Hugging Face's logo

Perflow-Shuai
/
NVILA-8B-longvila-256frames-model

Safetensors
llava_llama
Model card Files
xet
 Community
Yukang Chen commited on
Commit
2245ec7
·
1 Parent(s): 64221f3

Initial commit for NVILA-8B-longvila-256frames

Browse files
Files changed (21) hide show
  1. .gitattributes +1 -0
  2. .gitignore +5 -0
  3. config.json +322 -0
  4. llm/added_tokens.json +10 -0
  5. llm/config.json +32 -0
  6. llm/generation_config.json +14 -0
  7. llm/merges.txt +0 -0
  8. llm/model-00001-of-00004.safetensors +3 -0
  9. llm/model-00002-of-00004.safetensors +3 -0
  10. llm/model-00003-of-00004.safetensors +3 -0
  11. llm/model-00004-of-00004.safetensors +3 -0
  12. llm/model.safetensors.index.json +346 -0
  13. llm/special_tokens_map.json +30 -0
  14. llm/tokenizer_config.json +88 -0
  15. llm/vocab.json +0 -0
  16. mm_projector/config.json +10 -0
  17. mm_projector/model.safetensors +3 -0
  18. trainer_state.json +1512 -0
  19. vision_tower/config.json +23 -0
  20. vision_tower/model.safetensors +3 -0
  21. vision_tower/preprocessor_config.json +24 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.wandb filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ wandb/
2
+ logs/
3
+ *.wandb
4
+ *.tmp
5
+
config.json ADDED
@@ -0,0 +1,322 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Ubit": 100,
3
+ "_attn_implementation_autoset": true,
4
+ "_name_or_path": "./output/NVILA-8B-longvila-256frames",
5
+ "architectures": [
6
+ "LlavaLlamaModel"
7
+ ],
8
+ "babit": "E5M2",
9
+ "bobit": "E5M2",
10
+ "bwbit": "E5M2",
11
+ "chat_template": null,
12
+ "col_blocksize": -1,
13
+ "col_blocksize_optimizer": 128,
14
+ "draw_distribution_backward": false,
15
+ "draw_distribution_forward": false,
16
+ "drop_path_rate": 0.0,
17
+ "dynamic_s2": true,
18
+ "epsilon": 1e-10,
19
+ "epsilon_optimizer": 1e-15,
20
+ "fabit": "E4M3",
21
+ "first_order_bit": null,
22
+ "first_order_quant_type": null,
23
+ "fobit": "E4M3",
24
+ "fps": 2.0,
25
+ "fwbit": "E4M3",
26
+ "group_size": -1,
27
+ "hidden_size": 3584,
28
+ "image_aspect_ratio": "dynamic_s2",
29
+ "image_encoder": {
30
+ "_target_": "llava.model.encoders.BasicImageEncoder"
31
+ },
32
+ "interpolate_mode": "linear",
33
+ "llm_cfg": {
34
+ "_attn_implementation_autoset": false,
35
+ "_name_or_path": "./output/NVILA-8B-longvila-256frames/llm",
36
+ "add_cross_attention": false,
37
+ "architectures": [
38
+ "Qwen2ForCausalLM"
39
+ ],
40
+ "attention_dropout": 0.0,
41
+ "bad_words_ids": null,
42
+ "begin_suppress_tokens": null,
43
+ "bos_token_id": 151643,
44
+ "chunk_size_feed_forward": 0,
45
+ "cross_attention_hidden_size": null,
46
+ "decoder_start_token_id": null,
47
+ "diversity_penalty": 0.0,
48
+ "do_sample": false,
49
+ "early_stopping": false,
50
+ "encoder_no_repeat_ngram_size": 0,
51
+ "eos_token_id": 151645,
52
+ "exponential_decay_length_penalty": null,
53
+ "finetuning_task": null,
54
+ "forced_bos_token_id": null,
55
+ "forced_eos_token_id": null,
56
+ "hidden_act": "silu",
57
+ "hidden_size": 3584,
58
+ "id2label": {
59
+ "0": "LABEL_0",
60
+ "1": "LABEL_1"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 18944,
64
+ "is_decoder": false,
65
+ "is_encoder_decoder": false,
66
+ "label2id": {
67
+ "LABEL_0": 0,
68
+ "LABEL_1": 1
69
+ },
70
+ "length_penalty": 1.0,
71
+ "max_length": 20,
72
+ "max_position_embeddings": 131072,
73
+ "max_window_layers": 28,
74
+ "min_length": 0,
75
+ "model_max_length": 131072,
76
+ "model_type": "qwen2",
77
+ "no_repeat_ngram_size": 0,
78
+ "num_attention_heads": 28,
79
+ "num_beam_groups": 1,
80
+ "num_beams": 1,
81
+ "num_hidden_layers": 28,
82
+ "num_key_value_heads": 4,
83
+ "num_return_sequences": 1,
84
+ "output_attentions": false,
85
+ "output_hidden_states": false,
86
+ "output_scores": false,
87
+ "pad_token_id": null,
88
+ "prefix": null,
89
+ "problem_type": null,
90
+ "pruned_heads": {},
91
+ "remove_invalid_values": false,
92
+ "repetition_penalty": 1.0,
93
+ "return_dict": true,
94
+ "return_dict_in_generate": false,
95
+ "rms_norm_eps": 1e-06,
96
+ "rope_scaling": null,
97
+ "rope_theta": 15300000,
98
+ "sep_token_id": null,
99
+ "sliding_window": null,
100
+ "suppress_tokens": null,
101
+ "task_specific_params": null,
102
+ "temperature": 1.0,
103
+ "tf_legacy_loss": false,
104
+ "tie_encoder_decoder": false,
105
+ "tie_word_embeddings": false,
106
+ "tokenizer_class": null,
107
+ "tokenizer_model_max_length": 131072,
108
+ "tokenizer_padding_side": "right",
109
+ "top_k": 50,
110
+ "top_p": 1.0,
111
+ "torch_dtype": "bfloat16",
112
+ "torchscript": false,
113
+ "typical_p": 1.0,
114
+ "use_bfloat16": false,
115
+ "use_cache": true,
116
+ "use_sliding_window": false,
117
+ "vocab_size": 151651
118
+ },
119
+ "max_tiles": 12,
120
+ "min_blockunit_col": 4,
121
+ "min_blockunit_row": 4,
122
+ "min_tiles": 1,
123
+ "mlp_path": null,
124
+ "mm_hidden_size": 3456,
125
+ "mm_projector": "mlp_downsample",
126
+ "mm_projector_cfg": {
127
+ "_attn_implementation_autoset": false,
128
+ "_name_or_path": "./output/NVILA-8B-longvila-256frames/mm_projector",
129
+ "add_cross_attention": false,
130
+ "architectures": [
131
+ "MultimodalProjector"
132
+ ],
133
+ "bad_words_ids": null,
134
+ "begin_suppress_tokens": null,
135
+ "bos_token_id": null,
136
+ "chunk_size_feed_forward": 0,
137
+ "cross_attention_hidden_size": null,
138
+ "decoder_start_token_id": null,
139
+ "diversity_penalty": 0.0,
140
+ "do_sample": false,
141
+ "early_stopping": false,
142
+ "encoder_no_repeat_ngram_size": 0,
143
+ "eos_token_id": null,
144
+ "exponential_decay_length_penalty": null,
145
+ "finetuning_task": null,
146
+ "forced_bos_token_id": null,
147
+ "forced_eos_token_id": null,
148
+ "id2label": {
149
+ "0": "LABEL_0",
150
+ "1": "LABEL_1"
151
+ },
152
+ "is_decoder": false,
153
+ "is_encoder_decoder": false,
154
+ "label2id": {
155
+ "LABEL_0": 0,
156
+ "LABEL_1": 1
157
+ },
158
+ "length_penalty": 1.0,
159
+ "max_length": 20,
160
+ "min_length": 0,
161
+ "mm_projector_type": "mlp_downsample",
162
+ "model_type": "v2l_projector",
163
+ "no_repeat_ngram_size": 0,
164
+ "num_beam_groups": 1,
165
+ "num_beams": 1,
166
+ "num_return_sequences": 1,
167
+ "output_attentions": false,
168
+ "output_hidden_states": false,
169
+ "output_scores": false,
170
+ "pad_token_id": null,
171
+ "prefix": null,
172
+ "problem_type": null,
173
+ "pruned_heads": {},
174
+ "remove_invalid_values": false,
175
+ "repetition_penalty": 1.0,
176
+ "return_dict": true,
