Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +5 -0
- config.json +360 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +772 -0
- special_tokens_map.json +20 -0
- tokenizer.json +3 -0
- tokenizer_config.json +44 -0
- trainer_state.json +1414 -0
- training_args.bin +3 -0
- vocab.json +0 -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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "lmms-lab/llava-onevision-qwen2-7b-ov/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaQwenForCausalLM"
|
| 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 |
+
"ignore_index": -100,
|
| 12 |
+
"image_aspect_ratio": "anyres_max_9_randomroi",
|
| 13 |
+
"image_crop_resolution": null,
|
| 14 |
+
"image_grid_pinpoints": [
|
| 15 |
+
[
|
| 16 |
+
384,
|
| 17 |
+
384
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
384,
|
| 21 |
+
768
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
384,
|
| 25 |
+
1152
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
384,
|
| 29 |
+
1536
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
384,
|
| 33 |
+
1920
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
384,
|
| 37 |
+
2304
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
768,
|
| 41 |
+
384
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
768,
|
| 45 |
+
768
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
768,
|
| 49 |
+
1152
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
768,
|
| 53 |
+
1536
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
768,
|
| 57 |
+
1920
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
768,
|
| 61 |
+
2304
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
1152,
|
| 65 |
+
384
|
| 66 |
+
],
|
| 67 |
+
[
|
| 68 |
+
1152,
|
| 69 |
+
768
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
1152,
|
| 73 |
+
1152
|
| 74 |
+
],
|
| 75 |
+
[
|
| 76 |
+
1152,
|
| 77 |
+
1536
|
| 78 |
+
],
|
| 79 |
+
[
|
| 80 |
+
1152,
|
| 81 |
+
1920
|
| 82 |
+
],
|
| 83 |
+
[
|
| 84 |
+
1152,
|
| 85 |
+
2304
|
| 86 |
+
],
|
| 87 |
+
[
|
| 88 |
+
1536,
|
| 89 |
+
384
|
| 90 |
+
],
|
| 91 |
+
[
|
| 92 |
+
1536,
|
| 93 |
+
768
|
| 94 |
+
],
|
| 95 |
+
[
|
| 96 |
+
1536,
|
| 97 |
+
1152
|
| 98 |
+
],
|
| 99 |
+
[
|
| 100 |
+
1536,
|
| 101 |
+
1536
|
| 102 |
+
],
|
| 103 |
+
[
|
| 104 |
+
1536,
|
| 105 |
+
1920
|
| 106 |
+
],
|
| 107 |
+
[
|
| 108 |
+
1536,
|
| 109 |
+
2304
|
| 110 |
+
],
|
| 111 |
+
[
|
| 112 |
+
1920,
|
| 113 |
+
384
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
1920,
|
| 117 |
+
768
|
| 118 |
+
],
|
| 119 |
+
[
|
| 120 |
+
1920,
|
| 121 |
+
1152
|
| 122 |
+
],
|
| 123 |
+
[
|
| 124 |
+
1920,
|
| 125 |
+
1536
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
1920,
|
| 129 |
+
1920
|
| 130 |
+
],
|
| 131 |
+
[
|
| 132 |
+
1920,
|
| 133 |
+
2304
|
| 134 |
+
],
|
| 135 |
+
[
|
| 136 |
+
2304,
|
| 137 |
+
384
|
| 138 |
+
],
|
| 139 |
+
[
|
| 140 |
+
2304,
|
| 141 |
+
768
|
| 142 |
+
],
|
| 143 |
+
[
|
| 144 |
+
2304,
|
| 145 |
+
1152
|
| 146 |
+
],
|
| 147 |
+
[
|
| 148 |
+
2304,
|
| 149 |
+
1536
|
| 150 |
+
],
|
| 151 |
+
[
|
| 152 |
+
2304,
|
| 153 |
+
1920
|
| 154 |
+
],
|
| 155 |
+
[
|
| 156 |
+
2304,
|
| 157 |
+
2304
|
| 158 |
+
]
|
| 159 |
+
],
|
| 160 |
+
"image_seq_length": 576,
|
| 161 |
+
"image_split_resolution": null,
|
| 162 |
+
"image_token_index": 151646,
|
| 163 |
+
"initializer_range": 0.02,
|
| 164 |
+
"intermediate_size": 18944,
|
| 165 |
+
"max_position_embeddings": 32768,
|
| 166 |
+
"max_window_layers": 28,
|
| 167 |
+
"mm_hidden_size": 1152,
|
| 168 |
+
"mm_newline_position": "one_token",
|
| 169 |
+
"mm_patch_merge_type": "spatial_avgpool_auto_unpad_randomroi_newl",
|
| 170 |
+
"mm_projector_lr": null,
|
| 171 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 172 |
+
"mm_resampler_type": null,
|
| 173 |
+
"mm_spatial_pool_mode": "bilinear",
|
| 174 |
+
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
|
| 175 |
+
"mm_use_im_patch_token": false,
|
| 176 |
+
"mm_use_im_start_end": false,
|
| 177 |
+
"mm_vision_select_feature": "patch",
|
| 178 |
+
"mm_vision_select_layer": -2,
|
| 179 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-384",
|
| 180 |
+
"mm_vision_tower_lr": 2e-06,
|
| 181 |
+
"model_type": "llava",
|
| 182 |
+
"num_attention_heads": 28,
|
| 183 |
+
"num_hidden_layers": 28,
|
| 184 |
+
"num_key_value_heads": 4,
|
| 185 |
+
"pos_skipping_range": 4096,
|
| 186 |
+
"projector_hidden_act": "gelu",
|
| 187 |
+
"rms_norm_eps": 1e-06,
|
| 188 |
+
"rope_scaling": null,
|
| 189 |
+
"rope_theta": 1000000.0,
|
| 190 |
+
"sliding_window": 131072,
|
| 191 |
+
"text_config_bak": {
|
| 192 |
+
"_attn_implementation_autoset": false,
|
| 193 |
+
"_name_or_path": "",
|
| 194 |
+
"add_cross_attention": false,
|
| 195 |
+
"architectures": null,
|
| 196 |
+
"attention_bias": false,
|
| 197 |
+
"attention_dropout": 0.0,
|
| 198 |
+
"bad_words_ids": null,
|
| 199 |
+
"begin_suppress_tokens": null,
|
| 200 |
+
"bos_token_id": 1,
|
| 201 |
+
"chunk_size_feed_forward": 0,
|
| 202 |
+
"cross_attention_hidden_size": null,
|
| 203 |
+
"decoder_start_token_id": null,
|
| 204 |
+
"diversity_penalty": 0.0,
|
| 205 |
+
"do_sample": false,
|
| 206 |
+
"early_stopping": false,
|
| 207 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 208 |
+
"eos_token_id": 2,
|
| 209 |
+
"exponential_decay_length_penalty": null,
|
| 210 |
+
"finetuning_task": null,
|
| 211 |
+
"forced_bos_token_id": null,
|
| 212 |
+
"forced_eos_token_id": null,
|
| 213 |
+
"head_dim": 128,
|
| 214 |
+
"hidden_act": "silu",
|
| 215 |
+
"hidden_size": 4096,
|
| 216 |
+
"id2label": {
|
| 217 |
+
"0": "LABEL_0",
|
| 218 |
+
"1": "LABEL_1"
|
| 219 |
+
},
|
| 220 |
+
"initializer_range": 0.02,
|
| 221 |
+
"intermediate_size": 11008,
|
| 222 |
+
"is_decoder": false,
|
| 223 |
+
"is_encoder_decoder": false,
|
| 224 |
+
"label2id": {
|
| 225 |
+
"LABEL_0": 0,
|
| 226 |
+
"LABEL_1": 1
|
| 227 |
+
},
|
| 228 |
+
"length_penalty": 1.0,
|
| 229 |
+
"max_length": 20,
|
| 230 |
+
"max_position_embeddings": 2048,
|
| 231 |
+
"min_length": 0,
|
| 232 |
+
"mlp_bias": false,
|
| 233 |
+
"model_type": "llama",
|
| 234 |
+
"no_repeat_ngram_size": 0,
|
| 235 |
+
"num_attention_heads": 32,
|
| 236 |
+
"num_beam_groups": 1,
|
| 237 |
+
"num_beams": 1,
|
| 238 |
+
"num_hidden_layers": 32,
|
| 239 |
+
"num_key_value_heads": 32,
|
| 240 |
+
"num_return_sequences": 1,
|
| 241 |
+
"output_attentions": false,
|
| 242 |
+
"output_hidden_states": false,
|
| 243 |
+
"output_scores": false,
