2806
+ "grad_norm": 2.0206579020801048,
2807
+ "learning_rate": 9.997942920901154e-06,
2808
+ "loss": 0.4662,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 0.03902676399026764,
2813
+ "grad_norm": 2.0019154912621246,
2814
+ "learning_rate": 9.997897465148236e-06,
2815
+ "loss": 0.588,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 0.03912408759124088,
2820
+ "grad_norm": 1.9556688755730123,
2821
+ "learning_rate": 9.997851512751178e-06,
2822
+ "loss": 0.5364,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 0.03922141119221411,
2827
+ "grad_norm": 2.1735940620422687,
2828
+ "learning_rate": 9.997805063714541e-06,
2829
+ "loss": 0.4155,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 0.03931873479318735,
2834
+ "grad_norm": 1.893104755523836,
2835
+ "learning_rate": 9.997758118042945e-06,
2836
+ "loss": 0.2835,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 0.03941605839416058,
2841
+ "grad_norm": 1.892857392200546,
2842
+ "learning_rate": 9.99771067574105e-06,
2843
+ "loss": 0.317,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 0.03951338199513382,
2848
+ "grad_norm": 2.194365925195629,
2849
+ "learning_rate": 9.997662736813575e-06,
2850
+ "loss": 0.5972,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 0.039610705596107056,
2855
+ "grad_norm": 2.3359516870584547,
2856
+ "learning_rate": 9.997614301265281e-06,
2857
+ "loss": 0.3505,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 0.039708029197080295,
2862
+ "grad_norm": 1.8041349283411827,
2863
+ "learning_rate": 9.997565369100983e-06,
2864
+ "loss": 0.4003,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 0.03980535279805353,
2869
+ "grad_norm": 2.2199870140108273,
2870
+ "learning_rate": 9.997515940325542e-06,
2871
+ "loss": 0.4428,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 0.03990267639902676,
2876
+ "grad_norm": 2.193796849633566,
2877
+ "learning_rate": 9.997466014943871e-06,
2878
+ "loss": 0.3906,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 0.04,
2883
+ "grad_norm": 2.7309920828616168,
2884
+ "learning_rate": 9.99741559296093e-06,
2885
+ "loss": 0.6283,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 0.040097323600973234,
2890
+ "grad_norm": 2.220745639846989,
2891
+ "learning_rate": 9.99736467438173e-06,
2892
+ "loss": 0.4568,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 0.04019464720194647,
2897
+ "grad_norm": 1.905067765139487,
2898
+ "learning_rate": 9.99731325921133e-06,
2899
+ "loss": 0.3198,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 0.040291970802919706,
2904
+ "grad_norm": 2.0461180940034116,
2905
+ "learning_rate": 9.997261347454841e-06,
2906
+ "loss": 0.3783,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 0.040389294403892946,
2911
+ "grad_norm": 1.9732614929529544,
2912
+ "learning_rate": 9.99720893911742e-06,
2913
+ "loss": 0.5211,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 0.04048661800486618,
2918
+ "grad_norm": 2.341156401873798,
2919
+ "learning_rate": 9.997156034204276e-06,
2920
+ "loss": 0.5094,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 0.04058394160583942,
2925
+ "grad_norm": 2.2588135503158138,
2926
+ "learning_rate": 9.997102632720664e-06,
2927
+ "loss": 0.591,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 0.04068126520681265,
2932
+ "grad_norm": 2.187795564574772,
2933
+ "learning_rate": 9.997048734671893e-06,
2934
+ "loss": 0.3811,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 0.04077858880778589,
2939
+ "grad_norm": 2.2570398189900938,
2940
+ "learning_rate": 9.996994340063314e-06,
2941
+ "loss": 0.4494,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 0.040875912408759124,
2946
+ "grad_norm": 2.3267878846596597,
2947
+ "learning_rate": 9.996939448900341e-06,
2948
