Hugging Face's logo

nkkbr
/
ViCA-ScanNet-10p

Safetensors
llava
Model card Files
xet
Community
nkkbr commited on
Commit
81d5c87
·
1 Parent(s): 5186a7c

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 +2317 -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_step328
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:e2c08c0763702e21e64ade4a7bbfb2e25887cf6c22c7b70114c062fa6230c0eb
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:dfb52ac0a41339976302945e460b6096cba87465c37e08967e94ec40a1277473
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b42b5342ab42f14941bb8af36a8cbaea404984e05e3b05654e781da8d6df21f
3
+ size 4994571904
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc697ccc75665d028b7564dcba4ce60e679e943fd1df28402788abdc23f2c40
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 sha256:4e0823dd1c0413af90c70259767fa2cab059108a440e087d76b52e2af33925a3
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26aca316ba0d4c6677045ada1185d5ae3f6ff3cffcfbe8021dc1202c6d957afc
3
+ size 15984
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d69eba4b2736f93de5b20bd52a33c4d116c5dc2f1034dd2edb256564eb67fe0
3
+ size 15984
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e56680f0cb6addb8cf21ab04b1368ad78f4dce9c648cb2a7aeaa9f64f1bdb12
3
+ size 15984
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16bc6652251b62d799cafe0fce8e8b58966540e9fcf10950a97b0e6b4fbc5fda
3
+ size 15984
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b5edd0e0a703b7f24fac8ab6a683cafad7c860902c42e6e53b13aef9221517
3
+ size 15984
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01580883e3cf0653dcbaa98ad58548951dfab3ef7e44089358a8d6b3681b0e0
3
+ size 15984
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13e1d7daa1e65ad38baa3cb67833adeb99266471f40b6ac4a6540fca209a7b86
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 +1,2317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.1001068213032199,
5
+ "eval_steps": 500,
6
+ "global_step": 328,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0003052037234854265,
13
+ "grad_norm": 19.476922880741295,
14
+ "learning_rate": 1.0101010101010103e-07,
15
+ "loss": 1.1728,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.000610407446970853,
20
+ "grad_norm": 29.879020388476594,
21
+ "learning_rate": 2.0202020202020205e-07,
22
+ "loss": 1.0955,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0009156111704562796,
27
+ "grad_norm": 24.931945947136526,
28
+ "learning_rate": 3.0303030303030305e-07,
29
+ "loss": 0.9541,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.001220814893941706,
34
+ "grad_norm": 27.83214939667906,
35
+ "learning_rate": 4.040404040404041e-07,
36
+ "loss": 1.0735,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.0015260186174271325,
41
+ "grad_norm": 21.219233961021736,
42
+ "learning_rate": 5.05050505050505e-07,
43
+ "loss": 1.0455,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.0018312223409125592,
48
+ "grad_norm": 20.022707446211225,
49
+ "learning_rate": 6.060606060606061e-07,
50
+ "loss": 0.9675,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.0021364260643979855,
55
+ "grad_norm": 26.532427830157193,
56
+ "learning_rate": 7.070707070707071e-07,
57
+ "loss": 1.1393,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.002441629787883412,
62
+ "grad_norm": 27.89728780710031,
63
+ "learning_rate": 8.080808080808082e-07,
64
+ "loss": 1.0952,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.0027468335113688385,
69
+ "grad_norm": 20.346264005570532,
70
+ "learning_rate": 9.090909090909091e-07,
71
+ "loss": 0.9626,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.003052037234854265,
76
+ "grad_norm": 18.804489508720884,
77
+ "learning_rate": 1.01010101010101e-06,
78
+ "loss": 1.0255,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.003357240958339692,
83
+ "grad_norm": 19.776534785573535,
84
+ "learning_rate": 1.111111111111111e-06,
85
+ "loss": 0.7399,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.0036624446818251184,
90
+ "grad_norm": 21.16130386460154,
91
+ "learning_rate": 1.2121212121212122e-06,
92
+ "loss": 0.5413,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.0039676484053105445,
97
+ "grad_norm": 16.482713371526263,
98
+ "learning_rate": 1.3131313131313134e-06,
99
+ "loss": 0.5773,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.004272852128795971,
104
+ "grad_norm": 10.780528168770594,
105
+ "learning_rate": 1.4141414141414143e-06,
106
+ "loss": 0.6782,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.0045780558522813975,
111
+ "grad_norm": 7.0900135030469915,
112
+ "learning_rate": 1.5151515151515152e-06,
113
+ "loss": 0.9153,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.004883259575766824,
118
+ "grad_norm": 8.490445320662754,
119
+ "learning_rate": 1.6161616161616164e-06,
120
+ "loss": 0.4798,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.0051884632992522505,
125
+ "grad_norm": 6.677142812986669,
126
+ "learning_rate": 1.7171717171717173e-06,
127
+ "loss": 0.4782,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.005493667022737677,
132
+ "grad_norm": 5.9204247946017485,
133
+ "learning_rate": 1.8181818181818183e-06,
134
+ "loss": 0.3191,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.0057988707462231035,
139
+ "grad_norm": 5.012462343754674,
140
+ "learning_rate": 1.9191919191919192e-06,
141
+ "loss": 0.4115,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.00610407446970853,
146
+ "grad_norm": 3.9095937836899113,
147
+ "learning_rate": 2.02020202020202e-06,
148
+ "loss": 0.6158,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.006409278193193957,
153
+ "grad_norm": 4.438163815129716,
154
+ "learning_rate": 2.1212121212121216e-06,
155
+ "loss": 0.7388,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.006714481916679384,
160
+ "grad_norm": 3.62875198348435,
161
+ "learning_rate": 2.222222222222222e-06,
162
+ "loss": 0.2875,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.00701968564016481,
167
+ "grad_norm": 4.963543929599541,
168
+ "learning_rate": 2.3232323232323234e-06,
169
+ "loss": 0.4662,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.007324889363650237,
174
+ "grad_norm": 4.274904100558248,
175
+ "learning_rate": 2.4242424242424244e-06,
176
+ "loss": 0.5171,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.007630093087135663,
181
+ "grad_norm": 2.670885047669819,
182
+ "learning_rate": 2.5252525252525258e-06,
183
+ "loss": 0.4488,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.007935296810621089,
188
+ "grad_norm": 2.6864388610994014,
189
+ "learning_rate": 2.6262626262626267e-06,
190
+ "loss": 0.372,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.008240500534106516,
195
+ "grad_norm": 3.804357369452407,
196
+ "learning_rate": 2.7272727272727272e-06,
197
+ "loss": 0.2646,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.008545704257591942,
202
+ "grad_norm": 4.059008227452532,
203
+ "learning_rate": 2.8282828282828286e-06,
204
+ "loss": 0.5907,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.008850907981077369,
209
+ "grad_norm": 4.9062443629918855,
210
+ "learning_rate": 2.9292929292929295e-06,
211
+ "loss": 0.2972,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.009156111704562795,
216
+ "grad_norm": 3.5391495380267064,
217
+ "learning_rate": 3.0303030303030305e-06,
218
+ "loss": 0.3821,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.009461315428048222,
223
+ "grad_norm": 2.5896920322264854,
224
+ "learning_rate": 3.131313131313132e-06,
225
+ "loss": 0.4164,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.009766519151533648,
230
+ "grad_norm": 3.0230775761822937,
231
+ "learning_rate": 3.232323232323233e-06,
232