|
| 244 |
+
"pad_token_id": null,
|
| 245 |
+
"prefix": null,
|
| 246 |
+
"pretraining_tp": 1,
|
| 247 |
+
"problem_type": null,
|
| 248 |
+
"pruned_heads": {},
|
| 249 |
+
"remove_invalid_values": false,
|
| 250 |
+
"repetition_penalty": 1.0,
|
| 251 |
+
"return_dict": true,
|
| 252 |
+
"return_dict_in_generate": false,
|
| 253 |
+
"rms_norm_eps": 1e-06,
|
| 254 |
+
"rope_scaling": null,
|
| 255 |
+
"rope_theta": 10000.0,
|
| 256 |
+
"sep_token_id": null,
|
| 257 |
+
"suppress_tokens": null,
|
| 258 |
+
"task_specific_params": null,
|
| 259 |
+
"temperature": 1.0,
|
| 260 |
+
"tf_legacy_loss": false,
|
| 261 |
+
"tie_encoder_decoder": false,
|
| 262 |
+
"tie_word_embeddings": false,
|
| 263 |
+
"tokenizer_class": null,
|
| 264 |
+
"top_k": 50,
|
| 265 |
+
"top_p": 1.0,
|
| 266 |
+
"torch_dtype": null,
|
| 267 |
+
"torchscript": false,
|
| 268 |
+
"typical_p": 1.0,
|
| 269 |
+
"use_bfloat16": false,
|
| 270 |
+
"use_cache": true,
|
| 271 |
+
"vocab_size": 32000
|
| 272 |
+
},
|
| 273 |
+
"tie_word_embeddings": false,
|
| 274 |
+
"tokenizer_model_max_length": 32768,
|
| 275 |
+
"tokenizer_padding_side": "right",
|
| 276 |
+
"torch_dtype": "bfloat16",
|
| 277 |
+
"transformers_version": "4.46.1",
|
| 278 |
+
"use_cache": true,
|
| 279 |
+
"use_mm_proj": true,
|
| 280 |
+
"use_pos_skipping": false,
|
| 281 |
+
"use_sliding_window": false,
|
| 282 |
+
"vision_config": {
|
| 283 |
+
"_attn_implementation_autoset": false,
|
| 284 |
+
"_name_or_path": "",
|
| 285 |
+
"add_cross_attention": false,
|
| 286 |
+
"architectures": null,
|
| 287 |
+
"attention_dropout": 0.0,
|
| 288 |
+
"bad_words_ids": null,
|
| 289 |
+
"begin_suppress_tokens": null,
|
| 290 |
+
"bos_token_id": null,
|
| 291 |
+
"chunk_size_feed_forward": 0,
|
| 292 |
+
"cross_attention_hidden_size": null,
|
| 293 |
+
"decoder_start_token_id": null,
|
| 294 |
+
"diversity_penalty": 0.0,
|
| 295 |
+
"do_sample": false,
|
| 296 |
+
"early_stopping": false,
|
| 297 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 298 |
+
"eos_token_id": null,
|
| 299 |
+
"exponential_decay_length_penalty": null,
|
| 300 |
+
"finetuning_task": null,
|
| 301 |
+
"forced_bos_token_id": null,
|
| 302 |
+
"forced_eos_token_id": null,
|
| 303 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 304 |
+
"hidden_size": 1152,
|
| 305 |
+
"id2label": {
|
| 306 |
+
"0": "LABEL_0",
|
| 307 |
+
"1": "LABEL_1"
|
| 308 |
+
},
|
| 309 |
+
"image_size": 384,
|
| 310 |
+
"intermediate_size": 4304,
|
| 311 |
+
"is_decoder": false,
|
| 312 |
+
"is_encoder_decoder": false,
|
| 313 |
+
"label2id": {
|
| 314 |
+
"LABEL_0": 0,
|
| 315 |
+
"LABEL_1": 1
|
| 316 |
+
},
|
| 317 |
+
"layer_norm_eps": 1e-06,
|
| 318 |
+
"length_penalty": 1.0,
|
| 319 |
+
"max_length": 20,
|
| 320 |
+
"min_length": 0,
|
| 321 |
+
"model_type": "siglip_vision_model",
|
| 322 |
+
"no_repeat_ngram_size": 0,
|
| 323 |
+
"num_attention_heads": 16,
|
| 324 |
+
"num_beam_groups": 1,
|
| 325 |
+
"num_beams": 1,
|
| 326 |
+
"num_channels": 3,
|
| 327 |
+
"num_hidden_layers": 27,
|
| 328 |
+
"num_return_sequences": 1,
|
| 329 |
+
"output_attentions": false,
|
| 330 |
+
"output_hidden_states": false,
|
| 331 |
+
"output_scores": false,
|
| 332 |
+
"pad_token_id": null,
|
| 333 |
+
"patch_size": 14,
|
| 334 |
+
"prefix": null,
|
| 335 |
+
"problem_type": null,
|
| 336 |
+
"pruned_heads": {},
|
| 337 |
+
"remove_invalid_values": false,
|
| 338 |
+
"repetition_penalty": 1.0,
|
| 339 |
+
"return_dict": true,
|
| 340 |
+
"return_dict_in_generate": false,
|
| 341 |
+
"sep_token_id": null,
|
| 342 |
+
"suppress_tokens": null,
|
| 343 |
+
"task_specific_params": null,
|
| 344 |
+
"temperature": 1.0,
|
| 345 |
+
"tf_legacy_loss": false,
|
| 346 |
+
"tie_encoder_decoder": false,
|
| 347 |
+
"tie_word_embeddings": true,
|
| 348 |
+
"tokenizer_class": null,
|
| 349 |
+
"top_k": 50,
|
| 350 |
+
"top_p": 1.0,
|
| 351 |
+
"torch_dtype": null,
|
| 352 |
+
"torchscript": false,
|
| 353 |
+
"typical_p": 1.0,
|
| 354 |
+
"use_bfloat16": false
|
| 355 |
+
},
|
| 356 |
+
"vision_feature_layer": -2,
|
| 357 |
+
"vision_feature_select_strategy": "default",
|
| 358 |
+
"vision_tower_pretrained": null,
|
| 359 |
+
"vocab_size": 152064
|
| 360 |
+
}
|
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": "4.46.1"
|
| 14 |
+
}
|
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 sha256:6f3e596d9ef7519b63bd46e690003e5868b1955a63f1c721923173831b380eff
|
| 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:fcccd8887221b40d7bb9ec3edd4509ed107cf70e381185e80a60bd5d155afdcb
|
| 3 |
+
size 4932751008
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c8237a743158cfeee059cedaad5205fde085cbc2204dad4359810c68c9e93b5
|
| 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:c8847cb29791580cc253fc5a3eca637296b5792c5744a4aba330ec8834e3b982
|
| 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 |
+
}
|
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
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
+
size 11418266
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"padding_side": "right",
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
+
"unk_token": null
|
| 44 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1414 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9972968675465098,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 196,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.005088249324216886,
|
| 13 |
+
"grad_norm": 6.376819304774717,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 15 |
+
"loss": 1.2212,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.010176498648433773,
|
| 20 |
+
"grad_norm": 9.156958532034324,
|
| 21 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 22 |
+
"loss": 1.2331,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01526474797265066,
|
| 27 |
+
"grad_norm": 8.548654865637552,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 1.2903,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.020352997296867546,
|
| 34 |
+
"grad_norm": 7.6472800849066225,
|
| 35 |
+
"learning_rate": 6.666666666666667e-06,
|
| 36 |
+
"loss": 1.0864,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.025441246621084435,
|
| 41 |
+
"grad_norm": 14.279902584657638,
|
| 42 |
+
"learning_rate": 8.333333333333334e-06,
|
| 43 |
+
"loss": 1.0768,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03052949594530132,
|
| 48 |
+