+ "loss": 0.5254,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 0.04097323600973236,
2953
+ "grad_norm": 1.9149387144635641,
2954
+ "learning_rate": 9.99688406118842e-06,
2955
+ "loss": 0.4281,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 0.0410705596107056,
2960
+ "grad_norm": 2.4052095021382285,
2961
+ "learning_rate": 9.996828176933062e-06,
2962
+ "loss": 0.61,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 0.04116788321167883,
2967
+ "grad_norm": 2.8744864627123237,
2968
+ "learning_rate": 9.996771796139814e-06,
2969
+ "loss": 0.4708,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 0.04126520681265207,
2974
+ "grad_norm": 2.0334953222734513,
2975
+ "learning_rate": 9.996714918814284e-06,
2976
+ "loss": 0.2697,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 0.0413625304136253,
2981
+ "grad_norm": 2.1314093477075486,
2982
+ "learning_rate": 9.996657544962119e-06,
2983
+ "loss": 0.3026,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 0.04145985401459854,
2988
+ "grad_norm": 1.7241742631767316,
2989
+ "learning_rate": 9.996599674589022e-06,
2990
+ "loss": 0.3624,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 0.041557177615571775,
2995
+ "grad_norm": 2.417754377928955,
2996
+ "learning_rate": 9.996541307700746e-06,
2997
+ "loss": 0.6682,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 0.041654501216545015,
3002
+ "grad_norm": 2.2126055245100256,
3003
+ "learning_rate": 9.99648244430309e-06,
3004
+ "loss": 0.3705,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 0.04175182481751825,
3009
+ "grad_norm": 1.8224510106748588,
3010
+ "learning_rate": 9.996423084401901e-06,
3011
+ "loss": 0.4318,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 0.04184914841849149,
3016
+ "grad_norm": 1.6786428352287364,
3017
+ "learning_rate": 9.996363228003079e-06,
3018
+ "loss": 0.4662,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 0.04194647201946472,
3023
+ "grad_norm": 1.9342922605897592,
3024
+ "learning_rate": 9.99630287511257e-06,
3025
+ "loss": 0.4874,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 0.04204379562043795,
3030
+ "grad_norm": 1.9444011100602645,
3031
+ "learning_rate": 9.996242025736377e-06,
3032
+ "loss": 0.3711,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 0.04214111922141119,
3037
+ "grad_norm": 3.114184163688958,
3038
+ "learning_rate": 9.99618067988054e-06,
3039
+ "loss": 0.5342,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 0.042238442822384425,
3044
+ "grad_norm": 1.993932460938173,
3045
+ "learning_rate": 9.99611883755116e-06,
3046
+ "loss": 0.465,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 0.042335766423357665,
3051
+ "grad_norm": 1.5062408953506277,
3052
+ "learning_rate": 9.99605649875438e-06,
3053
+ "loss": 0.3862,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 0.0424330900243309,
3058
+ "grad_norm": 2.5287447175721733,
3059
+ "learning_rate": 9.995993663496394e-06,
3060
+ "loss": 0.5638,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 0.04253041362530414,
3065
+ "grad_norm": 1.7215400937807486,
3066
+ "learning_rate": 9.995930331783448e-06,
3067
+ "loss": 0.3507,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 0.04262773722627737,
3072
+ "grad_norm": 1.5105936757865817,
3073
+ "learning_rate": 9.995866503621834e-06,
3074
+ "loss": 0.4086,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 0.04272506082725061,
3079
+ "grad_norm": 1.828501540310894,
3080
+ "learning_rate": 9.995802179017893e-06,
3081
+ "loss": 0.3477,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 0.04282238442822384,
3086
+ "grad_norm": 1.6658361590948114,
3087
+ "learning_rate": 9.995737357978022e-06,
3088
+ "loss": 0.4006,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 0.04291970802919708,
3093
+ "grad_norm": 1.6434395036324305,
3094