+ "loss": 0.4237,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.010071722875019075,
237
+ "grad_norm": 2.8417717057519423,
238
+ "learning_rate": 3.3333333333333333e-06,
239
+ "loss": 0.3353,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.010376926598504501,
244
+ "grad_norm": 2.5789157463945878,
245
+ "learning_rate": 3.4343434343434347e-06,
246
+ "loss": 0.3769,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.010682130321989928,
251
+ "grad_norm": 2.5222241581850096,
252
+ "learning_rate": 3.5353535353535356e-06,
253
+ "loss": 0.519,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.010987334045475354,
258
+ "grad_norm": 2.8704682168269127,
259
+ "learning_rate": 3.6363636363636366e-06,
260
+ "loss": 0.2829,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.01129253776896078,
265
+ "grad_norm": 3.24684532820184,
266
+ "learning_rate": 3.737373737373738e-06,
267
+ "loss": 0.3586,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.011597741492446207,
272
+ "grad_norm": 5.24792475783676,
273
+ "learning_rate": 3.8383838383838385e-06,
274
+ "loss": 0.402,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.011902945215931634,
279
+ "grad_norm": 3.111184671834165,
280
+ "learning_rate": 3.93939393939394e-06,
281
+ "loss": 0.466,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.01220814893941706,
286
+ "grad_norm": 3.165565566985893,
287
+ "learning_rate": 4.04040404040404e-06,
288
+ "loss": 0.2678,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.012513352662902488,
293
+ "grad_norm": 2.5486933296193257,
294
+ "learning_rate": 4.141414141414142e-06,
295
+ "loss": 0.5457,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.012818556386387915,
300
+ "grad_norm": 3.4373721012250438,
301
+ "learning_rate": 4.242424242424243e-06,
302
+ "loss": 0.3862,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.013123760109873341,
307
+ "grad_norm": 2.863317221380458,
308
+ "learning_rate": 4.343434343434344e-06,
309
+ "loss": 0.3601,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.013428963833358768,
314
+ "grad_norm": 2.1041128573446035,
315
+ "learning_rate": 4.444444444444444e-06,
316
+ "loss": 0.3693,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.013734167556844194,
321
+ "grad_norm": 2.286990324679626,
322
+ "learning_rate": 4.5454545454545455e-06,
323
+ "loss": 0.2513,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.01403937128032962,
328
+ "grad_norm": 8.793466778432636,
329
+ "learning_rate": 4.646464646464647e-06,
330
+ "loss": 0.4343,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.014344575003815047,
335
+ "grad_norm": 1.8648737533834159,
336
+ "learning_rate": 4.747474747474748e-06,
337
+ "loss": 0.2631,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.014649778727300474,
342
+ "grad_norm": 2.3081781364995324,
343
+ "learning_rate": 4.848484848484849e-06,
344
+ "loss": 0.2755,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.0149549824507859,
349
+ "grad_norm": 2.284005369243557,
350
+ "learning_rate": 4.94949494949495e-06,
351
+ "loss": 0.4186,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.015260186174271327,
356
+ "grad_norm": 2.6759709423238096,
357
+ "learning_rate": 5.0505050505050515e-06,
358
+ "loss": 0.6459,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.015565389897756753,
363
+ "grad_norm": 2.8773749120652523,
364
+ "learning_rate": 5.151515151515152e-06,
365
+ "loss": 0.3324,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.015870593621242178,
370
+ "grad_norm": 2.8060164424498786,
371
+ "learning_rate": 5.252525252525253e-06,
372
+ "loss": 0.3608,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.016175797344727606,
377
+ "grad_norm": 2.3060494229726793,
378
+ "learning_rate": 5.353535353535354e-06,
379
+ "loss": 0.3818,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.01648100106821303,
384
+ "grad_norm": 2.073464811557714,
385
+ "learning_rate": 5.4545454545454545e-06,
386
+ "loss": 0.2667,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.01678620479169846,
391
+ "grad_norm": 2.3474749655399245,
392
+ "learning_rate": 5.555555555555557e-06,
393
+ "loss": 0.35,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.017091408515183884,
398
+ "grad_norm": 3.6988890036672086,
399
+ "learning_rate": 5.656565656565657e-06,
400
+ "loss": 0.284,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.017396612238669312,
405
+ "grad_norm": 2.313501192849839,
406
+ "learning_rate": 5.7575757575757586e-06,
407
+ "loss": 0.3308,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.017701815962154737,
412
+ "grad_norm": 2.411936098122121,
413
+ "learning_rate": 5.858585858585859e-06,
414
+ "loss": 0.3982,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.018007019685640165,
419
+ "grad_norm": 2.724660127775508,
420
+ "learning_rate": 5.95959595959596e-06,
421
+ "loss": 0.3587,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.01831222340912559,
426
+ "grad_norm": 3.130895013540925,
427
+ "learning_rate": 6.060606060606061e-06,
428
+ "loss": 0.3427,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.01861742713261102,
433
+ "grad_norm": 3.4261489723004614,
434
+ "learning_rate": 6.1616161616161615e-06,
435
+ "loss": 0.4578,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.018922630856096443,
440
+ "grad_norm": 2.413871881063889,
441
+ "learning_rate": 6.262626262626264e-06,
442
+ "loss": 0.2067,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.01922783457958187,
447
+ "grad_norm": 2.0941348505038366,
448
+ "learning_rate": 6.363636363636364e-06,
449
+ "loss": 0.27,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.019533038303067296,
454
+ "grad_norm": 2.2153240133926153,
455
+ "learning_rate": 6.464646464646466e-06,
456
+ "loss": 0.3298,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.019838242026552724,
461
+ "grad_norm": 2.422022070572305,
462
+ "learning_rate": 6.565656565656566e-06,
463
+ "loss": 0.4894,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.02014344575003815,
468
+ "grad_norm": 2.45442660843552,
469
+ "learning_rate": 6.666666666666667e-06,
470
+ "loss": 0.3684,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.020448649473523577,
475
+ "grad_norm": 3.5398238081108304,
476
+ "learning_rate": 6.767676767676769e-06,
477
+ "loss": 0.4233,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.020753853197009002,
482
+ "grad_norm": 2.530397719080883,
483
+ "learning_rate": 6.868686868686869e-06,
484
+ "loss": 0.2676,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.02105905692049443,
489
+ "grad_norm": 2.259346305696615,
490
+ "learning_rate": 6.969696969696971e-06,
491
+ "loss": 0.4409,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.021364260643979855,
496
+ "grad_norm": 2.3339543424453764,
497
+ "learning_rate": 7.070707070707071e-06,
498
+ "loss": 0.3882,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.021669464367465283,
503
+ "grad_norm": 2.348843038116063,
504
+ "learning_rate": 7.171717171717172e-06,
505
+ "loss": 0.3904,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.021974668090950708,
510
+ "grad_norm": 2.7011363922899965,
511
+ "learning_rate": 7.272727272727273e-06,
512
+ "loss": 0.3586,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.022279871814436136,
517
+ "grad_norm": 2.6923381814173486,
518
+ "learning_rate": 7.373737373737374e-06,
519
+ "loss": 0.4331,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.02258507553792156,
524
+ "grad_norm": 2.0435337430530924,
525
+ "learning_rate": 7.474747474747476e-06,
526
+ "loss": 0.2739,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.02289027926140699,
531
+ "grad_norm": 2.257183264462076,
532
+ "learning_rate": 7.5757575757575764e-06,
533