177
+ "return_dict_in_generate": false,
178
+ "sep_token_id": null,
179
+ "suppress_tokens": null,
180
+ "task_specific_params": null,
181
+ "temperature": 1.0,
182
+ "tf_legacy_loss": false,
183
+ "tie_encoder_decoder": false,
184
+ "tie_word_embeddings": true,
185
+ "tokenizer_class": null,
186
+ "top_k": 50,
187
+ "top_p": 1.0,
188
+ "torch_dtype": "bfloat16",
189
+ "torchscript": false,
190
+ "typical_p": 1.0,
191
+ "use_bfloat16": false
192
+ },
193
+ "mm_projector_lr": null,
194
+ "mm_use_im_patch_token": false,
195
+ "mm_use_im_start_end": false,
196
+ "mm_vision_select_feature": "cls_patch",
197
+ "mm_vision_select_layer": -2,
198
+ "model_dtype": "torch.bfloat16",
199
+ "model_name_or_path": "/lustre/fsw/portfolios/nvr/users/yukangc/pretrained-models/NVILA-8B-128k",
200
+ "model_type": "llava_llama",
201
+ "num_time_tokens": 0,
202
+ "num_video_frames": 256,
203
+ "pad_block": false,
204
+ "pad_to_multiple_of": 0,
205
+ "qchoice": "none",
206
+ "quantize_model": false,
207
+ "refine_attn_blocksize": false,
208
+ "refine_col_blocksize": 4,
209
+ "refine_ln_blocksize": false,
210
+ "refine_ln_blocksize_but_only_backward": false,
211
+ "refine_ln_blocksize_but_only_forward": false,
212
+ "refine_ln_pertoken": false,
213
+ "refine_mlp_blocksize": false,
214
+ "refine_residual_fp": false,
215
+ "refine_row_blocksize": 4,
216
+ "resume_path": "./output/NVILA-8B-longvila-256frames",
217
+ "row_blocksize": -1,
218
+ "row_blocksize_optimizer": 1,
219
+ "s2": false,
220
+ "s2_max_split_size": 448,
221
+ "s2_resize_output_to_scale_idx": -1,
222
+ "s2_scales": "448,896,1344",
223
+ "second_order_bit": null,
224
+ "second_order_quant_type": null,
225
+ "soft_ce_std": 1.0,
226
+ "symm": true,
227
+ "time_token_format": "<t{t}>",
228
+ "time_token_ids": [],
229
+ "transformers_version": "4.46.0",
230
+ "tune_language_model": true,
231
+ "tune_mm_projector": true,
232
+ "tune_vision_tower": true,
233
+ "use_quantize_optimizer": false,
234
+ "version": "qwen2",
235
+ "video_encoder": {
236
+ "_target_": "llava.model.encoders.BasicVideoEncoder"
237
+ },
238
+ "vision_resolution": -1,
239
+ "vision_tower": "Efficient-Large-Model/paligemma-siglip-so400m-patch14-448",
240
+ "vision_tower_cfg": {
241
+ "_attn_implementation_autoset": false,
242
+ "_name_or_path": "./output/NVILA-8B-longvila-256frames/vision_tower",
243
+ "add_cross_attention": false,
244
+ "architectures": [
245
+ "SiglipVisionModel"
246
+ ],
247
+ "attention_dropout": 0.0,
248
+ "bad_words_ids": null,
249
+ "begin_suppress_tokens": null,
250
+ "bos_token_id": null,
251
+ "chunk_size_feed_forward": 0,
252
+ "cross_attention_hidden_size": null,
253
+ "decoder_start_token_id": null,
254
+ "diversity_penalty": 0.0,
255
+ "do_sample": false,
256
+ "early_stopping": false,
257
+ "encoder_no_repeat_ngram_size": 0,
258
+ "eos_token_id": null,
259
+ "exponential_decay_length_penalty": null,
260
+ "finetuning_task": null,
261
+ "forced_bos_token_id": null,
262
+ "forced_eos_token_id": null,
263
+ "hidden_act": "gelu_pytorch_tanh",
264
+ "hidden_size": 1152,
265
+ "id2label": {
266
+ "0": "LABEL_0",
267
+ "1": "LABEL_1"
268
+ },
269
+ "image_size": 448,
270
+ "intermediate_size": 4304,
271
+ "is_decoder": false,
272
+ "is_encoder_decoder": false,
273
+ "label2id": {
274
+ "LABEL_0": 0,
275
+ "LABEL_1": 1
276
+ },
277
+ "layer_norm_eps": 1e-06,
278
+ "length_penalty": 1.0,
279
+ "max_length": 20,
280
+ "min_length": 0,
281
+ "model_type": "siglip_vision_model",
282
+ "no_repeat_ngram_size": 0,
283
+ "num_attention_heads": 16,
284
+ "num_beam_groups": 1,
285
+ "num_beams": 1,
286
+ "num_channels": 3,
287
+ "num_hidden_layers": 27,
288
+ "num_image_tokens": 256,
289
+ "num_return_sequences": 1,
290
+ "output_attentions": false,
291
+ "output_hidden_states": false,
292
+ "output_scores": false,
293
+ "pad_token_id": null,
294
+ "patch_size": 14,
295
+ "prefix": null,
296
+ "problem_type": null,
297
+ "projection_dim": 2048,
298
+ "projector_hidden_act": "gelu_fast",
299
+ "pruned_heads": {},
300
+ "remove_invalid_values": false,
301
+ "repetition_penalty": 1.0,
302
+ "return_dict": true,
303
+ "return_dict_in_generate": false,
304
+ "sep_token_id": null,
305
+ "suppress_tokens": null,
306
+ "task_specific_params": null,
307
+ "temperature": 1.0,
308
+ "tf_legacy_loss": false,
309
+ "tie_encoder_decoder": false,
310
+ "tie_word_embeddings": true,
311
+ "tokenizer_class": null,
312
+ "top_k": 50,
313
+ "top_p": 1.0,
314
+ "torch_dtype": "bfloat16",
315
+ "torchscript": false,
316
+ "typical_p": 1.0,
317
+ "use_bfloat16": false,
318
+ "vision_use_head": false
319
+ },
320
+ "vision_tower_lr": null,
321
+ "weight_memory_efficient": true
322
+ }
llm/added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151649,
3
+ "<vila/sentinel>": 151648,
4
+ "<vila/video>": 151650,
5
+ "<|endoftext|>": 151643,
6
+ "<|im_end|>": 151645,
7
+ "<|im_start|>": 151644,
8
+ "[BOS]": 151646,
9
+ "[PAD]": 151647
10
+ }
llm/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output/NVILA-8B-longvila-256frames/llm",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 28,
15
+ "model_max_length": 131072,
16
+ "model_type": "qwen2",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 15300000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "tokenizer_model_max_length": 131072,
26
+ "tokenizer_padding_side": "right",
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.46.0",
29
+ "use_cache": true,
30
+ "use_sliding_window": false,
31
+ "vocab_size": 151651
32
+ }
llm/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": "4.46.0"
14
+ }
llm/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
llm/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fad97f4acf07c7fe5fc1f66aedc01b815292a103cde77bdf6081b0243b7fbf5
3
+ size 4874700392
llm/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa748350b597c9b518805e1a7c87d119aa00ee3af8de60899eb2e255bc92d68
3
+ size 4932751008
llm/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff4fade605aff4e85df3816cd4d5df137f272f840ecf09714b769dd355c48481
3
+ size 4330865200
llm/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d943a7c7542fba919b32e6a37e217521f2be3fa7ec6bf4858ab2c8e174ce2836
3
+ size 1087034496
llm/model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15225312256
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.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
+ }
346
+ }
llm/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<vila/sentinel>",