+ "learning_rate": 9.995672040508656e-06,
3095
+ "loss": 0.4349,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 0.043017031630170316,
3100
+ "grad_norm": 1.9913424027071125,
3101
+ "learning_rate": 9.99560622661629e-06,
3102
+ "loss": 0.3415,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 0.043114355231143556,
3107
+ "grad_norm": 1.6487474195389296,
3108
+ "learning_rate": 9.995539916307463e-06,
3109
+ "loss": 0.4804,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 0.04321167883211679,
3114
+ "grad_norm": 1.4861266391850032,
3115
+ "learning_rate": 9.995473109588764e-06,
3116
+ "loss": 0.411,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 0.04330900243309002,
3121
+ "grad_norm": 1.4390762643228305,
3122
+ "learning_rate": 9.995405806466831e-06,
3123
+ "loss": 0.3806,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 0.04340632603406326,
3128
+ "grad_norm": 1.7775332171720517,
3129
+ "learning_rate": 9.995338006948353e-06,
3130
+ "loss": 0.3332,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 0.043503649635036494,
3135
+ "grad_norm": 1.7312883283317864,
3136
+ "learning_rate": 9.995269711040067e-06,
3137
+ "loss": 0.2736,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 0.043600973236009734,
3142
+ "grad_norm": 1.7973901424872405,
3143
+ "learning_rate": 9.995200918748759e-06,
3144
+ "loss": 0.5597,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 0.04369829683698297,
3149
+ "grad_norm": 2.0409413301370334,
3150
+ "learning_rate": 9.995131630081265e-06,
3151
+ "loss": 0.6045,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 0.043795620437956206,
3156
+ "grad_norm": 3.2708903670147347,
3157
+ "learning_rate": 9.995061845044473e-06,
3158
+ "loss": 0.6245,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 0.04389294403892944,
3163
+ "grad_norm": 1.744466889932859,
3164
+ "learning_rate": 9.994991563645314e-06,
3165
+ "loss": 0.4129,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 0.04399026763990268,
3170
+ "grad_norm": 1.8775864246251477,
3171
+ "learning_rate": 9.994920785890771e-06,
3172
+ "loss": 0.414,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 0.04408759124087591,
3177
+ "grad_norm": 1.3868286948878126,
3178
+ "learning_rate": 9.994849511787881e-06,
3179
+ "loss": 0.3164,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 0.04418491484184915,
3184
+ "grad_norm": 1.6888257223301795,
3185
+ "learning_rate": 9.994777741343727e-06,
3186
+ "loss": 0.3241,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 0.044282238442822384,
3191
+ "grad_norm": 1.5029594314338663,
3192
+ "learning_rate": 9.994705474565436e-06,
3193
+ "loss": 0.4148,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 0.04437956204379562,
3198
+ "grad_norm": 1.7159996915963702,
3199
+ "learning_rate": 9.994632711460193e-06,
3200
+ "loss": 0.3387,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 0.04447688564476886,
3205
+ "grad_norm": 1.7717997513120352,
3206
+ "learning_rate": 9.994559452035228e-06,
3207
+ "loss": 0.4547,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 0.04457420924574209,
3212
+ "grad_norm": 1.887765282184233,
3213
+ "learning_rate": 9.99448569629782e-06,
3214
+ "loss": 0.5919,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 0.04467153284671533,
3219
+ "grad_norm": 2.0151049512314585,
3220
+ "learning_rate": 9.994411444255298e-06,
3221
+ "loss": 0.4556,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 0.04476885644768856,
3226
+ "grad_norm": 1.5706463359289826,
3227
+ "learning_rate": 9.994336695915041e-06,
3228
+ "loss": 0.3443,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 0.0448661800486618,
3233
+ "grad_norm": 1.9067884841542395,
3234
+ "learning_rate": 9.994261451284477e-06,
3235
+ "loss": 0.5862,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 0.044963503649635035,