+ "loss": 0.4554,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.023195482984892414,
538
+ "grad_norm": 2.5384248372961626,
539
+ "learning_rate": 7.676767676767677e-06,
540
+ "loss": 0.4934,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.023500686708377842,
545
+ "grad_norm": 2.1578730127908488,
546
+ "learning_rate": 7.77777777777778e-06,
547
+ "loss": 0.3519,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.023805890431863267,
552
+ "grad_norm": 2.1316764516757476,
553
+ "learning_rate": 7.87878787878788e-06,
554
+ "loss": 0.3268,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.024111094155348695,
559
+ "grad_norm": 2.095996278024237,
560
+ "learning_rate": 7.97979797979798e-06,
561
+ "loss": 0.3318,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.02441629787883412,
566
+ "grad_norm": 1.9985574049541877,
567
+ "learning_rate": 8.08080808080808e-06,
568
+ "loss": 0.1852,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.02472150160231955,
573
+ "grad_norm": 1.7092921737326583,
574
+ "learning_rate": 8.181818181818183e-06,
575
+ "loss": 0.2412,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.025026705325804977,
580
+ "grad_norm": 1.9609482601524066,
581
+ "learning_rate": 8.282828282828283e-06,
582
+ "loss": 0.3349,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.0253319090492904,
587
+ "grad_norm": 2.5619254980161412,
588
+ "learning_rate": 8.383838383838384e-06,
589
+ "loss": 0.3327,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.02563711277277583,
594
+ "grad_norm": 2.1734116421771827,
595
+ "learning_rate": 8.484848484848486e-06,
596
+ "loss": 0.5005,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.025942316496261254,
601
+ "grad_norm": 2.4612836321871785,
602
+ "learning_rate": 8.585858585858587e-06,
603
+ "loss": 0.5919,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.026247520219746683,
608
+ "grad_norm": 2.050264187978962,
609
+ "learning_rate": 8.686868686868687e-06,
610
+ "loss": 0.2654,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.026552723943232107,
615
+ "grad_norm": 1.7466792206761999,
616
+ "learning_rate": 8.787878787878788e-06,
617
+ "loss": 0.2875,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.026857927666717536,
622
+ "grad_norm": 1.9114055019911376,
623
+ "learning_rate": 8.888888888888888e-06,
624
+ "loss": 0.3317,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.02716313139020296,
629
+ "grad_norm": 2.136028617695754,
630
+ "learning_rate": 8.98989898989899e-06,
631
+ "loss": 0.4322,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.02746833511368839,
636
+ "grad_norm": 2.0559196693817303,
637
+ "learning_rate": 9.090909090909091e-06,
638
+ "loss": 0.3372,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.027773538837173813,
643
+ "grad_norm": 1.6053810559753854,
644
+ "learning_rate": 9.191919191919193e-06,
645
+ "loss": 0.2833,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.02807874256065924,
650
+ "grad_norm": 1.9190338968500587,
651
+ "learning_rate": 9.292929292929294e-06,
652
+ "loss": 0.2358,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.028383946284144666,
657
+ "grad_norm": 1.7424429804531956,
658
+ "learning_rate": 9.393939393939396e-06,
659
+ "loss": 0.2805,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.028689150007630095,
664
+ "grad_norm": 1.5616301594921251,
665
+ "learning_rate": 9.494949494949497e-06,
666
+ "loss": 0.326,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.02899435373111552,
671
+ "grad_norm": 2.6517363851490297,
672
+ "learning_rate": 9.595959595959597e-06,
673
+ "loss": 0.5839,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.029299557454600948,
678
+ "grad_norm": 1.9068377479857994,
679
+ "learning_rate": 9.696969696969698e-06,
680
+ "loss": 0.4213,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.029604761178086372,
685
+ "grad_norm": 2.147263972819766,
686
+ "learning_rate": 9.797979797979798e-06,
687
+ "loss": 0.3776,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.0299099649015718,
692
+ "grad_norm": 2.3466004395170685,
693
+ "learning_rate": 9.8989898989899e-06,
694
+ "loss": 0.4828,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.030215168625057225,
699
+ "grad_norm": 1.9328188798162316,
700
+ "learning_rate": 1e-05,
701
+ "loss": 0.3816,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.030520372348542654,
706
+ "grad_norm": 2.120656679761712,
707
+ "learning_rate": 9.999997555414177e-06,
708
+ "loss": 0.287,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.03082557607202808,
713
+ "grad_norm": 1.8272767014289886,
714
+ "learning_rate": 9.999990221659095e-06,
715
+ "loss": 0.2529,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.031130779795513507,
720
+ "grad_norm": 2.108876035097533,
721
+ "learning_rate": 9.999977998741925e-06,
722
+ "loss": 0.4,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.031435983518998935,
727
+ "grad_norm": 2.611227326027621,
728
+ "learning_rate": 9.999960886674623e-06,
729
+ "loss": 0.5577,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.031741187242484356,
734
+ "grad_norm": 2.012760226088087,
735
+ "learning_rate": 9.999938885473916e-06,
736
+ "loss": 0.2397,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.032046390965969784,
741
+ "grad_norm": 3.4069313977643088,
742
+ "learning_rate": 9.999911995161323e-06,
743
+ "loss": 0.3074,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.03235159468945521,
748
+ "grad_norm": 1.5281487804348939,
749
+ "learning_rate": 9.999880215763133e-06,
750
+ "loss": 0.306,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.03265679841294064,
755
+ "grad_norm": 1.5733903167529437,
756
+ "learning_rate": 9.999843547310427e-06,
757
+ "loss": 0.3123,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.03296200213642606,
762
+ "grad_norm": 2.2084260837102776,
763
+ "learning_rate": 9.999801989839055e-06,
764
+ "loss": 0.2686,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.03326720585991149,
769
+ "grad_norm": 2.0235527329790477,
770
+ "learning_rate": 9.999755543389658e-06,
771
+ "loss": 0.362,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.03357240958339692,
776
+ "grad_norm": 1.4126246608311444,
777
+ "learning_rate": 9.999704208007647e-06,
778
+ "loss": 0.1868,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.03387761330688235,
783
+ "grad_norm": 1.9363750145032863,
784
+ "learning_rate": 9.999647983743227e-06,
785
+ "loss": 0.4674,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.03418281703036777,
790
+ "grad_norm": 2.306492812857686,
791
+ "learning_rate": 9.999586870651372e-06,
792
+ "loss": 0.7454,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.034488020753853196,
797
+ "grad_norm": 1.9927578577114744,
798
+ "learning_rate": 9.999520868791839e-06,
799
+ "loss": 0.2964,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.034793224477338625,
804
+ "grad_norm": 2.897230200199283,
805
+ "learning_rate": 9.99944997822917e-06,
806
+ "loss": 0.3507,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.03509842820082405,
811
+ "grad_norm": 1.7040567211820554,
812
+ "learning_rate": 9.999374199032682e-06,
813
+ "loss": 0.358,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.035403631924309474,
818
+ "grad_norm": 1.7684725864001616,
819
+ "learning_rate": 9.999293531276475e-06,
820
+ "loss": 0.469,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.0357088356477949,
825
+ "grad_norm": 2.151331613378997,
826
+ "learning_rate": 9.999207975039429e-06,
827
+ "loss": 0.4007,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.03601403937128033,
832
+ "grad_norm": 2.1827006415812678,
833
+ "learning_rate": 9.999117530405205e-06,
834