6
+ "<image>",
7
+ "<vila/video>"
8
+ ],
9
+ "bos_token": {
10
+ "content": "[BOS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "<|im_end|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
llm/tokenizer_config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[BOS]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "[PAD]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<vila/sentinel>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<image>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<vila/video>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ }
68
+ },
69
+ "additional_special_tokens": [
70
+ "<|im_start|>",
71
+ "<|im_end|>",
72
+ "<vila/sentinel>",
73
+ "<image>",
74
+ "<vila/video>"
75
+ ],
76
+ "bos_token": "[BOS]",
77
+ "chat_template": "{% if messages[0]['role'] != 'system' %}{{ '<|im_start|>system\\nYou are a helpful assistant<|im_end|>\\n' }}{% endif %}{% for message in messages if message['content'] is not none %}{{ '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
78
+ "clean_up_tokenization_spaces": false,
79
+ "eos_token": "<|im_end|>",
80
+ "errors": "replace",
81
+ "legacy": false,
82
+ "model_max_length": 131072,
83
+ "pad_token": "[PAD]",
84
+ "padding_side": "right",
85
+ "split_special_tokens": false,
86
+ "tokenizer_class": "Qwen2Tokenizer",
87
+ "unk_token": null
88
+ }
llm/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
mm_projector/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output/NVILA-8B-longvila-256frames/mm_projector",
3
+ "architectures": [
4
+ "MultimodalProjector"
5
+ ],
6
+ "mm_projector_type": "mlp_downsample",
7
+ "model_type": "v2l_projector",
8
+ "torch_dtype": "bfloat16",
9
+ "transformers_version": "4.46.0"
10
+ }
mm_projector/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:568ff7bc9c6ccc3921be58d3f681d1dcb7f8a676eb8aac8d568e6ad74d5504b8
3
+ size 124850712
trainer_state.json ADDED
@@ -0,0 +1,1512 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 210,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "grad_norm": 80.00438704007676,
14
+ "learning_rate": 2.8571428571428573e-06,
15
+ "loss": 6.2941,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.06,
20
+ "grad_norm": 96.34802446721417,
21
+ "learning_rate": 5.7142857142857145e-06,
22
+ "loss": 6.8085,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.09,
27
+ "grad_norm": 154.2232661357414,
28
+ "learning_rate": 8.571428571428571e-06,
29
+ "loss": 6.1192,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.11,
34
+ "grad_norm": 23.03476938439163,
35
+ "learning_rate": 1.1428571428571429e-05,
36
+ "loss": 5.4161,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.14,
41
+ "grad_norm": 11.647036257139195,
42
+ "learning_rate": 1.4285714285714287e-05,
43
+ "loss": 5.2596,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.17,
48
+ "grad_norm": 14.698112775361619,
49
+ "learning_rate": 1.7142857142857142e-05,
50
+ "loss": 5.3002,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.2,
55
+ "grad_norm": 23.71107587456011,
56
+ "learning_rate": 2e-05,
57
+ "loss": 4.6473,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.23,
62
+ "grad_norm": 14.120600306959602,
63
+ "learning_rate": 1.9998802517966852e-05,
64
+ "loss": 5.3174,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.26,
69
+ "grad_norm": 8.191706198497702,
70
+ "learning_rate": 1.9995210358660037e-05,
71
+ "loss": 4.9716,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.29,
76
+ "grad_norm": 10.458311244778137,
77
+ "learning_rate": 1.9989224382388813e-05,
78
+ "loss": 4.5338,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.31,
83
+ "grad_norm": 9.213287452666169,
84
+ "learning_rate": 1.9980846022772978e-05,
85
+ "loss": 4.7343,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.34,
90
+ "grad_norm": 5.9009430281116675,
91
+ "learning_rate": 1.997007728639956e-05,
92
+ "loss": 5.0022,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.37,
97
+ "grad_norm": 7.8868800818479174,
98
+ "learning_rate": 1.9956920752342226e-05,
99
+ "loss": 5.0521,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.4,
104
+ "grad_norm": 6.259759634256785,
105
+ "learning_rate": 1.9941379571543597e-05,
106
+ "loss": 4.6051,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.43,
111
+ "grad_norm": 5.579574504065297,
112
+ "learning_rate": 1.9923457466060637e-05,
113
+ "loss": 4.2182,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.46,
118
+ "grad_norm": 5.913831283576424,
119
+ "learning_rate": 1.9903158728173206e-05,
120
+ "loss": 4.2917,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.49,
125
+ "grad_norm": 7.717836608401082,
126
+ "learning_rate": 1.9880488219356086e-05,
127
+ "loss": 4.3894,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.51,
132
+ "grad_norm": 6.296015368993091,
133
+ "learning_rate": 1.9855451369114677e-05,
134
+ "loss": 4.3322,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.54,
139
+ "grad_norm": 8.475421651603199,
140
+ "learning_rate": 1.9828054173684646e-05,
141
+ "loss": 4.6874,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.57,
146
+ "grad_norm": 8.452753919149812,
147
+ "learning_rate": 1.9798303194595846e-05,
148
+ "loss": 4.3446,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.6,
153
+ "grad_norm": 5.716694629623973,
154
+ "learning_rate": 1.976620555710087e-05,
155
+ "loss": 4.0236,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.63,
160
+ "grad_norm": 6.3915589352407345,
161
+ "learning_rate": 1.973176894846855e-05,
162
+ "loss": 4.4564,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.66,
167
+ "grad_norm": 3.849187023823461,
168
+ "learning_rate": 1.9695001616142916e-05,
169
+ "loss": 3.9989,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.69,
174
+ "grad_norm": 6.228918174540112,
175
+ "learning_rate": 1.965591236576794e-05,
176
+ "loss": 4.3524,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.71,
181
+ "grad_norm": 5.974882597027604,
182
+ "learning_rate": 1.9614510559078626e-05,
183
+ "loss": 4.1009,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.74,
188
+ "grad_norm": 4.926401136001884,
189
+ "learning_rate": 1.95708061116589e-05,
190
+ "loss": 4.216,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.77,
195
+ "grad_norm": 5.034835120114335,
196
+ "learning_rate": 1.9524809490566878e-05,
197
+ "loss": 4.3396,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.8,
202