3240
+ "grad_norm": 1.7346846845298518,
3241
+ "learning_rate": 9.994185710371083e-06,
3242
+ "loss": 0.3588,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 0.045060827250608275,
3247
+ "grad_norm": 1.5593715629463312,
3248
+ "learning_rate": 9.994109473182385e-06,
3249
+ "loss": 0.2891,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 0.04515815085158151,
3254
+ "grad_norm": 2.326736753149576,
3255
+ "learning_rate": 9.994032739725959e-06,
3256
+ "loss": 0.6517,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 0.04525547445255475,
3261
+ "grad_norm": 2.2142852132770305,
3262
+ "learning_rate": 9.99395551000943e-06,
3263
+ "loss": 0.3571,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 0.04535279805352798,
3268
+ "grad_norm": 1.7351954813390544,
3269
+ "learning_rate": 9.993877784040474e-06,
3270
+ "loss": 0.3849,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 0.04545012165450121,
3275
+ "grad_norm": 1.3962336815381617,
3276
+ "learning_rate": 9.993799561826811e-06,
3277
+ "loss": 0.311,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 0.04554744525547445,
3282
+ "grad_norm": 1.878958465421645,
3283
+ "learning_rate": 9.993720843376216e-06,
3284
+ "loss": 0.5602,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 0.045644768856447686,
3289
+ "grad_norm": 1.519160992933857,
3290
+ "learning_rate": 9.993641628696513e-06,
3291
+ "loss": 0.2379,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 0.045742092457420926,
3296
+ "grad_norm": 2.5345930464298885,
3297
+ "learning_rate": 9.99356191779557e-06,
3298
+ "loss": 0.4239,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 0.04583941605839416,
3303
+ "grad_norm": 1.3153911718041251,
3304
+ "learning_rate": 9.993481710681314e-06,
3305
+ "loss": 0.3454,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 0.0459367396593674,
3310
+ "grad_norm": 2.16208125563947,
3311
+ "learning_rate": 9.993401007361707e-06,
3312
+ "loss": 0.5386,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 0.04603406326034063,
3317
+ "grad_norm": 1.8150842593472827,
3318
+ "learning_rate": 9.993319807844775e-06,
3319
+ "loss": 0.3077,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 0.04613138686131387,
3324
+ "grad_norm": 1.6656864462678063,
3325
+ "learning_rate": 9.993238112138584e-06,
3326
+ "loss": 0.4927,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 0.046228710462287104,
3331
+ "grad_norm": 1.3429917702468868,
3332
+ "learning_rate": 9.993155920251252e-06,
3333
+ "loss": 0.2433,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 0.04632603406326034,
3338
+ "grad_norm": 1.3651155739367906,
3339
+ "learning_rate": 9.993073232190949e-06,
3340
+ "loss": 0.2947,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 0.046423357664233576,
3345
+ "grad_norm": 1.7815516701613203,
3346
+ "learning_rate": 9.992990047965887e-06,
3347
+ "loss": 0.5372,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 0.046520681265206816,
3352
+ "grad_norm": 1.846696342179327,
3353
+ "learning_rate": 9.992906367584337e-06,
3354
+ "loss": 0.5127,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 0.04661800486618005,
3359
+ "grad_norm": 1.7511253825578088,
3360
+ "learning_rate": 9.992822191054612e-06,
3361
+ "loss": 0.4074,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 0.04671532846715328,
3366
+ "grad_norm": 1.8105635986872588,
3367
+ "learning_rate": 9.992737518385076e-06,
3368
+ "loss": 0.4998,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 0.04681265206812652,
3373
+ "grad_norm": 2.2743597617900746,
3374
+ "learning_rate": 9.992652349584147e-06,
3375
+ "loss": 0.6249,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 0.046909975669099754,
3380
+ "grad_norm": 1.93948496382319,
3381