"grad_norm": 3.7335646723367324,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 0.9323,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.035617745269518206,
|
| 55 |
+
"grad_norm": 0.8627027447832171,
|
| 56 |
+
"learning_rate": 9.999316524962347e-06,
|
| 57 |
+
"loss": 0.4469,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04070599459373509,
|
| 62 |
+
"grad_norm": 0.8221611562946466,
|
| 63 |
+
"learning_rate": 9.99726628670463e-06,
|
| 64 |
+
"loss": 0.4761,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04579424391795198,
|
| 69 |
+
"grad_norm": 2.733350766966074,
|
| 70 |
+
"learning_rate": 9.993849845741525e-06,
|
| 71 |
+
"loss": 0.8348,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.05088249324216887,
|
| 76 |
+
"grad_norm": 2.723165619967254,
|
| 77 |
+
"learning_rate": 9.989068136093873e-06,
|
| 78 |
+
"loss": 0.8526,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.055970742566385755,
|
| 83 |
+
"grad_norm": 0.9401228979509004,
|
| 84 |
+
"learning_rate": 9.98292246503335e-06,
|
| 85 |
+
"loss": 0.4237,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.06105899189060264,
|
| 90 |
+
"grad_norm": 2.4866400038081946,
|
| 91 |
+
"learning_rate": 9.975414512725058e-06,
|
| 92 |
+
"loss": 0.7775,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06614724121481953,
|
| 97 |
+
"grad_norm": 2.2343217891723306,
|
| 98 |
+
"learning_rate": 9.966546331768192e-06,
|
| 99 |
+
"loss": 0.8362,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.07123549053903641,
|
| 104 |
+
"grad_norm": 2.1476340113996155,
|
| 105 |
+
"learning_rate": 9.956320346634877e-06,
|
| 106 |
+
"loss": 0.6924,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0763237398632533,
|
| 111 |
+
"grad_norm": 2.2660253147542924,
|
| 112 |
+
"learning_rate": 9.944739353007344e-06,
|
| 113 |
+
"loss": 0.8006,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08141198918747018,
|
| 118 |
+
"grad_norm": 1.962741499851516,
|
| 119 |
+
"learning_rate": 9.931806517013612e-06,
|
| 120 |
+
"loss": 0.7972,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08650023851168707,
|
| 125 |
+
"grad_norm": 2.3043159657707557,
|
| 126 |
+
"learning_rate": 9.917525374361913e-06,
|
| 127 |
+
"loss": 0.8331,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.09158848783590395,
|
| 132 |
+
"grad_norm": 2.50787182166959,
|
| 133 |
+
"learning_rate": 9.901899829374048e-06,
|
| 134 |
+
"loss": 0.6467,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.09667673716012085,
|
| 139 |
+
"grad_norm": 2.067143884273235,
|
| 140 |
+
"learning_rate": 9.884934153917998e-06,
|
| 141 |
+
"loss": 0.5831,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.10176498648433774,
|
| 146 |
+
"grad_norm": 1.9355150939047303,
|
| 147 |
+
"learning_rate": 9.86663298624003e-06,
|
| 148 |
+
"loss": 0.6237,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.10685323580855462,
|
| 153 |
+
"grad_norm": 2.4286709059735885,
|
| 154 |
+
"learning_rate": 9.847001329696653e-06,
|
| 155 |
+
"loss": 0.7907,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.11194148513277151,
|
| 160 |
+
"grad_norm": 2.1638545004928136,
|
| 161 |
+
"learning_rate": 9.826044551386743e-06,
|
| 162 |
+
"loss": 0.6921,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.11702973445698839,
|
| 167 |
+
"grad_norm": 1.9157802742965189,
|
| 168 |
+
"learning_rate": 9.803768380684242e-06,
|
| 169 |
+
"loss": 0.6975,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.12211798378120528,
|
| 174 |
+
"grad_norm": 1.9485581275135593,
|
| 175 |
+
"learning_rate": 9.780178907671788e-06,
|
| 176 |
+
"loss": 0.6949,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12720623310542217,
|
| 181 |
+
"grad_norm": 2.048988282393849,
|
| 182 |
+
"learning_rate": 9.755282581475769e-06,
|
| 183 |
+
"loss": 0.6428,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.13229448242963907,
|
| 188 |
+
"grad_norm": 2.058756336489088,
|
| 189 |
+
"learning_rate": 9.729086208503174e-06,
|
| 190 |
+
"loss": 0.5476,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.13738273175385593,
|
| 195 |
+
"grad_norm": 1.8921946476223952,
|
| 196 |
+
"learning_rate": 9.701596950580807e-06,
|
| 197 |
+
"loss": 0.5733,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.14247098107807282,
|
| 202 |
+
"grad_norm": 2.200558594868892,
|
| 203 |
+
"learning_rate": 9.672822322997305e-06,
|
| 204 |
+
"loss": 0.6763,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.14755923040228971,
|
| 209 |
+
"grad_norm": 2.2478552460928927,
|
| 210 |
+
"learning_rate": 9.642770192448537e-06,
|
| 211 |
+
"loss": 0.6203,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.1526474797265066,
|
| 216 |
+
"grad_norm": 1.174257433300181,
|
| 217 |
+
"learning_rate": 9.611448774886925e-06,
|
| 218 |
+
"loss": 0.4586,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15773572905072347,
|
| 223 |
+
"grad_norm": 1.0023424088545339,
|
| 224 |
+
"learning_rate": 9.578866633275289e-06,
|
| 225 |
+
"loss": 0.451,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.16282397837494036,
|
| 230 |
+
"grad_norm": 2.0005021535427128,
|
| 231 |
+
"learning_rate": 9.545032675245814e-06,
|
| 232 |
+
"loss": 0.7157,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.16791222769915726,
|
| 237 |
+
"grad_norm": 1.9642144233569843,
|
| 238 |
+
"learning_rate": 9.509956150664796e-06,
|
| 239 |
+
"loss": 0.689,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.17300047702337415,
|
| 244 |
+
"grad_norm": 2.3153254847421914,
|
| 245 |
+
"learning_rate": 9.473646649103819e-06,
|
| 246 |
+
"loss": 0.6978,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.17808872634759104,
|
| 251 |
+
"grad_norm": 2.0920285074327105,
|
| 252 |
+
"learning_rate": 9.43611409721806e-06,
|
| 253 |
+
"loss": 0.6146,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.1831769756718079,
|
| 258 |
+
"grad_norm": 1.9609871683991977,
|
| 259 |
+
"learning_rate": 9.397368756032445e-06,
|
| 260 |
+
"loss": 0.6792,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1882652249960248,
|
| 265 |
+
"grad_norm": 2.139412662348695,
|
| 266 |
+
"learning_rate": 9.357421218136387e-06,
|
| 267 |
+
"loss": 0.5454,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.1933534743202417,
|
| 272 |
+
"grad_norm": 1.0220339211752483,
|
| 273 |
+
"learning_rate": 9.31628240478787e-06,
|
| 274 |
+
"loss": 0.4778,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.19844172364445858,
|
| 279 |
+
"grad_norm": 2.0404826104161025,
|
| 280 |
+