+ "grad_norm": 4.643514172374943,
203
+ "learning_rate": 1.9476531711828027e-05,
204
+ "loss": 4.0161,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.83,
209
+ "grad_norm": 4.210788851218648,
210
+ "learning_rate": 1.942598433779687e-05,
211
+ "loss": 4.5483,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.86,
216
+ "grad_norm": 4.684561962496697,
217
+ "learning_rate": 1.9373179474387858e-05,
218
+ "loss": 4.3755,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.89,
223
+ "grad_norm": 4.673387982745991,
224
+ "learning_rate": 1.9318129768176033e-05,
225
+ "loss": 4.4423,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.91,
230
+ "grad_norm": 4.990722772080045,
231
+ "learning_rate": 1.926084840336821e-05,
232
+ "loss": 4.3072,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.94,
237
+ "grad_norm": 4.9483245517186605,
238
+ "learning_rate": 1.9201349098645433e-05,
239
+ "loss": 4.2863,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.97,
244
+ "grad_norm": 4.427315167497816,
245
+ "learning_rate": 1.9139646103877378e-05,
246
+ "loss": 4.1236,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.0,
251
+ "grad_norm": 4.922455864121031,
252
+ "learning_rate": 1.9075754196709574e-05,
253
+ "loss": 4.7598,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.03,
258
+ "grad_norm": 4.123279198243713,
259
+ "learning_rate": 1.900968867902419e-05,
260
+ "loss": 3.8454,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.06,
265
+ "grad_norm": 4.251851688874165,
266
+ "learning_rate": 1.894146537327533e-05,
267
+ "loss": 4.1765,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.09,
272
+ "grad_norm": 4.440763895011154,
273
+ "learning_rate": 1.8871100618699553e-05,
274
+ "loss": 4.5498,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.11,
279
+ "grad_norm": 4.359765853893123,
280
+ "learning_rate": 1.8798611267402745e-05,
281
+ "loss": 4.5428,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.14,
286
+ "grad_norm": 5.0972668892147475,
287
+ "learning_rate": 1.872401468032406e-05,
288
+ "loss": 4.5734,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.17,
293
+ "grad_norm": 5.452699114764846,
294
+ "learning_rate": 1.864732872307804e-05,
295
+ "loss": 4.083,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.2,
300
+ "grad_norm": 3.6602209793027534,
301
+ "learning_rate": 1.8568571761675893e-05,
302
+ "loss": 3.8202,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.23,
307
+ "grad_norm": 4.930178982421816,
308
+ "learning_rate": 1.8487762658126872e-05,
309
+ "loss": 4.2528,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.26,
314
+ "grad_norm": 4.407664636029237,
315
+ "learning_rate": 1.8404920765920898e-05,
316
+ "loss": 3.8699,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.29,
321
+ "grad_norm": 4.78545005474896,
322
+ "learning_rate": 1.8320065925393468e-05,
323
+ "loss": 3.6822,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.31,
328
+ "grad_norm": 4.078401960467532,
329
+ "learning_rate": 1.8233218458973984e-05,
330
+ "loss": 3.7794,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.34,
335
+ "grad_norm": 5.326820494758211,
336
+ "learning_rate": 1.814439916631857e-05,
337
+ "loss": 3.7876,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.37,
342
+ "grad_norm": 6.378382372761396,
343
+ "learning_rate": 1.8053629319328662e-05,
344
+ "loss": 3.9788,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.4,
349
+ "grad_norm": 5.750592810925643,
350
+ "learning_rate": 1.796093065705644e-05,
351
+ "loss": 3.6474,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.43,
356
+ "grad_norm": 3.8174994985593544,
357
+ "learning_rate": 1.786632538049842e-05,
358
+ "loss": 3.3771,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.46,
363
+ "grad_norm": 5.557487394414142,
364
+ "learning_rate": 1.776983614727838e-05,
365
+ "loss": 3.3717,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.49,
370
+ "grad_norm": 4.074429527562,
371
+ "learning_rate": 1.7671486066220965e-05,
372
+ "loss": 3.5966,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 1.51,
377
+ "grad_norm": 4.063021464956913,
378
+ "learning_rate": 1.757129869181718e-05,
379
+ "loss": 3.507,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 1.54,
384
+ "grad_norm": 4.894442593636845,
385
+ "learning_rate": 1.746929801858317e-05,
386
+ "loss": 3.9196,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 1.57,
391
+ "grad_norm": 4.452722126818571,
392
+ "learning_rate": 1.736550847531366e-05,
393
+ "loss": 3.6257,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 1.6,
398
+ "grad_norm": 4.00522098752344,
399
+ "learning_rate": 1.725995491923131e-05,
400
+ "loss": 3.3246,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.63,
405
+ "grad_norm": 4.25230998576677,
406
+ "learning_rate": 1.7152662630033506e-05,
407
+ "loss": 3.6398,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 1.66,
412
+ "grad_norm": 4.089951263233628,
413
+ "learning_rate": 1.7043657303837965e-05,
414
+ "loss": 3.1908,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 1.69,
419
+ "grad_norm": 5.72352434378825,
420
+ "learning_rate": 1.693296504702862e-05,
421
+ "loss": 3.5252,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.71,
426
+ "grad_norm": 5.160209312433058,
427
+ "learning_rate": 1.682061237000322e-05,
428
+ "loss": 3.4718,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.74,
433
+ "grad_norm": 5.488539699634776,
434
+ "learning_rate": 1.6706626180824185e-05,
435
+ "loss": 3.4474,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.77,
440
+ "grad_norm": 4.42082715558397,
441
+ "learning_rate": 1.659103377877423e-05,
442
+ "loss": 3.4319,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 1.8,
447
+ "grad_norm": 5.021528964342142,
448
+ "learning_rate": 1.647386284781828e-05,
449
+ "loss": 3.2333,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 1.83,
454
+ "grad_norm": 4.771790748100547,
455
+ "learning_rate": 1.6355141449973254e-05,
456
+ "loss": 3.5741,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 1.86,
461
+ "grad_norm": 4.315875791980731,
462
+ "learning_rate": 1.6234898018587336e-05,
463
+ "loss": 3.565,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 1.89,
468
+ "grad_norm": 4.243056541134396,
469
+ "learning_rate": 1.611316135153026e-05,
470
+ "loss": 3.5365,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 1.91,
475
+ "grad_norm": 4.346968517779339,
476