+ "learning_rate": 9.992566684660282e-06,
3382
+ "loss": 0.5411,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 0.047007299270072994,
3387
+ "grad_norm": 1.4073760716303516,
3388
+ "learning_rate": 9.992480523621999e-06,
3389
+ "loss": 0.3506,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 0.04710462287104623,
3394
+ "grad_norm": 1.388293079160528,
3395
+ "learning_rate": 9.992393866477856e-06,
3396
+ "loss": 0.3304,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 0.04720194647201947,
3401
+ "grad_norm": 2.082643572745618,
3402
+ "learning_rate": 9.992306713236467e-06,
3403
+ "loss": 0.5653,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 0.0472992700729927,
3408
+ "grad_norm": 1.7104664332606834,
3409
+ "learning_rate": 9.992219063906492e-06,
3410
+ "loss": 0.3317,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 0.04739659367396594,
3415
+ "grad_norm": 1.7575848919482624,
3416
+ "learning_rate": 9.992130918496638e-06,
3417
+ "loss": 0.4109,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 0.04749391727493917,
3422
+ "grad_norm": 1.7351379091271637,
3423
+ "learning_rate": 9.992042277015668e-06,
3424
+ "loss": 0.5065,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 0.04759124087591241,
3429
+ "grad_norm": 1.4444570948381004,
3430
+ "learning_rate": 9.991953139472387e-06,
3431
+ "loss": 0.4023,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 0.047688564476885645,
3436
+ "grad_norm": 1.4697709289140384,
3437
+ "learning_rate": 9.991863505875656e-06,
3438
+ "loss": 0.3364,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 0.04778588807785888,
3443
+ "grad_norm": 1.9428205960506804,
3444
+ "learning_rate": 9.99177337623438e-06,
3445
+ "loss": 0.4303,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 0.04788321167883212,
3450
+ "grad_norm": 1.931152158561148,
3451
+ "learning_rate": 9.991682750557516e-06,
3452
+ "loss": 0.2857,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 0.04798053527980535,
3457
+ "grad_norm": 1.9301394655308035,
3458
+ "learning_rate": 9.991591628854067e-06,
3459
+ "loss": 0.5998,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 0.04807785888077859,
3464
+ "grad_norm": 1.7788293016868693,
3465
+ "learning_rate": 9.99150001113309e-06,
3466
+ "loss": 0.4595,
3467
+ "step": 494
3468
+ },
3469
+ {
3470
+ "epoch": 0.04817518248175182,
3471
+ "grad_norm": 2.0641225732440134,
3472
+ "learning_rate": 9.99140789740369e-06,
3473
+ "loss": 0.3848,
3474
+ "step": 495
3475
+ },
3476
+ {
3477
+ "epoch": 0.04827250608272506,
3478
+ "grad_norm": 2.2832955373527044,
3479
+ "learning_rate": 9.99131528767502e-06,
3480
+ "loss": 0.6396,
3481
+ "step": 496
3482
+ },
3483
+ {
3484
+ "epoch": 0.048369829683698295,
3485
+ "grad_norm": 1.6658790952812916,
3486
+ "learning_rate": 9.99122218195628e-06,
3487
+ "loss": 0.5429,
3488
+ "step": 497
3489
+ },
3490
+ {
3491
+ "epoch": 0.048467153284671535,
3492
+ "grad_norm": 1.6568038302360257,
3493
+ "learning_rate": 9.991128580256725e-06,
3494
+ "loss": 0.4532,
3495
+ "step": 498
3496
+ },
3497
+ {
3498
+ "epoch": 0.04856447688564477,
3499
+ "grad_norm": 1.8451659374514144,
3500
+ "learning_rate": 9.991034482585656e-06,
3501
+ "loss": 0.5845,
3502
+ "step": 499
3503
+ },
3504
+ {
3505
+ "epoch": 0.04866180048661801,
3506
+ "grad_norm": 1.9103948838029656,
3507
+ "learning_rate": 9.99093988895242e-06,
3508
+ "loss": 0.5508,
3509
+ "step": 500
3510
+ },
3511
+ {
3512
+ "epoch": 0.04875912408759124,
3513
+ "grad_norm": 1.9691733858712537,
3514
+ "learning_rate": 9.990844799366422e-06,
3515
+ "loss": 0.6374,
3516
+ "step": 501
3517
+ },
3518
+ {
3519
+ "epoch": 0.048856447688564474,
3520
+ "grad_norm": 2.1278472226161846,
3521
+ "learning_rate": 9.990749213837108e-06,
3522
+ "loss": 0.572,
3523
+ "step": 502
3524
+ },
3525
+ {
3526