+ "loss": 0.373,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.03631924309476576,
839
+ "grad_norm": 2.0424756244526283,
840
+ "learning_rate": 9.99902219746224e-06,
841
+ "loss": 0.4664,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.03662444681825118,
846
+ "grad_norm": 2.4438750213097014,
847
+ "learning_rate": 9.998921976303757e-06,
848
+ "loss": 0.5884,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.03692965054173661,
853
+ "grad_norm": 1.6168805259489245,
854
+ "learning_rate": 9.998816867027753e-06,
855
+ "loss": 0.3874,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.03723485426522204,
860
+ "grad_norm": 2.4836564854380914,
861
+ "learning_rate": 9.99870686973701e-06,
862
+ "loss": 0.3865,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.037540057988707465,
867
+ "grad_norm": 2.187549263535683,
868
+ "learning_rate": 9.998591984539085e-06,
869
+ "loss": 0.4419,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.037845261712192886,
874
+ "grad_norm": 2.3145724108896366,
875
+ "learning_rate": 9.998472211546317e-06,
876
+ "loss": 0.5048,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.038150465435678314,
881
+ "grad_norm": 2.6043824271784377,
882
+ "learning_rate": 9.998347550875825e-06,
883
+ "loss": 0.4323,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.03845566915916374,
888
+ "grad_norm": 1.7266964407358079,
889
+ "learning_rate": 9.998218002649507e-06,
890
+ "loss": 0.3093,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.03876087288264917,
895
+ "grad_norm": 2.3091863655820397,
896
+ "learning_rate": 9.99808356699404e-06,
897
+ "loss": 0.5394,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.03906607660613459,
902
+ "grad_norm": 2.178584103245907,
903
+ "learning_rate": 9.997944244040877e-06,
904
+ "loss": 0.562,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.03937128032962002,
909
+ "grad_norm": 1.4762803065381216,
910
+ "learning_rate": 9.997800033926252e-06,
911
+ "loss": 0.3012,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.03967648405310545,
916
+ "grad_norm": 1.6768704233807339,
917
+ "learning_rate": 9.997650936791183e-06,
918
+ "loss": 0.3314,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.03998168777659088,
923
+ "grad_norm": 1.8423584681568375,
924
+ "learning_rate": 9.997496952781461e-06,
925
+ "loss": 0.5373,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.0402868915000763,
930
+ "grad_norm": 1.4926628434179245,
931
+ "learning_rate": 9.997338082047656e-06,
932
+ "loss": 0.1992,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.040592095223561726,
937
+ "grad_norm": 1.6323074947028773,
938
+ "learning_rate": 9.997174324745117e-06,
939
+ "loss": 0.4872,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.040897298947047155,
944
+ "grad_norm": 2.159688005520465,
945
+ "learning_rate": 9.997005681033973e-06,
946
+ "loss": 0.5076,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.04120250267053258,
951
+ "grad_norm": 2.207163038792008,
952
+ "learning_rate": 9.996832151079127e-06,
953
+ "loss": 0.2677,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.041507706394018004,
958
+ "grad_norm": 1.3990677420334965,
959
+ "learning_rate": 9.996653735050265e-06,
960
+ "loss": 0.2526,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.04181291011750343,
965
+ "grad_norm": 1.7368886105229604,
966
+ "learning_rate": 9.996470433121847e-06,
967
+ "loss": 0.2874,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.04211811384098886,
972
+ "grad_norm": 1.8138446424045762,
973
+ "learning_rate": 9.996282245473113e-06,
974
+ "loss": 0.2986,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.04242331756447429,
979
+ "grad_norm": 1.8564789601928355,
980
+ "learning_rate": 9.996089172288078e-06,
981
+ "loss": 0.3954,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.04272852128795971,
986
+ "grad_norm": 1.9085920361180522,
987
+ "learning_rate": 9.995891213755536e-06,
988
+ "loss": 0.2739,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.04303372501144514,
993
+ "grad_norm": 1.8924678931794556,
994
+ "learning_rate": 9.99568837006906e-06,
995
+ "loss": 0.2766,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.04333892873493057,
1000
+ "grad_norm": 1.8418836037208652,
1001
+ "learning_rate": 9.995480641426992e-06,
1002
+ "loss": 0.488,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.043644132458415995,
1007
+ "grad_norm": 1.6305125707231247,
1008
+ "learning_rate": 9.99526802803246e-06,
1009
+ "loss": 0.3045,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.043949336181901416,
1014
+ "grad_norm": 2.143051665423358,
1015
+ "learning_rate": 9.995050530093366e-06,
1016
+ "loss": 0.3567,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.044254539905386844,
1021
+ "grad_norm": 1.994194545633334,
1022
+ "learning_rate": 9.994828147822387e-06,
1023
+ "loss": 0.3655,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.04455974362887227,
1028
+ "grad_norm": 1.8553346605537173,
1029
+ "learning_rate": 9.994600881436972e-06,
1030
+ "loss": 0.3249,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.0448649473523577,
1035
+ "grad_norm": 2.1613773805709857,
1036
+ "learning_rate": 9.994368731159351e-06,
1037
+ "loss": 0.4863,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.04517015107584312,
1042
+ "grad_norm": 2.199571706523493,
1043
+ "learning_rate": 9.99413169721653e-06,
1044
+ "loss": 0.465,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.04547535479932855,
1049
+ "grad_norm": 1.681707967900651,
1050
+ "learning_rate": 9.99388977984029e-06,
1051
+ "loss": 0.3472,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.04578055852281398,
1056
+ "grad_norm": 1.6586587053140593,
1057
+ "learning_rate": 9.993642979267184e-06,
1058
+ "loss": 0.3626,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.04608576224629941,
1063
+ "grad_norm": 2.12592721793332,
1064
+ "learning_rate": 9.993391295738542e-06,
1065
+ "loss": 0.3218,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.04639096596978483,
1070
+ "grad_norm": 1.6765944279655143,
1071
+ "learning_rate": 9.99313472950047e-06,
1072
+ "loss": 0.3402,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.046696169693270256,
1077
+ "grad_norm": 1.6019038139070678,
1078
+ "learning_rate": 9.992873280803848e-06,
1079
+ "loss": 0.4554,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.047001373416755685,
1084
+ "grad_norm": 1.6429860881882794,
1085
+ "learning_rate": 9.99260694990433e-06,
1086
+ "loss": 0.4086,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.04730657714024111,
1091
+ "grad_norm": 1.98592334325083,
1092
+ "learning_rate": 9.992335737062338e-06,
1093
+ "loss": 0.5733,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.047611780863726534,
1098
+ "grad_norm": 1.5624846648417388,
1099
+ "learning_rate": 9.992059642543076e-06,
1100
+ "loss": 0.2524,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.04791698458721196,
1105
+ "grad_norm": 1.4438198320418865,
1106
+ "learning_rate": 9.991778666616523e-06,
1107
+ "loss": 0.1756,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.04822218831069739,
1112
+ "grad_norm": 1.6284817295660008,
1113
+ "learning_rate": 9.991492809557424e-06,
1114
+ "loss": 0.4144,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.04852739203418282,
1119
+ "grad_norm": 1.2236340789910145,
1120
+ "learning_rate": 9.991202071645298e-06,
1121
+ "loss": 0.1664,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.04883259575766824,
1126
+ "grad_norm": 1.4874398163232816,
1127
+ "learning_rate": 9.99090645316444e-06,
1128
+ "loss": 0.3323,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.04913779948115367,
1133
+ "grad_norm": 2.5394515927833403,
1134
+ "learning_rate": 9.990605954403917e-06,