+ "learning_rate": 1.598996060429634e-05,
477
+ "loss": 3.5757,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 1.94,
482
+ "grad_norm": 4.884427461945468,
483
+ "learning_rate": 1.586532528302183e-05,
484
+ "loss": 3.5492,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 1.97,
489
+ "grad_norm": 4.5157468490886785,
490
+ "learning_rate": 1.5739285237418323e-05,
491
+ "loss": 3.3304,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.0,
496
+ "grad_norm": 5.070256806343138,
497
+ "learning_rate": 1.5611870653623826e-05,
498
+ "loss": 3.9314,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.03,
503
+ "grad_norm": 3.6449860141474963,
504
+ "learning_rate": 1.548311204697331e-05,
505
+ "loss": 3.1916,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.06,
510
+ "grad_norm": 4.255978041595801,
511
+ "learning_rate": 1.5353040254690396e-05,
512
+ "loss": 3.4329,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.09,
517
+ "grad_norm": 5.139952618469592,
518
+ "learning_rate": 1.5221686428501929e-05,
519
+ "loss": 3.6179,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.11,
524
+ "grad_norm": 4.605357638561885,
525
+ "learning_rate": 1.5089082027177291e-05,
526
+ "loss": 3.6597,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.14,
531
+ "grad_norm": 6.077382699948124,
532
+ "learning_rate": 1.4955258808994096e-05,
533
+ "loss": 3.6931,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.17,
538
+ "grad_norm": 5.497332973780629,
539
+ "learning_rate": 1.4820248824132221e-05,
540
+ "loss": 4.3554,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.2,
545
+ "grad_norm": 5.805455693303122,
546
+ "learning_rate": 1.4684084406997903e-05,
547
+ "loss": 4.3734,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.23,
552
+ "grad_norm": 5.457678962357698,
553
+ "learning_rate": 1.4546798168479756e-05,
554
+ "loss": 4.4448,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 2.26,
559
+ "grad_norm": 4.520222765843399,
560
+ "learning_rate": 1.4408422988138585e-05,
561
+ "loss": 4.347,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 2.29,
566
+ "grad_norm": 5.401119547471518,
567
+ "learning_rate": 1.4268992006332847e-05,
568
+ "loss": 4.5233,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 2.31,
573
+ "grad_norm": 6.4460955298094955,
574
+ "learning_rate": 1.412853861628166e-05,
575
+ "loss": 3.1766,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 2.34,
580
+ "grad_norm": 5.789832740451367,
581
+ "learning_rate": 1.3987096456067236e-05,
582
+ "loss": 3.3281,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 2.37,
587
+ "grad_norm": 4.998279839354735,
588
+ "learning_rate": 1.3844699400578696e-05,
589
+ "loss": 3.378,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 2.4,
594
+ "grad_norm": 4.615720057294197,
595
+ "learning_rate": 1.3701381553399147e-05,
596
+ "loss": 3.0408,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 2.43,
601
+ "grad_norm": 4.469304200887987,
602
+ "learning_rate": 1.3557177238637987e-05,
603
+ "loss": 2.7044,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 2.46,
608
+ "grad_norm": 4.222990961364449,
609
+ "learning_rate": 1.3412120992710425e-05,
610
+ "loss": 2.8298,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 2.49,
615
+ "grad_norm": 4.805325799209531,
616
+ "learning_rate": 1.3266247556066122e-05,
617
+ "loss": 2.7601,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 2.51,
622
+ "grad_norm": 5.480294735880267,
623
+ "learning_rate": 1.3119591864868979e-05,
624
+ "loss": 2.7043,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 2.54,
629
+ "grad_norm": 5.768438764027398,
630
+ "learning_rate": 1.2972189042630044e-05,
631
+ "loss": 3.0128,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 2.57,
636
+ "grad_norm": 6.141508752253715,
637
+ "learning_rate": 1.2824074391795571e-05,
638
+ "loss": 2.7125,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 2.6,
643
+ "grad_norm": 5.6316708738751435,
644
+ "learning_rate": 1.2675283385292212e-05,
645
+ "loss": 2.6139,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 2.63,
650
+ "grad_norm": 5.679660349214387,
651
+ "learning_rate": 1.252585165803135e-05,
652
+ "loss": 2.7675,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 2.66,
657
+ "grad_norm": 5.145903533309325,
658
+ "learning_rate": 1.2375814998374714e-05,
659
+ "loss": 2.6252,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 2.69,
664
+ "grad_norm": 5.421011319827069,
665
+ "learning_rate": 1.2225209339563144e-05,
666
+ "loss": 2.8014,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 2.71,
671
+ "grad_norm": 5.468955060971493,
672
+ "learning_rate": 1.2074070751110752e-05,
673
+ "loss": 2.837,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 2.74,
678
+ "grad_norm": 5.164937111950548,
679
+ "learning_rate": 1.192243543016637e-05,
680
+ "loss": 2.8372,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 2.77,
685
+ "grad_norm": 5.180488985174343,
686
+ "learning_rate": 1.1770339692844484e-05,
687
+ "loss": 2.547,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 2.8,
692
+ "grad_norm": 6.006405690750611,
693
+ "learning_rate": 1.161781996552765e-05,
694
+ "loss": 2.5804,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 2.83,
699
+ "grad_norm": 5.952437046746775,
700
+ "learning_rate": 1.1464912776142494e-05,
701
+ "loss": 2.7432,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 2.86,
706
+ "grad_norm": 5.094786893941399,
707
+ "learning_rate": 1.1311654745411424e-05,
708
+ "loss": 2.6715,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 2.89,
713
+ "grad_norm": 5.351854924535129,
714
+ "learning_rate": 1.115808257808209e-05,
715
+ "loss": 2.5912,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 2.91,
720
+ "grad_norm": 5.278029090648024,
721
+ "learning_rate": 1.1004233054136726e-05,
722
+ "loss": 2.7294,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 2.94,
727
+ "grad_norm": 5.602710570648003,
728
+ "learning_rate": 1.0850143019983475e-05,
729
+ "loss": 2.8212,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 2.97,
734
+ "grad_norm": 5.203710653440999,
735
+ "learning_rate": 1.0695849379631813e-05,
736
+ "loss": 2.6128,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 3.0,
741
+ "grad_norm": 5.712401092804933,
742
+ "learning_rate": 1.0541389085854177e-05,
743
+ "loss": 3.1367,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 3.03,
748
+ "grad_norm": 4.625678226976654,