"learning_rate": 9.273963562927695e-06,
|
| 281 |
+
"loss": 0.6245,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.20352997296867548,
|
| 286 |
+
"grad_norm": 2.281403761746208,
|
| 287 |
+
"learning_rate": 9.230476262104678e-06,
|
| 288 |
+
"loss": 0.6804,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.20861822229289234,
|
| 293 |
+
"grad_norm": 3.6084177219171947,
|
| 294 |
+
"learning_rate": 9.185832391312644e-06,
|
| 295 |
+
"loss": 0.6272,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.21370647161710923,
|
| 300 |
+
"grad_norm": 1.8239489766079142,
|
| 301 |
+
"learning_rate": 9.140044155740102e-06,
|
| 302 |
+
"loss": 0.711,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.21879472094132613,
|
| 307 |
+
"grad_norm": 2.070200136807796,
|
| 308 |
+
"learning_rate": 9.093124073433464e-06,
|
| 309 |
+
"loss": 0.6276,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.22388297026554302,
|
| 314 |
+
"grad_norm": 1.8227868131794736,
|
| 315 |
+
"learning_rate": 9.045084971874738e-06,
|
| 316 |
+
"loss": 0.568,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2289712195897599,
|
| 321 |
+
"grad_norm": 2.0312409937908273,
|
| 322 |
+
"learning_rate": 8.995939984474624e-06,
|
| 323 |
+
"loss": 0.5819,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.23405946891397678,
|
| 328 |
+
"grad_norm": 2.0591484505591984,
|
| 329 |
+
"learning_rate": 8.94570254698197e-06,
|
| 330 |
+
"loss": 0.6189,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.23914771823819367,
|
| 335 |
+
"grad_norm": 1.8413511377406058,
|
| 336 |
+
"learning_rate": 8.894386393810563e-06,
|
| 337 |
+
"loss": 0.6415,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.24423596756241056,
|
| 342 |
+
"grad_norm": 1.871308715661416,
|
| 343 |
+
"learning_rate": 8.842005554284296e-06,
|
| 344 |
+
"loss": 0.7269,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.24932421688662745,
|
| 349 |
+
"grad_norm": 0.9010820982007217,
|
| 350 |
+
"learning_rate": 8.788574348801676e-06,
|
| 351 |
+
"loss": 0.4621,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.25441246621084435,
|
| 356 |
+
"grad_norm": 1.9355973891126907,
|
| 357 |
+
"learning_rate": 8.734107384920771e-06,
|
| 358 |
+
"loss": 0.4703,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2595007155350612,
|
| 363 |
+
"grad_norm": 1.6598644446012476,
|
| 364 |
+
"learning_rate": 8.67861955336566e-06,
|
| 365 |
+
"loss": 0.4163,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.26458896485927813,
|
| 370 |
+
"grad_norm": 0.8262469830378751,
|
| 371 |
+
"learning_rate": 8.622126023955446e-06,
|
| 372 |
+
"loss": 0.466,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.269677214183495,
|
| 377 |
+
"grad_norm": 1.9301500703636114,
|
| 378 |
+
"learning_rate": 8.564642241456986e-06,
|
| 379 |
+
"loss": 0.5155,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.27476546350771186,
|
| 384 |
+
"grad_norm": 2.0045597308796457,
|
| 385 |
+
"learning_rate": 8.506183921362443e-06,
|
| 386 |
+
"loss": 0.5895,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2798537128319288,
|
| 391 |
+
"grad_norm": 1.8768604434761909,
|
| 392 |
+
"learning_rate": 8.446767045592829e-06,
|
| 393 |
+
"loss": 0.5402,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.28494196215614565,
|
| 398 |
+
"grad_norm": 2.48459660000141,
|
| 399 |
+
"learning_rate": 8.386407858128707e-06,
|
| 400 |
+
"loss": 0.4908,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.29003021148036257,
|
| 405 |
+
"grad_norm": 2.018246694569729,
|
| 406 |
+
"learning_rate": 8.325122860569241e-06,
|
| 407 |
+
"loss": 0.6405,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.29511846080457943,
|
| 412 |
+
"grad_norm": 2.3388459880506542,
|
| 413 |
+
"learning_rate": 8.262928807620843e-06,
|
| 414 |
+
"loss": 0.6017,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3002067101287963,
|
| 419 |
+
"grad_norm": 2.3665994679506808,
|
| 420 |
+
"learning_rate": 8.199842702516584e-06,
|
| 421 |
+
"loss": 0.5229,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.3052949594530132,
|
| 426 |
+
"grad_norm": 2.0184106112937252,
|
| 427 |
+
"learning_rate": 8.135881792367686e-06,
|
| 428 |
+
"loss": 0.6064,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3103832087772301,
|
| 433 |
+
"grad_norm": 1.8643271820146765,
|
| 434 |
+
"learning_rate": 8.071063563448341e-06,
|
| 435 |
+
"loss": 0.5915,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.31547145810144694,
|
| 440 |
+
"grad_norm": 1.722265638914434,
|
| 441 |
+
"learning_rate": 8.005405736415127e-06,
|
| 442 |
+
"loss": 0.4657,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.32055970742566386,
|
| 447 |
+
"grad_norm": 1.706733120977353,
|
| 448 |
+
"learning_rate": 7.938926261462366e-06,
|
| 449 |
+
"loss": 0.499,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.32564795674988073,
|
| 454 |
+
"grad_norm": 2.240312731365644,
|
| 455 |
+
"learning_rate": 7.871643313414718e-06,
|
| 456 |
+
"loss": 0.5416,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.33073620607409765,
|
| 461 |
+
"grad_norm": 1.7568581955331595,
|
| 462 |
+
"learning_rate": 7.803575286758365e-06,
|
| 463 |
+
"loss": 0.4993,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.3358244553983145,
|
| 468 |
+
"grad_norm": 1.7451061943054298,
|
| 469 |
+
"learning_rate": 7.734740790612137e-06,
|
| 470 |
+
"loss": 0.5667,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3409127047225314,
|
| 475 |
+
"grad_norm": 2.193186411728282,
|
| 476 |
+
"learning_rate": 7.66515864363997e-06,
|
| 477 |
+
"loss": 0.5462,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3460009540467483,
|
| 482 |
+
"grad_norm": 1.9643747559281786,
|
| 483 |
+
"learning_rate": 7.594847868906076e-06,
|
| 484 |
+
"loss": 0.6262,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.35108920337096516,
|
| 489 |
+
"grad_norm": 1.95786323892343,
|
| 490 |
+
"learning_rate": 7.52382768867422e-06,
|
| 491 |
+
"loss": 0.6642,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3561774526951821,
|
| 496 |
+
"grad_norm": 1.0006199818159889,
|
| 497 |
+
"learning_rate": 7.452117519152542e-06,
|
| 498 |
+
"loss": 0.507,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.36126570201939895,
|
| 503 |
+
"grad_norm": 1.9223672992099927,
|
| 504 |
+
"learning_rate": 7.379736965185369e-06,
|
| 505 |
+
"loss": 0.7529,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3663539513436158,
|
| 510 |
+
"grad_norm": 2.0674107718199104,