+ "epoch": 0.04895377128953771,
3527
+ "grad_norm": 1.9704028865885994,
3528
+ "learning_rate": 9.990653132373977e-06,
3529
+ "loss": 0.6282,
3530
+ "step": 503
3531
+ },
3532
+ {
3533
+ "epoch": 0.049051094890510946,
3534
+ "grad_norm": 1.8965741341561362,
3535
+ "learning_rate": 9.990556554986577e-06,
3536
+ "loss": 0.5749,
3537
+ "step": 504
3538
+ },
3539
+ {
3540
+ "epoch": 0.049148418491484186,
3541
+ "grad_norm": 1.5425018763105707,
3542
+ "learning_rate": 9.990459481684504e-06,
3543
+ "loss": 0.4236,
3544
+ "step": 505
3545
+ },
3546
+ {
3547
+ "epoch": 0.04924574209245742,
3548
+ "grad_norm": 1.736669998068125,
3549
+ "learning_rate": 9.990361912477405e-06,
3550
+ "loss": 0.4275,
3551
+ "step": 506
3552
+ },
3553
+ {
3554
+ "epoch": 0.04934306569343066,
3555
+ "grad_norm": 2.049335776858506,
3556
+ "learning_rate": 9.990263847374976e-06,
3557
+ "loss": 0.6897,
3558
+ "step": 507
3559
+ },
3560
+ {
3561
+ "epoch": 0.04944038929440389,
3562
+ "grad_norm": 1.8544975871268152,
3563
+ "learning_rate": 9.990165286386961e-06,
3564
+ "loss": 0.4811,
3565
+ "step": 508
3566
+ },
3567
+ {
3568
+ "epoch": 0.04953771289537713,
3569
+ "grad_norm": 1.5709178763522822,
3570
+ "learning_rate": 9.990066229523155e-06,
3571
+ "loss": 0.4585,
3572
+ "step": 509
3573
+ },
3574
+ {
3575
+ "epoch": 0.049635036496350364,
3576
+ "grad_norm": 2.1410068811754153,
3577
+ "learning_rate": 9.989966676793399e-06,
3578
+ "loss": 0.4773,
3579
+ "step": 510
3580
+ },
3581
+ {
3582
+ "epoch": 0.049732360097323604,
3583
+ "grad_norm": 1.760724042734433,
3584
+ "learning_rate": 9.989866628207589e-06,
3585
+ "loss": 0.3144,
3586
+ "step": 511
3587
+ },
3588
+ {
3589
+ "epoch": 0.04982968369829684,
3590
+ "grad_norm": 1.8521560168370175,
3591
+ "learning_rate": 9.989766083775662e-06,
3592
+ "loss": 0.4656,
3593
+ "step": 512
3594
+ },
3595
+ {
3596
+ "epoch": 0.049927007299270076,
3597
+ "grad_norm": 1.544987615640627,
3598
+ "learning_rate": 9.989665043507616e-06,
3599
+ "loss": 0.4089,
3600
+ "step": 513
3601
+ },
3602
+ {
3603
+ "epoch": 0.05002433090024331,
3604
+ "grad_norm": 1.9122960249889975,
3605
+ "learning_rate": 9.989563507413487e-06,
3606
+ "loss": 0.4535,
3607
+ "step": 514
3608
+ },
3609
+ {
3610
+ "epoch": 0.05012165450121654,
3611
+ "grad_norm": 1.5187134098621655,
3612
+ "learning_rate": 9.989461475503363e-06,
3613
+ "loss": 0.31,
3614
+ "step": 515
3615
+ }
3616
+ ],
3617
+ "logging_steps": 1.0,
3618
+ "max_steps": 10275,
3619
+ "num_input_tokens_seen": 0,
3620
+ "num_train_epochs": 1,
3621
+ "save_steps": 515,
3622
+ "total_flos": 65890827296768.0,
3623
+ "train_batch_size": 2,
3624
+ "trial_name": null,
3625
+ "trial_params": null
3626
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f784165d5f5e0207135e3f069c12102dffb679e411fe92606397a36fd29dc9
3
+ size 8056
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
zero_to_fp32.py ADDED
@@ -0,0 +1,587 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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):
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
+ elif zero_stage == 3:
216
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
217
+
218
+
219
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
220
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
221
+ return
222
+
223
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
224
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
225
+
226
+ if debug:
227
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
228
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
229
+
230
+ wanted_params = len(frozen_param_shapes)
231
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
232
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
233
+ print(f'Frozen params: Have {avail_numel} numels to process.')