749
+ "learning_rate": 1.038679913133589e-05,
750
+ "loss": 2.4625,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 3.06,
755
+ "grad_norm": 4.945017754425003,
756
+ "learning_rate": 1.0232116539815558e-05,
757
+ "loss": 2.6775,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 3.09,
762
+ "grad_norm": 5.317308116977884,
763
+ "learning_rate": 1.0077378357218022e-05,
764
+ "loss": 2.8065,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 3.11,
769
+ "grad_norm": 5.417094774783667,
770
+ "learning_rate": 9.92262164278198e-06,
771
+ "loss": 2.8207,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 3.14,
776
+ "grad_norm": 5.470263884411447,
777
+ "learning_rate": 9.767883460184444e-06,
778
+ "loss": 2.9305,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 3.17,
783
+ "grad_norm": 5.098945198369544,
784
+ "learning_rate": 9.613200868664112e-06,
785
+ "loss": 3.4538,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 3.2,
790
+ "grad_norm": 6.026048110076312,
791
+ "learning_rate": 9.458610914145826e-06,
792
+ "loss": 3.506,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 3.23,
797
+ "grad_norm": 5.820084192866225,
798
+ "learning_rate": 9.304150620368189e-06,
799
+ "loss": 3.847,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 3.26,
804
+ "grad_norm": 5.454079563635766,
805
+ "learning_rate": 9.149856980016529e-06,
806
+ "loss": 3.6699,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 3.29,
811
+ "grad_norm": 4.856647591410433,
812
+ "learning_rate": 8.995766945863278e-06,
813
+ "loss": 3.9941,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 3.31,
818
+ "grad_norm": 5.445692392998836,
819
+ "learning_rate": 8.841917421917913e-06,
820
+ "loss": 4.3554,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 3.34,
825
+ "grad_norm": 5.084555008534811,
826
+ "learning_rate": 8.688345254588579e-06,
827
+ "loss": 4.3838,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 3.37,
832
+ "grad_norm": 4.985430311007982,
833
+ "learning_rate": 8.53508722385751e-06,
834
+ "loss": 4.5445,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 3.4,
839
+ "grad_norm": 3.943933363518215,
840
+ "learning_rate": 8.382180034472353e-06,
841
+ "loss": 4.2051,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 3.43,
846
+ "grad_norm": 4.491172285358988,
847
+ "learning_rate": 8.229660307155518e-06,
848
+ "loss": 4.498,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 3.46,
853
+ "grad_norm": 6.770327191921559,
854
+ "learning_rate": 8.077564569833633e-06,
855
+ "loss": 2.5859,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 3.49,
860
+ "grad_norm": 6.344093649426968,
861
+ "learning_rate": 7.92592924888925e-06,
862
+ "loss": 2.6089,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 3.51,
867
+ "grad_norm": 5.542543063619591,
868
+ "learning_rate": 7.774790660436857e-06,
869
+ "loss": 2.5915,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 3.54,
874
+ "grad_norm": 5.620129695091442,
875
+ "learning_rate": 7.6241850016252915e-06,
876
+ "loss": 2.7973,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 3.57,
881
+ "grad_norm": 4.937221142463724,
882
+ "learning_rate": 7.4741483419686525e-06,
883
+ "loss": 2.4647,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 3.6,
888
+ "grad_norm": 4.177317988292998,
889
+ "learning_rate": 7.324716614707794e-06,
890
+ "loss": 2.3549,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 3.63,
895
+ "grad_norm": 4.873379259329313,
896
+ "learning_rate": 7.175925608204428e-06,
897
+ "loss": 2.3888,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 3.66,
902
+ "grad_norm": 4.027921720790141,
903
+ "learning_rate": 7.0278109573699574e-06,
904
+ "loss": 2.2492,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 3.69,
909
+ "grad_norm": 4.489654053696505,
910
+ "learning_rate": 6.880408135131022e-06,
911
+ "loss": 2.244,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 3.71,
916
+ "grad_norm": 4.515410453085113,
917
+ "learning_rate": 6.733752443933879e-06,
918
+ "loss": 2.3124,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 3.74,
923
+ "grad_norm": 4.963204172080167,
924
+ "learning_rate": 6.587879007289576e-06,
925
+ "loss": 2.2542,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 3.77,
930
+ "grad_norm": 4.931378399728066,
931
+ "learning_rate": 6.442822761362015e-06,
932
+ "loss": 1.9509,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 3.8,
937
+ "grad_norm": 4.7328764276001,
938
+ "learning_rate": 6.298618446600856e-06,
939
+ "loss": 2.0579,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 3.83,
944
+ "grad_norm": 5.251697085848756,
945
+ "learning_rate": 6.155300599421305e-06,
946
+ "loss": 2.1462,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 3.86,
951
+ "grad_norm": 5.377799005102049,
952
+ "learning_rate": 6.0129035439327665e-06,
953
+ "loss": 1.991,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 3.89,
958
+ "grad_norm": 5.185963077105245,
959
+ "learning_rate": 5.871461383718344e-06,
960
+ "loss": 1.8895,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 3.91,
965
+ "grad_norm": 5.590606159281845,
966
+ "learning_rate": 5.731007993667155e-06,
967
+ "loss": 2.0092,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 3.94,
972
+ "grad_norm": 6.164057695091001,
973
+ "learning_rate": 5.5915770118614195e-06,
974
+ "loss": 2.0822,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 3.97,
979
+ "grad_norm": 6.77180320115024,
980
+ "learning_rate": 5.453201831520245e-06,
981
+ "loss": 1.8797,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 4.0,
986
+ "grad_norm": 7.052961110479867,
987
+ "learning_rate": 5.3159155930021e-06,
988
+ "loss": 2.3115,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 4.03,
993
+ "grad_norm": 13.172067376591047,
994
+ "learning_rate": 5.179751175867784e-06,
995
+ "loss": 5.3575,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 4.06,
1000
+ "grad_norm": 13.334878110202311,
1001
+ "learning_rate": 5.044741191005908e-06,
1002
+ "loss": 5.6717,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 4.09,
1007
+ "grad_norm": 10.171581292048922,
1008
+ "learning_rate": 4.910917972822713e-06,
1009
+ "loss": 4.9323,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 4.11,
1014
+ "grad_norm": 8.877047299036951,
1015
+ "learning_rate": 4.778313571498075e-06,
1016
+ "loss": 4.5247,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 4.14,
1021
+ "grad_norm": 7.916260375247708,