|
| 511 |
+
"learning_rate": 7.30670581489344e-06,
|
| 512 |
+
"loss": 0.4531,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.37144220066783273,
|
| 517 |
+
"grad_norm": 1.9129373169630381,
|
| 518 |
+
"learning_rate": 7.233044034264034e-06,
|
| 519 |
+
"loss": 0.5099,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3765304499920496,
|
| 524 |
+
"grad_norm": 1.7438996600779544,
|
| 525 |
+
"learning_rate": 7.158771761692464e-06,
|
| 526 |
+
"loss": 0.5289,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3816186993162665,
|
| 531 |
+
"grad_norm": 1.8111556114494765,
|
| 532 |
+
"learning_rate": 7.083909302476453e-06,
|
| 533 |
+
"loss": 0.5465,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3867069486404834,
|
| 538 |
+
"grad_norm": 1.9016815642934104,
|
| 539 |
+
"learning_rate": 7.008477123264849e-06,
|
| 540 |
+
"loss": 0.5224,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.39179519796470025,
|
| 545 |
+
"grad_norm": 1.773824146906631,
|
| 546 |
+
"learning_rate": 6.932495846462262e-06,
|
| 547 |
+
"loss": 0.618,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.39688344728891717,
|
| 552 |
+
"grad_norm": 1.6675568834230474,
|
| 553 |
+
"learning_rate": 6.855986244591104e-06,
|
| 554 |
+
"loss": 0.4824,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.40197169661313403,
|
| 559 |
+
"grad_norm": 1.710579271480641,
|
| 560 |
+
"learning_rate": 6.778969234612583e-06,
|
| 561 |
+
"loss": 0.5667,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.40705994593735095,
|
| 566 |
+
"grad_norm": 1.6868384794732627,
|
| 567 |
+
"learning_rate": 6.701465872208216e-06,
|
| 568 |
+
"loss": 0.5518,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.4121481952615678,
|
| 573 |
+
"grad_norm": 1.6861752383360624,
|
| 574 |
+
"learning_rate": 6.6234973460234184e-06,
|
| 575 |
+
"loss": 0.4939,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.4172364445857847,
|
| 580 |
+
"grad_norm": 0.8972052976655005,
|
| 581 |
+
"learning_rate": 6.545084971874738e-06,
|
| 582 |
+
"loss": 0.4659,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.4223246939100016,
|
| 587 |
+
"grad_norm": 0.8249541082696409,
|
| 588 |
+
"learning_rate": 6.466250186922325e-06,
|
| 589 |
+
"loss": 0.4719,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.42741294323421847,
|
| 594 |
+
"grad_norm": 1.726258626642056,
|
| 595 |
+
"learning_rate": 6.387014543809224e-06,
|
| 596 |
+
"loss": 0.4876,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.4325011925584354,
|
| 601 |
+
"grad_norm": 1.8496356628808968,
|
| 602 |
+
"learning_rate": 6.3073997047691e-06,
|
| 603 |
+
"loss": 0.5125,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.43758944188265225,
|
| 608 |
+
"grad_norm": 1.889689508642681,
|
| 609 |
+
"learning_rate": 6.227427435703997e-06,
|
| 610 |
+
"loss": 0.5656,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4426776912068691,
|
| 615 |
+
"grad_norm": 2.214394784133929,
|
| 616 |
+
"learning_rate": 6.147119600233758e-06,
|
| 617 |
+
"loss": 0.5406,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.44776594053108604,
|
| 622 |
+
"grad_norm": 0.8114218652395482,
|
| 623 |
+
"learning_rate": 6.066498153718735e-06,
|
| 624 |
+
"loss": 0.4521,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4528541898553029,
|
| 629 |
+
"grad_norm": 0.7973979099809638,
|
| 630 |
+
"learning_rate": 5.985585137257401e-06,
|
| 631 |
+
"loss": 0.4518,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4579424391795198,
|
| 636 |
+
"grad_norm": 1.8967354755477805,
|
| 637 |
+
"learning_rate": 5.904402671660551e-06,
|
| 638 |
+
"loss": 0.5441,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.4630306885037367,
|
| 643 |
+
"grad_norm": 1.716070744396094,
|
| 644 |
+
"learning_rate": 5.82297295140367e-06,
|
| 645 |
+
"loss": 0.6422,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.46811893782795355,
|
| 650 |
+
"grad_norm": 0.8154244178432215,
|
| 651 |
+
"learning_rate": 5.74131823855921e-06,
|
| 652 |
+
"loss": 0.4769,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.47320718715217047,
|
| 657 |
+
"grad_norm": 1.7620206363802955,
|
| 658 |
+
"learning_rate": 5.659460856710346e-06,
|
| 659 |
+
"loss": 0.4876,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.47829543647638734,
|
| 664 |
+
"grad_norm": 1.8793277177212415,
|
| 665 |
+
"learning_rate": 5.577423184847932e-06,
|
| 666 |
+
"loss": 0.5587,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.48338368580060426,
|
| 671 |
+
"grad_norm": 2.4056618280214623,
|
| 672 |
+
"learning_rate": 5.495227651252315e-06,
|
| 673 |
+
"loss": 0.5282,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.4884719351248211,
|
| 678 |
+
"grad_norm": 1.731399212916782,
|
| 679 |
+
"learning_rate": 5.412896727361663e-06,
|
| 680 |
+
"loss": 0.4832,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.493560184449038,
|
| 685 |
+
"grad_norm": 2.171469635883203,
|
| 686 |
+
"learning_rate": 5.3304529216284974e-06,
|
| 687 |
+
"loss": 0.5406,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.4986484337732549,
|
| 692 |
+
"grad_norm": 0.7396654418690498,
|
| 693 |
+
"learning_rate": 5.247918773366112e-06,
|
| 694 |
+
"loss": 0.4398,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.5037366830974718,
|
| 699 |
+
"grad_norm": 1.9873438409847994,
|
| 700 |
+
"learning_rate": 5.165316846586541e-06,
|
| 701 |
+
"loss": 0.5442,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.5088249324216887,
|
| 706 |
+
"grad_norm": 0.7557871402911565,
|
| 707 |
+
"learning_rate": 5.082669723831793e-06,
|
| 708 |
+
"loss": 0.4461,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.5139131817459055,
|
| 713 |
+
"grad_norm": 1.9632398561160358,
|
| 714 |
+
"learning_rate": 5e-06,
|
| 715 |
+
"loss": 0.657,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.5190014310701224,
|
| 720 |
+
"grad_norm": 2.7445952318033537,
|
| 721 |
+
"learning_rate": 4.917330276168208e-06,
|
| 722 |
+
"loss": 0.5372,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.5240896803943393,
|
| 727 |
+
"grad_norm": 1.9945819420280821,
|
| 728 |
+
"learning_rate": 4.8346831534134595e-06,
|
| 729 |
+
"loss": 0.5031,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5291779297185563,
|
| 734 |
+
"grad_norm": 1.8362856740868725,
|
| 735 |
+
"learning_rate": 4.752081226633888e-06,
|
| 736 |
+
"loss": 0.5084,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.5342661790427731,
|
| 741 |
+