1135
+ "loss": 0.27,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.0494430032046391,
1140
+ "grad_norm": 1.7966332314422868,
1141
+ "learning_rate": 9.990300575657565e-06,
1142
+ "loss": 0.4453,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.049748206928124525,
1147
+ "grad_norm": 1.825976682624809,
1148
+ "learning_rate": 9.989990317223995e-06,
1149
+ "loss": 0.2646,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.05005341065160995,
1154
+ "grad_norm": 1.6554541925183588,
1155
+ "learning_rate": 9.989675179406588e-06,
1156
+ "loss": 0.445,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.050358614375095374,
1161
+ "grad_norm": 1.6711133844293076,
1162
+ "learning_rate": 9.989355162513496e-06,
1163
+ "loss": 0.3685,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.0506638180985808,
1168
+ "grad_norm": 1.8033315345252203,
1169
+ "learning_rate": 9.989030266857644e-06,
1170
+ "loss": 0.2566,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.05096902182206623,
1175
+ "grad_norm": 1.6879852444966537,
1176
+ "learning_rate": 9.988700492756726e-06,
1177
+ "loss": 0.4086,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.05127422554555166,
1182
+ "grad_norm": 1.6855038740169574,
1183
+ "learning_rate": 9.988365840533204e-06,
1184
+ "loss": 0.3081,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.05157942926903708,
1189
+ "grad_norm": 2.245121010490438,
1190
+ "learning_rate": 9.988026310514316e-06,
1191
+ "loss": 0.5646,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.05188463299252251,
1196
+ "grad_norm": 1.531117336209479,
1197
+ "learning_rate": 9.987681903032065e-06,
1198
+ "loss": 0.3598,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.05218983671600794,
1203
+ "grad_norm": 1.4368727600956301,
1204
+ "learning_rate": 9.987332618423221e-06,
1205
+ "loss": 0.3864,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.052495040439493365,
1210
+ "grad_norm": 2.039026486601271,
1211
+ "learning_rate": 9.98697845702933e-06,
1212
+ "loss": 0.2728,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.052800244162978786,
1217
+ "grad_norm": 1.5481974795842472,
1218
+ "learning_rate": 9.986619419196704e-06,
1219
+ "loss": 0.2376,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.053105447886464215,
1224
+ "grad_norm": 1.583025735121783,
1225
+ "learning_rate": 9.986255505276418e-06,
1226
+ "loss": 0.3941,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.05341065160994964,
1231
+ "grad_norm": 2.025610033619695,
1232
+ "learning_rate": 9.985886715624326e-06,
1233
+ "loss": 0.432,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.05371585533343507,
1238
+ "grad_norm": 1.9370365819159912,
1239
+ "learning_rate": 9.985513050601037e-06,
1240
+ "loss": 0.3311,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.05402105905692049,
1245
+ "grad_norm": 1.534591376747653,
1246
+ "learning_rate": 9.985134510571936e-06,
1247
+ "loss": 0.3804,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.05432626278040592,
1252
+ "grad_norm": 1.5627980520171343,
1253
+ "learning_rate": 9.984751095907175e-06,
1254
+ "loss": 0.3991,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.05463146650389135,
1259
+ "grad_norm": 1.858760828475349,
1260
+ "learning_rate": 9.984362806981665e-06,
1261
+ "loss": 0.4124,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.05493667022737678,
1266
+ "grad_norm": 1.4922057145689682,
1267
+ "learning_rate": 9.983969644175092e-06,
1268
+ "loss": 0.2571,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.0552418739508622,
1273
+ "grad_norm": 1.4358215484460224,
1274
+ "learning_rate": 9.983571607871903e-06,
1275
+ "loss": 0.3351,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.05554707767434763,
1280
+ "grad_norm": 1.7105120125454414,
1281
+ "learning_rate": 9.983168698461312e-06,
1282
+ "loss": 0.4374,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.055852281397833055,
1287
+ "grad_norm": 1.4100459259074987,
1288
+ "learning_rate": 9.982760916337296e-06,
1289
+ "loss": 0.3958,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.05615748512131848,
1294
+ "grad_norm": 1.667173817085955,
1295
+ "learning_rate": 9.982348261898598e-06,
1296
+ "loss": 0.2867,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.056462688844803904,
1301
+ "grad_norm": 1.8278737995984025,
1302
+ "learning_rate": 9.981930735548731e-06,
1303
+ "loss": 0.3738,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.05676789256828933,
1308
+ "grad_norm": 1.806852289121097,
1309
+ "learning_rate": 9.98150833769596e-06,
1310
+ "loss": 0.5608,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.05707309629177476,
1315
+ "grad_norm": 1.6986308867720055,
1316
+ "learning_rate": 9.981081068753324e-06,
1317
+ "loss": 0.4253,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.05737830001526019,
1322
+ "grad_norm": 1.6392088091109513,
1323
+ "learning_rate": 9.98064892913862e-06,
1324
+ "loss": 0.2444,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.05768350373874561,
1329
+ "grad_norm": 1.7762995408711126,
1330
+ "learning_rate": 9.980211919274407e-06,
1331
+ "loss": 0.3866,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.05798870746223104,
1336
+ "grad_norm": 1.7144647062044762,
1337
+ "learning_rate": 9.979770039588013e-06,
1338
+ "loss": 0.4504,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.05829391118571647,
1343
+ "grad_norm": 1.9069269572943617,
1344
+ "learning_rate": 9.979323290511517e-06,
1345
+ "loss": 0.4972,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.058599114909201895,
1350
+ "grad_norm": 1.831943664409223,
1351
+ "learning_rate": 9.978871672481774e-06,
1352
+ "loss": 0.3884,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.058904318632687316,
1357
+ "grad_norm": 1.60483584957947,
1358
+ "learning_rate": 9.978415185940383e-06,
1359
+ "loss": 0.3366,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.059209522356172745,
1364
+ "grad_norm": 2.041633475935638,
1365
+ "learning_rate": 9.977953831333718e-06,
1366
+ "loss": 0.4928,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.05951472607965817,
1371
+ "grad_norm": 2.1574861604284243,
1372
+ "learning_rate": 9.977487609112904e-06,
1373
+ "loss": 0.7092,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.0598199298031436,
1378
+ "grad_norm": 1.5382345073334531,
1379
+ "learning_rate": 9.97701651973383e-06,
1380
+ "loss": 0.2236,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.06012513352662902,
1385
+ "grad_norm": 2.1479787995768014,
1386
+ "learning_rate": 9.976540563657143e-06,
1387
+ "loss": 0.5182,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.06043033725011445,
1392
+ "grad_norm": 1.8579437774142544,
1393
+ "learning_rate": 9.976059741348252e-06,
1394
+ "loss": 0.3093,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.06073554097359988,
1399
+ "grad_norm": 1.5409701380525285,
1400
+ "learning_rate": 9.975574053277317e-06,
1401
+ "loss": 0.2877,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.06104074469708531,
1406
+ "grad_norm": 1.5474598097011698,
1407
+ "learning_rate": 9.975083499919264e-06,
1408
+ "loss": 0.2981,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.06134594842057073,
1413
+ "grad_norm": 1.9202152932180157,
1414
+ "learning_rate": 9.974588081753773e-06,
1415
+ "loss": 0.5369,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.06165115214405616,
1420
+ "grad_norm": 1.4598442515817716,
1421
+ "learning_rate": 9.974087799265279e-06,
1422
+ "loss": 0.3696,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.061956355867541585,
1427
+ "grad_norm": 1.48078814360119,
1428
+ "learning_rate": 9.973582652942975e-06,
1429
+ "loss": 0.284,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.06226155959102701,