1022
+ "learning_rate": 4.64695974530961e-06,
1023
+ "loss": 4.2104,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 4.17,
1028
+ "grad_norm": 7.001700234460781,
1029
+ "learning_rate": 4.5168879530266906e-06,
1030
+ "loss": 3.6699,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 4.2,
1035
+ "grad_norm": 5.344925398470186,
1036
+ "learning_rate": 4.388129346376177e-06,
1037
+ "loss": 3.3075,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 4.23,
1042
+ "grad_norm": 5.740352187809239,
1043
+ "learning_rate": 4.260714762581677e-06,
1044
+ "loss": 3.5958,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 4.26,
1049
+ "grad_norm": 4.791723313221749,
1050
+ "learning_rate": 4.1346747169781695e-06,
1051
+ "loss": 3.2025,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 4.29,
1056
+ "grad_norm": 4.6059266231606655,
1057
+ "learning_rate": 4.010039395703665e-06,
1058
+ "loss": 3.0045,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 4.31,
1063
+ "grad_norm": 5.208392250257202,
1064
+ "learning_rate": 3.886838648469742e-06,
1065
+ "loss": 2.5741,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 4.34,
1070
+ "grad_norm": 5.233522675196091,
1071
+ "learning_rate": 3.7651019814126656e-06,
1072
+ "loss": 2.6712,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 4.37,
1077
+ "grad_norm": 5.135869425784653,
1078
+ "learning_rate": 3.6448585500267487e-06,
1079
+ "loss": 2.6455,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 4.4,
1084
+ "grad_norm": 4.645208008447359,
1085
+ "learning_rate": 3.5261371521817247e-06,
1086
+ "loss": 2.3787,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 4.43,
1091
+ "grad_norm": 4.660492061746799,
1092
+ "learning_rate": 3.4089662212257733e-06,
1093
+ "loss": 2.1385,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 4.46,
1098
+ "grad_norm": 4.4175550152417635,
1099
+ "learning_rate": 3.2933738191758158e-06,
1100
+ "loss": 2.0405,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 4.49,
1105
+ "grad_norm": 4.566709555922203,
1106
+ "learning_rate": 3.179387629996782e-06,
1107
+ "loss": 1.9903,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 4.51,
1112
+ "grad_norm": 4.349261816616526,
1113
+ "learning_rate": 3.067034952971382e-06,
1114
+ "loss": 1.9797,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 4.54,
1119
+ "grad_norm": 4.815462187163981,
1120
+ "learning_rate": 2.956342696162037e-06,
1121
+ "loss": 2.0851,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 4.57,
1126
+ "grad_norm": 4.791928073499566,
1127
+ "learning_rate": 2.8473373699664995e-06,
1128
+ "loss": 1.793,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 4.6,
1133
+ "grad_norm": 4.320192640779764,
1134
+ "learning_rate": 2.740045080768694e-06,
1135
+ "loss": 1.746,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 4.63,
1140
+ "grad_norm": 4.604601663113942,
1141
+ "learning_rate": 2.634491524686341e-06,
1142
+ "loss": 1.6877,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 4.66,
1147
+ "grad_norm": 3.63642030530214,
1148
+ "learning_rate": 2.5307019814168343e-06,
1149
+ "loss": 1.6653,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 4.69,
1154
+ "grad_norm": 3.7605261098294744,
1155
+ "learning_rate": 2.428701308182826e-06,
1156
+ "loss": 1.5892,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 4.71,
1161
+ "grad_norm": 3.770794461990271,
1162
+ "learning_rate": 2.3285139337790343e-06,
1163
+ "loss": 1.7293,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 4.74,
1168
+ "grad_norm": 3.9388567675880406,
1169
+ "learning_rate": 2.2301638527216196e-06,
1170
+ "loss": 1.6751,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 4.77,
1175
+ "grad_norm": 3.59303494013787,
1176
+ "learning_rate": 2.1336746195015845e-06,
1177
+ "loss": 1.3555,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 4.8,
1182
+ "grad_norm": 3.616144561640801,
1183
+ "learning_rate": 2.0390693429435626e-06,
1184
+ "loss": 1.4791,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 4.83,
1189
+ "grad_norm": 4.184463124765985,
1190
+ "learning_rate": 1.946370680671341e-06,
1191
+ "loss": 1.5188,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 4.86,
1196
+ "grad_norm": 4.105357361825141,
1197
+ "learning_rate": 1.8556008336814302e-06,
1198
+ "loss": 1.4057,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 4.89,
1203
+ "grad_norm": 4.231632132658564,
1204
+ "learning_rate": 1.7667815410260181e-06,
1205
+ "loss": 1.3032,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 4.91,
1210
+ "grad_norm": 4.194933198894844,
1211
+ "learning_rate": 1.679934074606533e-06,
1212
+ "loss": 1.4148,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 4.94,
1217
+ "grad_norm": 4.675308614956284,
1218
+ "learning_rate": 1.5950792340791044e-06,
1219
+ "loss": 1.5084,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 4.97,
1224
+ "grad_norm": 4.92049256107502,
1225
+ "learning_rate": 1.5122373418731306e-06,
1226
+ "loss": 1.3565,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 5.0,
1231
+ "grad_norm": 5.969442514645622,
1232
+ "learning_rate": 1.4314282383241097e-06,
1233
+ "loss": 1.7056,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 5.03,
1238
+ "grad_norm": 6.797850651633187,
1239
+ "learning_rate": 1.3526712769219619e-06,
1240
+ "loss": 1.9073,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 5.06,
1245
+ "grad_norm": 7.510748075175952,
1246
+ "learning_rate": 1.2759853196759454e-06,
1247
+ "loss": 2.0683,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 5.09,
1252
+ "grad_norm": 7.689466727133375,
1253
+ "learning_rate": 1.201388732597255e-06,
1254
+ "loss": 2.093,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 5.11,
1259
+ "grad_norm": 7.170048914177173,
1260
+ "learning_rate": 1.1288993813004467e-06,
1261
+ "loss": 2.1694,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 5.14,
1266
+ "grad_norm": 6.888698821967011,
1267
+ "learning_rate": 1.0585346267246743e-06,
1268
+ "loss": 2.1485,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 5.17,
1273
+ "grad_norm": 8.935327932773875,
1274
+ "learning_rate": 9.903113209758098e-07,
1275
+ "loss": 3.2942,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 5.2,
1280
+ "grad_norm": 7.282062148382787,
1281
+ "learning_rate": 9.242458032904311e-07,
1282
+ "loss": 3.0451,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 5.23,
1287
+ "grad_norm": 8.856238734952932,
1288