"grad_norm": 2.203070609994655,
|
| 742 |
+
"learning_rate": 4.669547078371503e-06,
|
| 743 |
+
"loss": 0.465,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.53935442836699,
|
| 748 |
+
"grad_norm": 1.892770767378631,
|
| 749 |
+
"learning_rate": 4.587103272638339e-06,
|
| 750 |
+
"loss": 0.5403,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5444426776912069,
|
| 755 |
+
"grad_norm": 1.9456031139611378,
|
| 756 |
+
"learning_rate": 4.504772348747687e-06,
|
| 757 |
+
"loss": 0.49,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5495309270154237,
|
| 762 |
+
"grad_norm": 2.0182884689849514,
|
| 763 |
+
"learning_rate": 4.42257681515207e-06,
|
| 764 |
+
"loss": 0.5333,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5546191763396406,
|
| 769 |
+
"grad_norm": 1.6146872630281819,
|
| 770 |
+
"learning_rate": 4.340539143289655e-06,
|
| 771 |
+
"loss": 0.5149,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5597074256638576,
|
| 776 |
+
"grad_norm": 1.6476137113275473,
|
| 777 |
+
"learning_rate": 4.25868176144079e-06,
|
| 778 |
+
"loss": 0.6769,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5647956749880744,
|
| 783 |
+
"grad_norm": 2.0658942705086423,
|
| 784 |
+
"learning_rate": 4.17702704859633e-06,
|
| 785 |
+
"loss": 0.6019,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5698839243122913,
|
| 790 |
+
"grad_norm": 1.7053065530036995,
|
| 791 |
+
"learning_rate": 4.0955973283394525e-06,
|
| 792 |
+
"loss": 0.502,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5749721736365082,
|
| 797 |
+
"grad_norm": 1.7794992744029052,
|
| 798 |
+
"learning_rate": 4.0144148627426e-06,
|
| 799 |
+
"loss": 0.6971,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5800604229607251,
|
| 804 |
+
"grad_norm": 2.0022976564849118,
|
| 805 |
+
"learning_rate": 3.9335018462812664e-06,
|
| 806 |
+
"loss": 0.61,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5851486722849419,
|
| 811 |
+
"grad_norm": 2.2216074964170307,
|
| 812 |
+
"learning_rate": 3.852880399766243e-06,
|
| 813 |
+
"loss": 0.6448,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.5902369216091589,
|
| 818 |
+
"grad_norm": 2.0218425771246347,
|
| 819 |
+
"learning_rate": 3.7725725642960047e-06,
|
| 820 |
+
"loss": 0.57,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5953251709333758,
|
| 825 |
+
"grad_norm": 1.8270891917131469,
|
| 826 |
+
"learning_rate": 3.6926002952309015e-06,
|
| 827 |
+
"loss": 0.6744,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.6004134202575926,
|
| 832 |
+
"grad_norm": 1.9064779086360353,
|
| 833 |
+
"learning_rate": 3.6129854561907786e-06,
|
| 834 |
+
"loss": 0.5952,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.6055016695818095,
|
| 839 |
+
"grad_norm": 2.0828115564813103,
|
| 840 |
+
"learning_rate": 3.533749813077677e-06,
|
| 841 |
+
"loss": 0.5799,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6105899189060264,
|
| 846 |
+
"grad_norm": 2.355735946808142,
|
| 847 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 848 |
+
"loss": 0.5214,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.6156781682302432,
|
| 853 |
+
"grad_norm": 2.342756754310459,
|
| 854 |
+
"learning_rate": 3.3765026539765832e-06,
|
| 855 |
+
"loss": 0.5773,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.6207664175544602,
|
| 860 |
+
"grad_norm": 1.9448686299055988,
|
| 861 |
+
"learning_rate": 3.298534127791785e-06,
|
| 862 |
+
"loss": 0.4619,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.6258546668786771,
|
| 867 |
+
"grad_norm": 1.6976170484807502,
|
| 868 |
+
"learning_rate": 3.2210307653874175e-06,
|
| 869 |
+
"loss": 0.5038,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6309429162028939,
|
| 874 |
+
"grad_norm": 1.5907623542619864,
|
| 875 |
+
"learning_rate": 3.1440137554088957e-06,
|
| 876 |
+
"loss": 0.5228,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.6360311655271108,
|
| 881 |
+
"grad_norm": 2.1506068679578614,
|
| 882 |
+
"learning_rate": 3.06750415353774e-06,
|
| 883 |
+
"loss": 0.4815,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.6411194148513277,
|
| 888 |
+
"grad_norm": 1.7867004118397054,
|
| 889 |
+
"learning_rate": 2.991522876735154e-06,
|
| 890 |
+
"loss": 0.4804,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.6462076641755446,
|
| 895 |
+
"grad_norm": 1.7461855814609817,
|
| 896 |
+
"learning_rate": 2.9160906975235493e-06,
|
| 897 |
+
"loss": 0.5897,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.6512959134997615,
|
| 902 |
+
"grad_norm": 1.8529499964190723,
|
| 903 |
+
"learning_rate": 2.8412282383075362e-06,
|
| 904 |
+
"loss": 0.5804,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6563841628239784,
|
| 909 |
+
"grad_norm": 1.7011820416779206,
|
| 910 |
+
"learning_rate": 2.766955965735968e-06,
|
| 911 |
+
"loss": 0.3779,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6614724121481953,
|
| 916 |
+
"grad_norm": 2.1878021538228594,
|
| 917 |
+
"learning_rate": 2.693294185106562e-06,
|
| 918 |
+
"loss": 0.5192,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6665606614724121,
|
| 923 |
+
"grad_norm": 1.89071352186738,
|
| 924 |
+
"learning_rate": 2.6202630348146323e-06,
|
| 925 |
+
"loss": 0.4808,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.671648910796629,
|
| 930 |
+
"grad_norm": 1.712076689870655,
|
| 931 |
+
"learning_rate": 2.5478824808474613e-06,
|
| 932 |
+
"loss": 0.4778,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.676737160120846,
|
| 937 |
+
"grad_norm": 2.2979388948141497,
|
| 938 |
+
"learning_rate": 2.476172311325783e-06,
|
| 939 |
+
"loss": 0.5166,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.6818254094450628,
|
| 944 |
+
"grad_norm": 1.8536884054739906,
|
| 945 |
+
"learning_rate": 2.4051521310939258e-06,
|
| 946 |
+
"loss": 0.4676,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6869136587692797,
|
| 951 |
+
"grad_norm": 0.8646900812662967,
|
| 952 |
+
"learning_rate": 2.3348413563600324e-06,
|
| 953 |
+
"loss": 0.4461,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6920019080934966,
|
| 958 |
+
"grad_norm": 2.01928532753317,
|
| 959 |
+
"learning_rate": 2.265259209387867e-06,
|
| 960 |
+
"loss": 0.5068,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6970901574177135,
|
| 965 |
+
"grad_norm": 1.8168602175973523,
|
| 966 |
+
"learning_rate": 2.1964247132416373e-06,
|
| 967 |
+
"loss": 0.4525,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.7021784067419303,
|
| 972 |