234
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
235
+
236
+ total_params = 0
237
+ total_numel = 0
238
+ for name, shape in frozen_param_shapes.items():
239
+ total_params += 1
240
+ unpartitioned_numel = shape.numel()
241
+ total_numel += unpartitioned_numel
242
+
243
+ state_dict[name] = frozen_param_fragments[name]
244
+
245
+ if debug:
246
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
247
+
248
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
249
+
250
+
251
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
252
+ param_shapes = zero_model_states[0].param_shapes
253
+
254
+ # Reconstruction protocol:
255
+ #
256
+ # XXX: document this
257
+
258
+ if debug:
259
+ for i in range(world_size):
260
+ for j in range(len(fp32_flat_groups[0])):
261
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
262
+
263
+ # XXX: memory usage doubles here (zero2)
264
+ num_param_groups = len(fp32_flat_groups[0])
265
+ merged_single_partition_of_fp32_groups = []
266
+ for i in range(num_param_groups):
267
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
268
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
269
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
270
+ avail_numel = sum(
271
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
272
+
273
+ if debug:
274
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
275
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
276
+ # not asserting if there is a mismatch due to possible padding
277
+ print(f"Have {avail_numel} numels to process.")
278
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
279
+
280
+ # params
281
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
282
+ # out-of-core computing solution
283
+ total_numel = 0
284
+ total_params = 0
285
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
286
+ offset = 0
287
+ avail_numel = full_single_fp32_vector.numel()
288
+ for name, shape in shapes.items():
289
+
290
+ unpartitioned_numel = shape.numel()
291
+ total_numel += unpartitioned_numel
292
+ total_params += 1
293
+
294
+ if debug:
295
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
296
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
297
+ offset += unpartitioned_numel
298
+
299
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
300
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
301
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
302
+ # live optimizer object, so we are checking that the numbers are within the right range
303
+ align_to = 2 * world_size
304
+
305
+ def zero2_align(x):
306
+ return align_to * math.ceil(x / align_to)
307
+
308
+ if debug:
309
+ print(f"original offset={offset}, avail_numel={avail_numel}")
310
+
311
+ offset = zero2_align(offset)
312
+ avail_numel = zero2_align(avail_numel)
313
+
314
+ if debug:
315
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
316
+
317
+ # Sanity check
318
+ if offset != avail_numel:
319
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
320
+
321
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
322
+
323
+
324
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
325
+ state_dict = OrderedDict()
326
+
327
+ # buffers
328
+ buffers = zero_model_states[0].buffers
329
+ state_dict.update(buffers)
330
+ if debug:
331
+ print(f"added {len(buffers)} buffers")
332
+
333
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
334
+
335
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
336
+
337
+ # recover shared parameters
338
+ for pair in zero_model_states[0].shared_params:
339
+ if pair[1] in state_dict:
340
+ state_dict[pair[0]] = state_dict[pair[1]]
341
+
342
+ return state_dict
343
+
344
+
345
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
346
+ remainder = unpartitioned_numel % world_size
347
+ padding_numel = (world_size - remainder) if remainder else 0
348
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
349
+ return partitioned_numel, padding_numel
350
+
351
+
352
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
353
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
354
+ return
355
+
356
+ if debug:
357
+ for i in range(world_size):
358
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
359
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
360
+
361
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
362
+ wanted_params = len(frozen_param_shapes)
363
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
364
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
365
+ print(f'Frozen params: Have {avail_numel} numels to process.')
366
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
367
+
368
+ total_params = 0
369
+ total_numel = 0
370
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
371
+ total_params += 1
372
+ unpartitioned_numel = shape.numel()
373
+ total_numel += unpartitioned_numel
374
+
375
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
376
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
377
+
378
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
379
+
380
+ if debug:
381
+ print(
382
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
383
+ )
384
+
385
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
386
+
387
+
388
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
389
+ param_shapes = zero_model_states[0].param_shapes
390
+ avail_numel = fp32_flat_groups[0].numel() * world_size
391
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
392
+ # param, re-consolidating each param, while dealing with padding if any
393
+
394
+ # merge list of dicts, preserving order
395
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
396
+
397
+ if debug:
398
+ for i in range(world_size):
399
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
400
+
401
+ wanted_params = len(param_shapes)
402
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
403
+ # not asserting if there is a mismatch due to possible padding
404
+ avail_numel = fp32_flat_groups[0].numel() * world_size
405
+ print(f"Trainable params: Have {avail_numel} numels to process.")