1434
+ "grad_norm": 2.100326004155181,
1435
+ "learning_rate": 9.973072643280813e-06,
1436
+ "loss": 0.5681,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.06256676331451244,
1441
+ "grad_norm": 1.976128330719915,
1442
+ "learning_rate": 9.972557770777496e-06,
1443
+ "loss": 0.3655,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.06287196703799787,
1448
+ "grad_norm": 1.2103730393566896,
1449
+ "learning_rate": 9.972038035936483e-06,
1450
+ "loss": 0.2471,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.06317717076148328,
1455
+ "grad_norm": 1.670449906238349,
1456
+ "learning_rate": 9.971513439265992e-06,
1457
+ "loss": 0.2184,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.06348237448496871,
1462
+ "grad_norm": 1.5020544764497652,
1463
+ "learning_rate": 9.970983981278989e-06,
1464
+ "loss": 0.3196,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.06378757820845414,
1469
+ "grad_norm": 1.7833251911345853,
1470
+ "learning_rate": 9.970449662493195e-06,
1471
+ "loss": 0.4122,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.06409278193193957,
1476
+ "grad_norm": 1.4149595334362772,
1477
+ "learning_rate": 9.96991048343109e-06,
1478
+ "loss": 0.2947,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.064397985655425,
1483
+ "grad_norm": 1.5991867680932033,
1484
+ "learning_rate": 9.969366444619898e-06,
1485
+ "loss": 0.1902,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.06470318937891043,
1490
+ "grad_norm": 1.4132064841734169,
1491
+ "learning_rate": 9.968817546591601e-06,
1492
+ "loss": 0.3389,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.06500839310239585,
1497
+ "grad_norm": 1.7671902900221814,
1498
+ "learning_rate": 9.968263789882926e-06,
1499
+ "loss": 0.4294,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.06531359682588128,
1504
+ "grad_norm": 1.5709821497329826,
1505
+ "learning_rate": 9.96770517503536e-06,
1506
+ "loss": 0.2765,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.0656188005493667,
1511
+ "grad_norm": 1.5211731343844295,
1512
+ "learning_rate": 9.967141702595134e-06,
1513
+ "loss": 0.387,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.06592400427285212,
1518
+ "grad_norm": 1.5499265222668686,
1519
+ "learning_rate": 9.96657337311323e-06,
1520
+ "loss": 0.4535,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.06622920799633755,
1525
+ "grad_norm": 1.4736546539447488,
1526
+ "learning_rate": 9.966000187145383e-06,
1527
+ "loss": 0.3834,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.06653441171982298,
1532
+ "grad_norm": 1.3306288958233108,
1533
+ "learning_rate": 9.965422145252072e-06,
1534
+ "loss": 0.3172,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.06683961544330841,
1539
+ "grad_norm": 1.5745937005003143,
1540
+ "learning_rate": 9.964839247998524e-06,
1541
+ "loss": 0.2725,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.06714481916679384,
1546
+ "grad_norm": 1.7546511557153388,
1547
+ "learning_rate": 9.96425149595472e-06,
1548
+ "loss": 0.3577,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.06745002289027927,
1553
+ "grad_norm": 2.0422588449754286,
1554
+ "learning_rate": 9.96365888969538e-06,
1555
+ "loss": 0.4976,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.0677552266137647,
1560
+ "grad_norm": 1.4661824124133862,
1561
+ "learning_rate": 9.963061429799979e-06,
1562
+ "loss": 0.3672,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.06806043033725011,
1567
+ "grad_norm": 2.0959067552369666,
1568
+ "learning_rate": 9.96245911685273e-06,
1569
+ "loss": 0.5381,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.06836563406073554,
1574
+ "grad_norm": 1.3296813372997014,
1575
+ "learning_rate": 9.961851951442599e-06,
1576
+ "loss": 0.2799,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.06867083778422096,
1581
+ "grad_norm": 1.7385807765114274,
1582
+ "learning_rate": 9.96123993416329e-06,
1583
+ "loss": 0.5183,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.06897604150770639,
1588
+ "grad_norm": 1.5190119701865645,
1589
+ "learning_rate": 9.960623065613254e-06,
1590
+ "loss": 0.4608,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.06928124523119182,
1595
+ "grad_norm": 1.4393894383331207,
1596
+ "learning_rate": 9.96000134639569e-06,
1597
+ "loss": 0.3455,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.06958644895467725,
1602
+ "grad_norm": 1.7132863682619555,
1603
+ "learning_rate": 9.959374777118533e-06,
1604
+ "loss": 0.316,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.06989165267816268,
1609
+ "grad_norm": 1.3227120889592454,
1610
+ "learning_rate": 9.958743358394464e-06,
1611
+ "loss": 0.2467,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.0701968564016481,
1616
+ "grad_norm": 1.5331153407144422,
1617
+ "learning_rate": 9.95810709084091e-06,
1618
+ "loss": 0.3138,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.07050206012513352,
1623
+ "grad_norm": 1.7990748995190806,
1624
+ "learning_rate": 9.957465975080031e-06,
1625
+ "loss": 0.4747,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.07080726384861895,
1630
+ "grad_norm": 1.1638981235859056,
1631
+ "learning_rate": 9.956820011738736e-06,
1632
+ "loss": 0.2265,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.07111246757210438,
1637
+ "grad_norm": 1.5739388418179414,
1638
+ "learning_rate": 9.956169201448665e-06,
1639
+ "loss": 0.5066,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.0714176712955898,
1644
+ "grad_norm": 1.6803933013620869,
1645
+ "learning_rate": 9.955513544846205e-06,
1646
+ "loss": 0.4415,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.07172287501907523,
1651
+ "grad_norm": 1.4014872110785643,
1652
+ "learning_rate": 9.954853042572479e-06,
1653
+ "loss": 0.3271,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.07202807874256066,
1658
+ "grad_norm": 1.5310222689941932,
1659
+ "learning_rate": 9.954187695273352e-06,
1660
+ "loss": 0.3289,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.07233328246604609,
1665
+ "grad_norm": 2.166268226472017,
1666
+ "learning_rate": 9.953517503599419e-06,
1667
+ "loss": 0.622,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.07263848618953152,
1672
+ "grad_norm": 2.258081862277545,
1673
+ "learning_rate": 9.952842468206019e-06,
1674
+ "loss": 0.5071,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.07294368991301693,
1679
+ "grad_norm": 1.7322119894263104,
1680
+ "learning_rate": 9.952162589753224e-06,
1681
+ "loss": 0.5097,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.07324889363650236,
1686
+ "grad_norm": 1.9966284228033864,
1687
+ "learning_rate": 9.951477868905843e-06,
1688
+ "loss": 0.2263,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.07355409735998779,
1693
+ "grad_norm": 1.6793267860774614,
1694
+ "learning_rate": 9.95078830633342e-06,
1695
+ "loss": 0.2065,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.07385930108347322,
1700
+ "grad_norm": 2.122564153881175,
1701
+ "learning_rate": 9.95009390271023e-06,
1702
+ "loss": 0.2665,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.07416450480695864,
1707
+ "grad_norm": 1.5852282963187305,
1708
+ "learning_rate": 9.949394658715289e-06,
1709
+ "loss": 0.4453,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.07446970853044407,
1714
+ "grad_norm": 1.7534712016120517,
1715
+ "learning_rate": 9.948690575032338e-06,
1716
+ "loss": 0.3628,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.0747749122539295,
1721
+ "grad_norm": 1.351810586905304,
1722
+ "learning_rate": 9.947981652349854e-06,
1723
+ "loss": 0.3984,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.07508011597741493,
1728
+ "grad_norm": 1.8377506474408298,
1729