+
"grad_norm": 1.7126759434503427,
|
| 973 |
+
"learning_rate": 2.1283566865852824e-06,
|
| 974 |
+
"loss": 0.4317,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.7072666560661472,
|
| 979 |
+
"grad_norm": 1.8291580014900488,
|
| 980 |
+
"learning_rate": 2.061073738537635e-06,
|
| 981 |
+
"loss": 0.4603,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.7123549053903642,
|
| 986 |
+
"grad_norm": 1.724099417960198,
|
| 987 |
+
"learning_rate": 1.9945942635848745e-06,
|
| 988 |
+
"loss": 0.5586,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.717443154714581,
|
| 993 |
+
"grad_norm": 2.1180511181848334,
|
| 994 |
+
"learning_rate": 1.928936436551661e-06,
|
| 995 |
+
"loss": 0.6016,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7225314040387979,
|
| 1000 |
+
"grad_norm": 3.880955775488794,
|
| 1001 |
+
"learning_rate": 1.864118207632315e-06,
|
| 1002 |
+
"loss": 0.4455,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.7276196533630148,
|
| 1007 |
+
"grad_norm": 3.455742706901813,
|
| 1008 |
+
"learning_rate": 1.8001572974834169e-06,
|
| 1009 |
+
"loss": 0.5335,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.7327079026872316,
|
| 1014 |
+
"grad_norm": 2.0932962158103767,
|
| 1015 |
+
"learning_rate": 1.7370711923791567e-06,
|
| 1016 |
+
"loss": 0.5403,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.7377961520114485,
|
| 1021 |
+
"grad_norm": 1.9169862335782764,
|
| 1022 |
+
"learning_rate": 1.6748771394307584e-06,
|
| 1023 |
+
"loss": 0.6151,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.7428844013356655,
|
| 1028 |
+
"grad_norm": 1.6739274256984877,
|
| 1029 |
+
"learning_rate": 1.6135921418712959e-06,
|
| 1030 |
+
"loss": 0.528,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.7479726506598824,
|
| 1035 |
+
"grad_norm": 1.9022344474756825,
|
| 1036 |
+
"learning_rate": 1.5532329544071712e-06,
|
| 1037 |
+
"loss": 0.5573,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.7530608999840992,
|
| 1042 |
+
"grad_norm": 1.9206290312751073,
|
| 1043 |
+
"learning_rate": 1.4938160786375571e-06,
|
| 1044 |
+
"loss": 0.5426,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.7581491493083161,
|
| 1049 |
+
"grad_norm": 0.8151237000504089,
|
| 1050 |
+
"learning_rate": 1.4353577585430152e-06,
|
| 1051 |
+
"loss": 0.476,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.763237398632533,
|
| 1056 |
+
"grad_norm": 1.8174998311715647,
|
| 1057 |
+
"learning_rate": 1.3778739760445552e-06,
|
| 1058 |
+
"loss": 0.6476,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7683256479567498,
|
| 1063 |
+
"grad_norm": 1.8511365294091442,
|
| 1064 |
+
"learning_rate": 1.321380446634342e-06,
|
| 1065 |
+
"loss": 0.6219,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7734138972809668,
|
| 1070 |
+
"grad_norm": 1.9281617529336113,
|
| 1071 |
+
"learning_rate": 1.2658926150792321e-06,
|
| 1072 |
+
"loss": 0.5665,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.7785021466051837,
|
| 1077 |
+
"grad_norm": 1.975480725256036,
|
| 1078 |
+
"learning_rate": 1.2114256511983274e-06,
|
| 1079 |
+
"loss": 0.4917,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.7835903959294005,
|
| 1084 |
+
"grad_norm": 1.881712184210223,
|
| 1085 |
+
"learning_rate": 1.157994445715706e-06,
|
| 1086 |
+
"loss": 0.5117,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7886786452536174,
|
| 1091 |
+
"grad_norm": 1.6096859946428606,
|
| 1092 |
+
"learning_rate": 1.1056136061894386e-06,
|
| 1093 |
+
"loss": 0.4197,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7937668945778343,
|
| 1098 |
+
"grad_norm": 1.5926249355515094,
|
| 1099 |
+
"learning_rate": 1.0542974530180327e-06,
|
| 1100 |
+
"loss": 0.5571,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7988551439020511,
|
| 1105 |
+
"grad_norm": 1.8331014781023134,
|
| 1106 |
+
"learning_rate": 1.0040600155253766e-06,
|
| 1107 |
+
"loss": 0.4837,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.8039433932262681,
|
| 1112 |
+
"grad_norm": 1.7661780666068934,
|
| 1113 |
+
"learning_rate": 9.549150281252633e-07,
|
| 1114 |
+
"loss": 0.6176,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.809031642550485,
|
| 1119 |
+
"grad_norm": 1.6128238891391746,
|
| 1120 |
+
"learning_rate": 9.068759265665384e-07,
|
| 1121 |
+
"loss": 0.4833,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.8141198918747019,
|
| 1126 |
+
"grad_norm": 1.9433571216817562,
|
| 1127 |
+
"learning_rate": 8.599558442598998e-07,
|
| 1128 |
+
"loss": 0.5556,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.8192081411989187,
|
| 1133 |
+
"grad_norm": 0.7908943487803456,
|
| 1134 |
+
"learning_rate": 8.141676086873574e-07,
|
| 1135 |
+
"loss": 0.441,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.8242963905231356,
|
| 1140 |
+
"grad_norm": 1.6159487866825593,
|
| 1141 |
+
"learning_rate": 7.695237378953224e-07,
|
| 1142 |
+
"loss": 0.4325,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.8293846398473526,
|
| 1147 |
+
"grad_norm": 1.7926977872061616,
|
| 1148 |
+
"learning_rate": 7.260364370723044e-07,
|
| 1149 |
+
"loss": 0.4728,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.8344728891715694,
|
| 1154 |
+
"grad_norm": 0.79042068129705,
|
| 1155 |
+
"learning_rate": 6.837175952121305e-07,
|
| 1156 |
+
"loss": 0.4435,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.8395611384957863,
|
| 1161 |
+
"grad_norm": 1.814089246270096,
|
| 1162 |
+
"learning_rate": 6.425787818636131e-07,
|
| 1163 |
+
"loss": 0.5072,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.8446493878200032,
|
| 1168 |
+
"grad_norm": 1.5747711545454517,
|
| 1169 |
+
"learning_rate": 6.026312439675553e-07,
|
| 1170 |
+
"loss": 0.55,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.84973763714422,
|
| 1175 |
+
"grad_norm": 1.8242377149400466,
|
| 1176 |
+
"learning_rate": 5.63885902781941e-07,
|
| 1177 |
+
"loss": 0.421,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.8548258864684369,
|
| 1182 |
+
"grad_norm": 1.953214479706857,
|
| 1183 |
+
"learning_rate": 5.263533508961827e-07,
|
| 1184 |
+
"loss": 0.5901,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.8599141357926539,
|
| 1189 |
+
"grad_norm": 2.2955242802982565,
|
| 1190 |
+
"learning_rate": 4.900438493352056e-07,
|
| 1191 |
+
"loss": 0.531,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.8650023851168708,
|
| 1196 |
+
"grad_norm": 1.790553869422144,
|
| 1197 |
+
"learning_rate": 4.549673247541875e-07,