+ "learning_rate": 8.603538961226233e-07,
1289
+ "loss": 3.2713,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 5.26,
1294
+ "grad_norm": 7.072514973353356,
1295
+ "learning_rate": 7.986509013545673e-07,
1296
+ "loss": 2.8979,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 5.29,
1301
+ "grad_norm": 6.300112859192955,
1302
+ "learning_rate": 7.391515966317908e-07,
1303
+ "loss": 2.7407,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 5.31,
1308
+ "grad_norm": 6.552708837647418,
1309
+ "learning_rate": 6.81870231823969e-07,
1310
+ "loss": 2.3151,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 5.34,
1315
+ "grad_norm": 6.390611058615414,
1316
+ "learning_rate": 6.268205256121396e-07,
1317
+ "loss": 2.3887,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 5.37,
1322
+ "grad_norm": 6.1849954718581195,
1323
+ "learning_rate": 5.740156622031301e-07,
1324
+ "loss": 2.3422,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 5.4,
1329
+ "grad_norm": 5.499570423135919,
1330
+ "learning_rate": 5.234682881719766e-07,
1331
+ "loss": 2.1039,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 5.43,
1336
+ "grad_norm": 4.872882858791267,
1337
+ "learning_rate": 4.7519050943312326e-07,
1338
+ "loss": 1.9011,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 5.46,
1343
+ "grad_norm": 4.373003479063446,
1344
+ "learning_rate": 4.2919388834110066e-07,
1345
+ "loss": 1.7516,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 5.49,
1350
+ "grad_norm": 4.508004752636755,
1351
+ "learning_rate": 3.854894409213761e-07,
1352
+ "loss": 1.6404,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 5.51,
1357
+ "grad_norm": 4.2889965352379535,
1358
+ "learning_rate": 3.4408763423206093e-07,
1359
+ "loss": 1.6365,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 5.54,
1364
+ "grad_norm": 4.682234330521379,
1365
+ "learning_rate": 3.049983838570858e-07,
1366
+ "loss": 1.6745,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 5.57,
1371
+ "grad_norm": 4.537341291350183,
1372
+ "learning_rate": 2.6823105153145125e-07,
1373
+ "loss": 1.4181,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 5.6,
1378
+ "grad_norm": 4.32840882506885,
1379
+ "learning_rate": 2.3379444289913344e-07,
1380
+ "loss": 1.41,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 5.63,
1385
+ "grad_norm": 4.618590743310313,
1386
+ "learning_rate": 2.016968054041546e-07,
1387
+ "loss": 1.3301,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 5.66,
1392
+ "grad_norm": 3.9839592670692716,
1393
+ "learning_rate": 1.7194582631535616e-07,
1394
+ "loss": 1.3857,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 5.69,
1399
+ "grad_norm": 4.189042770104091,
1400
+ "learning_rate": 1.4454863088532388e-07,
1401
+ "loss": 1.3024,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 5.71,
1406
+ "grad_norm": 4.2928472832951305,
1407
+ "learning_rate": 1.19511780643915e-07,
1408
+ "loss": 1.4741,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 5.74,
1413
+ "grad_norm": 4.58876530743957,
1414
+ "learning_rate": 9.684127182679526e-08,
1415
+ "loss": 1.4256,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 5.77,
1420
+ "grad_norm": 4.562646086161964,
1421
+ "learning_rate": 7.65425339393644e-08,
1422
+ "loss": 1.128,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 5.8,
1427
+ "grad_norm": 4.530949504721316,
1428
+ "learning_rate": 5.862042845640403e-08,
1429
+ "loss": 1.2618,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 5.83,
1434
+ "grad_norm": 5.3286756918257865,
1435
+ "learning_rate": 4.307924765777682e-08,
1436
+ "loss": 1.2957,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 5.86,
1441
+ "grad_norm": 5.2853418793857845,
1442
+ "learning_rate": 2.992271360043986e-08,
1443
+ "loss": 1.2061,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 5.89,
1448
+ "grad_norm": 5.532437877616826,
1449
+ "learning_rate": 1.9153977227022168e-08,
1450
+ "loss": 1.1273,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 5.91,
1455
+ "grad_norm": 5.896991609572843,
1456
+ "learning_rate": 1.0775617611189504e-08,
1457
+ "loss": 1.2515,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 5.94,
1462
+ "grad_norm": 6.221140999378529,
1463
+ "learning_rate": 4.7896413399639575e-09,
1464
+ "loss": 1.348,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 5.97,
1469
+ "grad_norm": 5.940323080238109,
1470
+ "learning_rate": 1.1974820331517313e-09,
1471
+ "loss": 1.2091,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 6.0,
1476
+ "grad_norm": 6.754644623774243,
1477
+ "learning_rate": 0.0,
1478
+ "loss": 1.5446,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 6.0,
1483
+ "step": 210,
1484
+ "total_flos": 0.0,
1485
+ "train_loss": 0.06094220252264114,
1486
+ "train_runtime": 5786.5332,
1487
+ "train_samples_per_second": 74.324,
1488
+ "train_steps_per_second": 0.036
1489
+ }
1490
+ ],
1491
+ "logging_steps": 1.0,
1492
+ "max_steps": 210,
1493
+ "num_input_tokens_seen": 0,
1494
+ "num_train_epochs": 6,
1495
+ "save_steps": 20,
1496
+ "stateful_callbacks": {
1497
+ "TrainerControl": {
1498
+ "args": {
1499
+ "should_epoch_stop": false,
1500
+ "should_evaluate": false,
1501
+ "should_log": false,
1502
+ "should_save": true,
1503
+ "should_training_stop": true
1504
+ },
1505
+ "attributes": {}
1506
+ }
1507
+ },
1508
+ "total_flos": 0.0,
1509
+ "train_batch_size": 1,
1510
+ "trial_name": null,
1511
+ "trial_params": null
1512
+ }
vision_tower/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output/NVILA-8B-longvila-256frames/vision_tower",
3
+ "architectures": [
4
+ "SiglipVisionModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "hidden_act": "gelu_pytorch_tanh",
8
+ "hidden_size": 1152,
9
+ "image_size": 448,
10
+ "intermediate_size": 4304,
11
+ "layer_norm_eps": 1e-06,
12
+ "model_type": "siglip_vision_model",
13
+ "num_attention_heads": 16,
14
+ "num_channels": 3,
15
+ "num_hidden_layers": 27,
16
+ "num_image_tokens": 256,
17
+ "patch_size": 14,
18
+ "projection_dim": 2048,
19
+ "projector_hidden_act": "gelu_fast",
20
+ "torch_dtype": "bfloat16",
21
+ "transformers_version": "4.46.0",
22
+ "vision_use_head": false
23
+ }
vision_tower/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61210e7ff782099a38524a367aaff6f3fd80785e8ba4310e0fc515dd61b9f904
3
+ size 826707904
vision_tower/preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 3,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 448,
22
+ "width": 448
23
+ }
24
+ }