+ "learning_rate": 9.947267891361051e-06,
1730
+ "loss": 0.3677,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.07538531970090036,
1735
+ "grad_norm": 1.4655632998364951,
1736
+ "learning_rate": 9.946549292763865e-06,
1737
+ "loss": 0.3516,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.07569052342438577,
1742
+ "grad_norm": 3.240838121636416,
1743
+ "learning_rate": 9.945825857260967e-06,
1744
+ "loss": 0.2627,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.0759957271478712,
1749
+ "grad_norm": 1.4085823215183912,
1750
+ "learning_rate": 9.945097585559757e-06,
1751
+ "loss": 0.2716,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.07630093087135663,
1756
+ "grad_norm": 1.6361471921651585,
1757
+ "learning_rate": 9.944364478372364e-06,
1758
+ "loss": 0.3595,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.07660613459484206,
1763
+ "grad_norm": 1.0912978886499554,
1764
+ "learning_rate": 9.943626536415647e-06,
1765
+ "loss": 0.1968,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.07691133831832749,
1770
+ "grad_norm": 1.9515717700893849,
1771
+ "learning_rate": 9.942883760411188e-06,
1772
+ "loss": 0.374,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.07721654204181291,
1777
+ "grad_norm": 1.5560755068838334,
1778
+ "learning_rate": 9.942136151085302e-06,
1779
+ "loss": 0.44,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.07752174576529834,
1784
+ "grad_norm": 1.4843235207715992,
1785
+ "learning_rate": 9.941383709169024e-06,
1786
+ "loss": 0.3175,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.07782694948878377,
1791
+ "grad_norm": 1.5210960196158274,
1792
+ "learning_rate": 9.94062643539812e-06,
1793
+ "loss": 0.3722,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.07813215321226918,
1798
+ "grad_norm": 1.6656094376801425,
1799
+ "learning_rate": 9.939864330513079e-06,
1800
+ "loss": 0.3511,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.07843735693575461,
1805
+ "grad_norm": 1.2732857455769802,
1806
+ "learning_rate": 9.939097395259108e-06,
1807
+ "loss": 0.2619,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.07874256065924004,
1812
+ "grad_norm": 1.8947301386622588,
1813
+ "learning_rate": 9.938325630386149e-06,
1814
+ "loss": 0.3933,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.07904776438272547,
1819
+ "grad_norm": 1.5625416559388712,
1820
+ "learning_rate": 9.937549036648857e-06,
1821
+ "loss": 0.4491,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.0793529681062109,
1826
+ "grad_norm": 1.5125179888703784,
1827
+ "learning_rate": 9.936767614806612e-06,
1828
+ "loss": 0.3674,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.07965817182969633,
1833
+ "grad_norm": 1.5026525250547669,
1834
+ "learning_rate": 9.935981365623516e-06,
1835
+ "loss": 0.4103,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.07996337555318175,
1840
+ "grad_norm": 2.3948536293362115,
1841
+ "learning_rate": 9.93519028986839e-06,
1842
+ "loss": 0.4009,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.08026857927666718,
1847
+ "grad_norm": 2.416554371647352,
1848
+ "learning_rate": 9.934394388314775e-06,
1849
+ "loss": 0.4265,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.0805737830001526,
1854
+ "grad_norm": 1.560923734953618,
1855
+ "learning_rate": 9.933593661740933e-06,
1856
+ "loss": 0.303,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.08087898672363802,
1861
+ "grad_norm": 1.6053945705234087,
1862
+ "learning_rate": 9.932788110929837e-06,
1863
+ "loss": 0.3295,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.08118419044712345,
1868
+ "grad_norm": 1.7775437462596928,
1869
+ "learning_rate": 9.931977736669185e-06,
1870
+ "loss": 0.2197,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.08148939417060888,
1875
+ "grad_norm": 1.701318325041301,
1876
+ "learning_rate": 9.931162539751392e-06,
1877
+ "loss": 0.3581,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.08179459789409431,
1882
+ "grad_norm": 1.5974548511363529,
1883
+ "learning_rate": 9.93034252097358e-06,
1884
+ "loss": 0.3432,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.08209980161757974,
1889
+ "grad_norm": 1.8669593065073864,
1890
+ "learning_rate": 9.929517681137594e-06,
1891
+ "loss": 0.4133,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.08240500534106517,
1896
+ "grad_norm": 1.4895827642408586,
1897
+ "learning_rate": 9.928688021049991e-06,
1898
+ "loss": 0.3111,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.0827102090645506,
1903
+ "grad_norm": 1.4317804244871846,
1904
+ "learning_rate": 9.927853541522041e-06,
1905
+ "loss": 0.2915,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.08301541278803601,
1910
+ "grad_norm": 1.252478145781798,
1911
+ "learning_rate": 9.927014243369727e-06,
1912
+ "loss": 0.2794,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.08332061651152144,
1917
+ "grad_norm": 1.6973954865497314,
1918
+ "learning_rate": 9.926170127413743e-06,
1919
+ "loss": 0.6183,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.08362582023500686,
1924
+ "grad_norm": 1.4723277244112698,
1925
+ "learning_rate": 9.925321194479494e-06,
1926
+ "loss": 0.2815,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.08393102395849229,
1931
+ "grad_norm": 1.7075555550514414,
1932
+ "learning_rate": 9.924467445397097e-06,
1933
+ "loss": 0.4178,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.08423622768197772,
1938
+ "grad_norm": 1.5354808046910606,
1939
+ "learning_rate": 9.923608881001377e-06,
1940
+ "loss": 0.2355,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.08454143140546315,
1945
+ "grad_norm": 1.1795750747565834,
1946
+ "learning_rate": 9.922745502131865e-06,
1947
+ "loss": 0.3404,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.08484663512894858,
1952
+ "grad_norm": 1.427067758888222,
1953
+ "learning_rate": 9.921877309632805e-06,
1954
+ "loss": 0.3141,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.085151838852434,
1959
+ "grad_norm": 1.3691564278772157,
1960
+ "learning_rate": 9.921004304353147e-06,
1961
+ "loss": 0.287,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.08545704257591942,
1966
+ "grad_norm": 1.9220775714586407,
1967
+ "learning_rate": 9.920126487146544e-06,
1968
+ "loss": 0.6617,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.08576224629940485,
1973
+ "grad_norm": 1.6761030408371134,
1974
+ "learning_rate": 9.919243858871355e-06,
1975
+ "loss": 0.466,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.08606745002289028,
1980
+ "grad_norm": 1.6120747264173168,
1981
+ "learning_rate": 9.918356420390645e-06,
1982
+ "loss": 0.5351,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.0863726537463757,
1987
+ "grad_norm": 1.5236961732014556,
1988
+ "learning_rate": 9.91746417257218e-06,
1989
+ "loss": 0.33,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.08667785746986113,
1994
+ "grad_norm": 1.6328635321860312,
1995
+ "learning_rate": 9.916567116288434e-06,
1996
+ "loss": 0.4301,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.08698306119334656,
2001
+ "grad_norm": 1.4120804188821041,
2002
+ "learning_rate": 9.915665252416577e-06,
2003
+ "loss": 0.3025,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.08728826491683199,
2008
+ "grad_norm": 1.8410843798908767,
2009
+ "learning_rate": 9.914758581838482e-06,
2010
+ "loss": 0.5415,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.08759346864031742,
2015
+ "grad_norm": 1.1807475096034001,
2016
+ "learning_rate": 9.913847105440725e-06,
2017
+ "loss": 0.3184,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.08789867236380283,
2022
+ "grad_norm": 1.52681276111022,
2023
+ "learning_rate": 9.912930824114577e-06,
2024
+ "loss": 0.4266,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.08820387608728826,