|
| 1198 |
+
"loss": 0.4578,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.8700906344410876,
|
| 1203 |
+
"grad_norm": 1.9079751423849147,
|
| 1204 |
+
"learning_rate": 4.211333667247125e-07,
|
| 1205 |
+
"loss": 0.6592,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.8751788837653045,
|
| 1210 |
+
"grad_norm": 1.5586622664999814,
|
| 1211 |
+
"learning_rate": 3.885512251130763e-07,
|
| 1212 |
+
"loss": 0.4316,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.8802671330895214,
|
| 1217 |
+
"grad_norm": 2.0693911883749134,
|
| 1218 |
+
"learning_rate": 3.572298075514652e-07,
|
| 1219 |
+
"loss": 0.5547,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.8853553824137382,
|
| 1224 |
+
"grad_norm": 2.3827153776142027,
|
| 1225 |
+
"learning_rate": 3.271776770026963e-07,
|
| 1226 |
+
"loss": 0.5233,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8904436317379552,
|
| 1231 |
+
"grad_norm": 1.726968337714764,
|
| 1232 |
+
"learning_rate": 2.984030494191942e-07,
|
| 1233 |
+
"loss": 0.5607,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.8955318810621721,
|
| 1238 |
+
"grad_norm": 1.678457800822472,
|
| 1239 |
+
"learning_rate": 2.7091379149682683e-07,
|
| 1240 |
+
"loss": 0.5635,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.9006201303863889,
|
| 1245 |
+
"grad_norm": 1.6304062948996085,
|
| 1246 |
+
"learning_rate": 2.447174185242324e-07,
|
| 1247 |
+
"loss": 0.5258,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.9057083797106058,
|
| 1252 |
+
"grad_norm": 1.7913849441660894,
|
| 1253 |
+
"learning_rate": 2.198210923282118e-07,
|
| 1254 |
+
"loss": 0.4812,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.9107966290348227,
|
| 1259 |
+
"grad_norm": 1.7493396501788248,
|
| 1260 |
+
"learning_rate": 1.962316193157593e-07,
|
| 1261 |
+
"loss": 0.5507,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.9158848783590396,
|
| 1266 |
+
"grad_norm": 1.7290444706260146,
|
| 1267 |
+
"learning_rate": 1.7395544861325718e-07,
|
| 1268 |
+
"loss": 0.4838,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.9209731276832565,
|
| 1273 |
+
"grad_norm": 1.8780586855355685,
|
| 1274 |
+
"learning_rate": 1.5299867030334815e-07,
|
| 1275 |
+
"loss": 0.4751,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.9260613770074734,
|
| 1280 |
+
"grad_norm": 1.9905075820968223,
|
| 1281 |
+
"learning_rate": 1.333670137599713e-07,
|
| 1282 |
+
"loss": 0.5576,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.9311496263316903,
|
| 1287 |
+
"grad_norm": 1.4999219259699108,
|
| 1288 |
+
"learning_rate": 1.1506584608200366e-07,
|
| 1289 |
+
"loss": 0.4519,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.9362378756559071,
|
| 1294 |
+
"grad_norm": 2.1199407248983437,
|
| 1295 |
+
"learning_rate": 9.810017062595322e-08,
|
| 1296 |
+
"loss": 0.5988,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.941326124980124,
|
| 1301 |
+
"grad_norm": 1.8067808204066615,
|
| 1302 |
+
"learning_rate": 8.247462563808816e-08,
|
| 1303 |
+
"loss": 0.4948,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.9464143743043409,
|
| 1308 |
+
"grad_norm": 1.763043188246363,
|
| 1309 |
+
"learning_rate": 6.819348298638839e-08,
|
| 1310 |
+
"loss": 0.4795,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.9515026236285578,
|
| 1315 |
+
"grad_norm": 2.057258550991737,
|
| 1316 |
+
"learning_rate": 5.526064699265754e-08,
|
| 1317 |
+
"loss": 0.5685,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.9565908729527747,
|
| 1322 |
+
"grad_norm": 2.4018383293989274,
|
| 1323 |
+
"learning_rate": 4.367965336512403e-08,
|
| 1324 |
+
"loss": 0.4988,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.9616791222769916,
|
| 1329 |
+
"grad_norm": 1.7096952541229,
|
| 1330 |
+
"learning_rate": 3.345366823180929e-08,
|
| 1331 |
+
"loss": 0.4607,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.9667673716012085,
|
| 1336 |
+
"grad_norm": 3.899388264590507,
|
| 1337 |
+
"learning_rate": 2.4585487274942922e-08,
|
| 1338 |
+
"loss": 0.4811,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.9718556209254253,
|
| 1343 |
+
"grad_norm": 2.22640179961524,
|
| 1344 |
+
"learning_rate": 1.7077534966650767e-08,
|
| 1345 |
+
"loss": 0.4044,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.9769438702496422,
|
| 1350 |
+
"grad_norm": 1.5616184108006692,
|
| 1351 |
+
"learning_rate": 1.0931863906127327e-08,
|
| 1352 |
+
"loss": 0.4917,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.9820321195738592,
|
| 1357 |
+
"grad_norm": 1.7256336283483458,
|
| 1358 |
+
"learning_rate": 6.150154258476315e-09,
|
| 1359 |
+
"loss": 0.5599,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.987120368898076,
|
| 1364 |
+
"grad_norm": 2.5414845965873263,
|
| 1365 |
+
"learning_rate": 2.7337132953697555e-09,
|
| 1366 |
+
"loss": 0.4509,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.9922086182222929,
|
| 1371 |
+
"grad_norm": 2.24086616108618,
|
| 1372 |
+
"learning_rate": 6.834750376549793e-10,
|
| 1373 |
+
"loss": 0.5172,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.9972968675465098,
|
| 1378 |
+
"grad_norm": 0.8175454134359621,
|
| 1379 |
+
"learning_rate": 0.0,
|
| 1380 |
+
"loss": 0.4358,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9972968675465098,
|
| 1385 |
+
"step": 196,
|
| 1386 |
+
"total_flos": 46920266465280.0,
|
| 1387 |
+
"train_loss": 0.5706830052088718,
|
| 1388 |
+
"train_runtime": 37228.8328,
|
| 1389 |
+
"train_samples_per_second": 0.676,
|
| 1390 |
+
"train_steps_per_second": 0.005
|
| 1391 |
+
}
|
| 1392 |
+
],
|
| 1393 |
+
"logging_steps": 1.0,
|
| 1394 |
+
"max_steps": 196,
|
| 1395 |
+
"num_input_tokens_seen": 0,
|
| 1396 |
+
"num_train_epochs": 1,
|
| 1397 |
+
"save_steps": 5000.0,
|
| 1398 |
+
"stateful_callbacks": {
|
| 1399 |
+
"TrainerControl": {
|
| 1400 |
+
"args": {
|
| 1401 |
+
"should_epoch_stop": false,
|
| 1402 |
+
"should_evaluate": false,
|
| 1403 |
+
"should_log": false,
|
| 1404 |
+
"should_save": false,
|
| 1405 |
+
"should_training_stop": false
|
| 1406 |
+
},
|
| 1407 |
+
"attributes": {}
|
| 1408 |
+
}
|
| 1409 |
+
},
|
| 1410 |
+
"total_flos": 46920266465280.0,
|
| 1411 |
+
"train_batch_size": 1,
|
| 1412 |
+
"trial_name": null,
|
| 1413 |
+
"trial_params": null
|
| 1414 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c202aadf5b3e8a334f07bc20bf73e78a6d4b16c96e819fe8ddd84aa2f8bbc96
|
| 3 |
+
size 8376
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|