406
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
407
+
408
+ # params
409
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
410
+ # out-of-core computing solution
411
+ offset = 0
412
+ total_numel = 0
413
+ total_params = 0
414
+ for name, shape in param_shapes.items():
415
+
416
+ unpartitioned_numel = shape.numel()
417
+ total_numel += unpartitioned_numel
418
+ total_params += 1
419
+
420
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
421
+
422
+ if debug:
423
+ print(
424
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
425
+ )
426
+
427
+ # XXX: memory usage doubles here
428
+ state_dict[name] = torch.cat(
429
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
430
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
431
+ offset += partitioned_numel
432
+
433
+ offset *= world_size
434
+
435
+ # Sanity check
436
+ if offset != avail_numel:
437
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
438
+
439
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
440
+
441
+
442
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
443
+ state_dict = OrderedDict()
444
+
445
+ # buffers
446
+ buffers = zero_model_states[0].buffers
447
+ state_dict.update(buffers)
448
+ if debug:
449
+ print(f"added {len(buffers)} buffers")
450
+
451
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
452
+
453
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
454
+
455
+ # recover shared parameters
456
+ for pair in zero_model_states[0].shared_params:
457
+ if pair[1] in state_dict:
458
+ state_dict[pair[0]] = state_dict[pair[1]]
459
+
460
+ return state_dict
461
+
462
+
463
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
464
+ """
465
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
466
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
467
+ via a model hub.
468
+
469
+ Args:
470
+ - ``checkpoint_dir``: path to the desired checkpoint folder
471
+ - ``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``
472
+
473
+ Returns:
474
+ - pytorch ``state_dict``
475
+
476
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
477
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
478
+ the checkpoint.
479
+
480
+ A typical usage might be ::
481
+
482
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
483
+ # do the training and checkpoint saving
484
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
485
+ model = model.cpu() # move to cpu
486
+ model.load_state_dict(state_dict)
487
+ # submit to model hub or save the model to share with others
488
+
489
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
490
+ application. i.e. you will need to re-initialize the deepspeed engine, since
491
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
492
+
493
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
494
+
495
+ """
496
+ if tag is None:
497
+ latest_path = os.path.join(checkpoint_dir, 'latest')
498
+ if os.path.isfile(latest_path):
499
+ with open(latest_path, 'r') as fd:
500
+ tag = fd.read().strip()
501
+ else:
502
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
503
+
504
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
505
+
506
+ if not os.path.isdir(ds_checkpoint_dir):
507
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
508
+
509
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
510
+
511
+
512
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
513
+ """
514
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
515
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
516
+
517
+ Args:
518
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
519
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
520
+ - ``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``
521
+ """
522
+
523
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
524
+ print(f"Saving fp32 state dict to {output_file}")
525
+ torch.save(state_dict, output_file)
526
+
527
+
528
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
529
+ """
530
+ 1. Put the provided model to cpu
531
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
532
+ 3. Load it into the provided model
533
+
534
+ Args:
535
+ - ``model``: the model object to update
536
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
537
+ - ``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``
538
+
539
+ Returns:
540
+ - ``model`: modified model
541
+
542
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
543
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
544
+ conveniently placed for you in the checkpoint folder.
545
+
546
+ A typical usage might be ::
547
+
548
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
549
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
550
+ # submit to model hub or save the model to share with others
551
+
552
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
553
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
554
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
555
+
556
+ """
557
+ logger.info(f"Extracting fp32 weights")
558
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
559
+
560
+ logger.info(f"Overwriting model with fp32 weights")
561
+ model = model.cpu()
562
+ model.load_state_dict(state_dict, strict=False)
563
+
564
+ return model
565
+
566
+
567
+ if __name__ == "__main__":
568
+
569
+ parser = argparse.ArgumentParser()
570
+ parser.add_argument("checkpoint_dir",
571
+ type=str,
572
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
573
+ parser.add_argument(
574
+ "output_file",
575
+ type=str,
576
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
577
+ parser.add_argument("-t",
578
+ "--tag",
579
+ type=str,
580
+ default=None,
581
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
582
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
583
+ args = parser.parse_args()
584
+
585
+ debug = args.debug
586
+
587
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)