2029
+ "grad_norm": 1.4904538614169496,
2030
+ "learning_rate": 9.91200973875601e-06,
2031
+ "loss": 0.3404,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.08850907981077369,
2036
+ "grad_norm": 1.7385111110311349,
2037
+ "learning_rate": 9.911083850265692e-06,
2038
+ "loss": 0.3371,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.08881428353425912,
2043
+ "grad_norm": 1.6013762575114376,
2044
+ "learning_rate": 9.91015315954899e-06,
2045
+ "loss": 0.4475,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.08911948725774455,
2050
+ "grad_norm": 1.5474202900018152,
2051
+ "learning_rate": 9.909217667515964e-06,
2052
+ "loss": 0.4162,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.08942469098122997,
2057
+ "grad_norm": 1.875769203080621,
2058
+ "learning_rate": 9.908277375081371e-06,
2059
+ "loss": 0.4446,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.0897298947047154,
2064
+ "grad_norm": 1.4914731218024286,
2065
+ "learning_rate": 9.907332283164663e-06,
2066
+ "loss": 0.4274,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.09003509842820083,
2071
+ "grad_norm": 1.6551811079983538,
2072
+ "learning_rate": 9.90638239268998e-06,
2073
+ "loss": 0.4883,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.09034030215168624,
2078
+ "grad_norm": 1.645510927644492,
2079
+ "learning_rate": 9.905427704586158e-06,
2080
+ "loss": 0.4885,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.09064550587517167,
2085
+ "grad_norm": 1.6759165462483547,
2086
+ "learning_rate": 9.904468219786727e-06,
2087
+ "loss": 0.3878,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.0909507095986571,
2092
+ "grad_norm": 1.596800484010474,
2093
+ "learning_rate": 9.903503939229901e-06,
2094
+ "loss": 0.2725,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.09125591332214253,
2099
+ "grad_norm": 1.4035704196730787,
2100
+ "learning_rate": 9.902534863858588e-06,
2101
+ "loss": 0.2147,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.09156111704562796,
2106
+ "grad_norm": 1.7460761357385464,
2107
+ "learning_rate": 9.90156099462038e-06,
2108
+ "loss": 0.3495,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.09186632076911339,
2113
+ "grad_norm": 1.3373562156184522,
2114
+ "learning_rate": 9.900582332467566e-06,
2115
+ "loss": 0.342,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.09217152449259881,
2120
+ "grad_norm": 1.1466755748188362,
2121
+ "learning_rate": 9.89959887835711e-06,
2122
+ "loss": 0.1737,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.09247672821608424,
2127
+ "grad_norm": 1.8078659273922337,
2128
+ "learning_rate": 9.898610633250669e-06,
2129
+ "loss": 0.3111,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.09278193193956966,
2134
+ "grad_norm": 1.5400638324339648,
2135
+ "learning_rate": 9.897617598114584e-06,
2136
+ "loss": 0.4746,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.09308713566305508,
2141
+ "grad_norm": 1.558728128630052,
2142
+ "learning_rate": 9.896619773919878e-06,
2143
+ "loss": 0.3085,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.09339233938654051,
2148
+ "grad_norm": 4.094736926672729,
2149
+ "learning_rate": 9.895617161642257e-06,
2150
+ "loss": 0.4664,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.09369754311002594,
2155
+ "grad_norm": 1.63116898024897,
2156
+ "learning_rate": 9.89460976226211e-06,
2157
+ "loss": 0.3878,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.09400274683351137,
2162
+ "grad_norm": 1.7238364123731507,
2163
+ "learning_rate": 9.893597576764508e-06,
2164
+ "loss": 0.2989,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.0943079505569968,
2169
+ "grad_norm": 1.2496662648050174,
2170
+ "learning_rate": 9.8925806061392e-06,
2171
+ "loss": 0.3054,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.09461315428048223,
2176
+ "grad_norm": 0.8807197003313585,
2177
+ "learning_rate": 9.891558851380614e-06,
2178
+ "loss": 0.1904,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.09491835800396765,
2183
+ "grad_norm": 1.5076918479598347,
2184
+ "learning_rate": 9.890532313487858e-06,
2185
+ "loss": 0.2679,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.09522356172745307,
2190
+ "grad_norm": 1.8465691043660122,
2191
+ "learning_rate": 9.889500993464716e-06,
2192
+ "loss": 0.5002,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.0955287654509385,
2197
+ "grad_norm": 1.9183643810942494,
2198
+ "learning_rate": 9.888464892319647e-06,
2199
+ "loss": 0.4869,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.09583396917442392,
2204
+ "grad_norm": 1.6515373264151805,
2205
+ "learning_rate": 9.887424011065788e-06,
2206
+ "loss": 0.4507,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.09613917289790935,
2211
+ "grad_norm": 1.6223391241834122,
2212
+ "learning_rate": 9.886378350720945e-06,
2213
+ "loss": 0.3445,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.09644437662139478,
2218
+ "grad_norm": 1.4416645097808285,
2219
+ "learning_rate": 9.885327912307604e-06,
2220
+ "loss": 0.2808,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.09674958034488021,
2225
+ "grad_norm": 1.4777192121308136,
2226
+ "learning_rate": 9.88427269685292e-06,
2227
+ "loss": 0.4335,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.09705478406836564,
2232
+ "grad_norm": 1.6934694740555867,
2233
+ "learning_rate": 9.883212705388715e-06,
2234
+ "loss": 0.4299,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.09735998779185107,
2239
+ "grad_norm": 1.9031284601590377,
2240
+ "learning_rate": 9.882147938951489e-06,
2241
+ "loss": 0.5364,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.09766519151533648,
2246
+ "grad_norm": 1.990035566558448,
2247
+ "learning_rate": 9.881078398582406e-06,
2248
+ "loss": 0.6476,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.09797039523882191,
2253
+ "grad_norm": 1.4458600630840748,
2254
+ "learning_rate": 9.8800040853273e-06,
2255
+ "loss": 0.268,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.09827559896230734,
2260
+ "grad_norm": 1.473557254783057,
2261
+ "learning_rate": 9.878925000236667e-06,
2262
+ "loss": 0.3889,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.09858080268579276,
2267
+ "grad_norm": 1.429462352597184,
2268
+ "learning_rate": 9.877841144365681e-06,
2269
+ "loss": 0.3348,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.0988860064092782,
2274
+ "grad_norm": 1.9126483909533352,
2275
+ "learning_rate": 9.876752518774167e-06,
2276
+ "loss": 0.5004,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.09919121013276362,
2281
+ "grad_norm": 1.528278815830415,
2282
+ "learning_rate": 9.875659124526622e-06,
2283
+ "loss": 0.1931,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.09949641385624905,
2288
+ "grad_norm": 1.6064809314060318,
2289
+ "learning_rate": 9.874560962692207e-06,
2290
+ "loss": 0.2627,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.09980161757973448,
2295
+ "grad_norm": 1.8583002911468363,
2296
+ "learning_rate": 9.873458034344741e-06,
2297
+ "loss": 0.4795,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.1001068213032199,
2302
+ "grad_norm": 2.180040993961252,
2303
+ "learning_rate": 9.872350340562704e-06,
2304
+ "loss": 0.3502,
2305
+ "step": 328
2306
+ }
2307
+ ],
2308
+ "logging_steps": 1.0,
2309
+ "max_steps": 3276,
2310
+ "num_input_tokens_seen": 0,
2311
+ "num_train_epochs": 1,
2312
+ "save_steps": 328,
2313
+ "total_flos": 40670334410752.0,
2314
+ "train_batch_size": 2,
2315
+ "trial_name": null,
2316
+ "trial_params": null
2317
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b4aa33f55e48e79da409167c0502ab30cbbfa7d18bea5b24f75297f9188653
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)