Commit
•
f452abf
1
Parent(s):
f0eb694
Upload folder using huggingface_hub
Browse files- config.json +15 -53
- generation_config.json +2 -2
- pytorch_model-00001-of-00003.bin +3 -0
- pytorch_model-00002-of-00003.bin +3 -0
- pytorch_model-00003-of-00003.bin +3 -0
- pytorch_model.bin.index.json +324 -561
- rng_state_0.pth +1 -1
- rng_state_1.pth +1 -1
- rng_state_2.pth +1 -1
- rng_state_3.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +22 -105
- tokenizer.model +3 -0
- tokenizer_config.json +29 -109
- trainer_state.json +452 -752
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,61 +1,23 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "lmsys/
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"is_gated_act": true,
|
| 17 |
-
"layer_norm_epsilon": 1e-06,
|
| 18 |
-
"model_type": "t5",
|
| 19 |
-
"n_positions": 512,
|
| 20 |
-
"num_decoder_layers": 24,
|
| 21 |
-
"num_heads": 32,
|
| 22 |
-
"num_layers": 24,
|
| 23 |
-
"output_past": true,
|
| 24 |
"pad_token_id": 0,
|
| 25 |
-
"
|
| 26 |
-
"relative_attention_num_buckets": 32,
|
| 27 |
-
"task_specific_params": {
|
| 28 |
-
"summarization": {
|
| 29 |
-
"early_stopping": true,
|
| 30 |
-
"length_penalty": 2.0,
|
| 31 |
-
"max_length": 200,
|
| 32 |
-
"min_length": 30,
|
| 33 |
-
"no_repeat_ngram_size": 3,
|
| 34 |
-
"num_beams": 4,
|
| 35 |
-
"prefix": "summarize: "
|
| 36 |
-
},
|
| 37 |
-
"translation_en_to_de": {
|
| 38 |
-
"early_stopping": true,
|
| 39 |
-
"max_length": 300,
|
| 40 |
-
"num_beams": 4,
|
| 41 |
-
"prefix": "translate English to German: "
|
| 42 |
-
},
|
| 43 |
-
"translation_en_to_fr": {
|
| 44 |
-
"early_stopping": true,
|
| 45 |
-
"max_length": 300,
|
| 46 |
-
"num_beams": 4,
|
| 47 |
-
"prefix": "translate English to French: "
|
| 48 |
-
},
|
| 49 |
-
"translation_en_to_ro": {
|
| 50 |
-
"early_stopping": true,
|
| 51 |
-
"max_length": 300,
|
| 52 |
-
"num_beams": 4,
|
| 53 |
-
"prefix": "translate English to Romanian: "
|
| 54 |
-
}
|
| 55 |
-
},
|
| 56 |
"tie_word_embeddings": false,
|
| 57 |
"torch_dtype": "float32",
|
| 58 |
"transformers_version": "4.28.1",
|
| 59 |
-
"use_cache":
|
| 60 |
-
"vocab_size":
|
| 61 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "lmsys/vicuna-7b-v1.3",
|
| 3 |
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"pad_token_id": 0,
|
| 17 |
+
"rms_norm_eps": 1e-06,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
"tie_word_embeddings": false,
|
| 19 |
"torch_dtype": "float32",
|
| 20 |
"transformers_version": "4.28.1",
|
| 21 |
+
"use_cache": false,
|
| 22 |
+
"vocab_size": 32000
|
| 23 |
}
|
generation_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"
|
| 4 |
-
"eos_token_id":
|
| 5 |
"pad_token_id": 0,
|
| 6 |
"transformers_version": "4.28.1"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
"transformers_version": "4.28.1"
|
| 7 |
}
|
pytorch_model-00001-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2403c0246b7c95b8ff32b84bff67ee4411e331d98ebea8a13f7ea23197c91410
|
| 3 |
+
size 9877993490
|
pytorch_model-00002-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da5be4f0bec4194afbeb22992907940f2795323555bf12758dc310ea16bdc57c
|
| 3 |
+
size 9894805046
|
pytorch_model-00003-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5a57b1c09c0a633885c66777e2add57cd5f3c8582c91f21e7ea5ca4fb19f939
|
| 3 |
+
size 7180993529
|
pytorch_model.bin.index.json
CHANGED
|
@@ -1,567 +1,330 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
"
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"
|
| 85 |
-
"
|
| 86 |
-
"
|
| 87 |
-
"
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
"
|
| 93 |
-
"
|
| 94 |
-
"
|
| 95 |
-
"
|
| 96 |
-
"
|
| 97 |
-
"
|
| 98 |
-
"
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"
|
| 102 |
-
"
|
| 103 |
-
"
|
| 104 |
-
"
|
| 105 |
-
"
|
| 106 |
-
"
|
| 107 |
-
"
|
| 108 |
-
"
|
| 109 |
-
"
|
| 110 |
-
"
|
| 111 |
-
"
|
| 112 |
-
"
|
| 113 |
-
"
|
| 114 |
-
"
|
| 115 |
-
"
|
| 116 |
-
"
|
| 117 |
-
"
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
-
"
|
| 121 |
-
"
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
-
"
|
| 125 |
-
"
|
| 126 |
-
"
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
-
"
|
| 131 |
-
"
|
| 132 |
-
"
|
| 133 |
-
"
|
| 134 |
-
"
|
| 135 |
-
"
|
| 136 |
-
"
|
| 137 |
-
"
|
| 138 |
-
"
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
"
|
| 142 |
-
"
|
| 143 |
-
"
|
| 144 |
-
"
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"
|
| 148 |
-
"
|
| 149 |
-
"
|
| 150 |
-
"
|
| 151 |
-
"
|
| 152 |
-
"
|
| 153 |
-
"
|
| 154 |
-
"
|
| 155 |
-
"
|
| 156 |
-
"
|
| 157 |
-
"
|
| 158 |
-
"
|
| 159 |
-
"
|
| 160 |
-
"
|
| 161 |
-
"
|
| 162 |
-
"
|
| 163 |
-
"
|
| 164 |
-
"
|
| 165 |
-
"
|
| 166 |
-
"
|
| 167 |
-
"
|
| 168 |
-
"
|
| 169 |
-
"
|
| 170 |
-
"
|
| 171 |
-
"
|
| 172 |
-
"
|
| 173 |
-
"
|
| 174 |
-
"
|
| 175 |
-
"
|
| 176 |
-
"
|
| 177 |
-
"
|
| 178 |
-
"
|
| 179 |
-
"
|
| 180 |
-
"
|
| 181 |
-
"
|
| 182 |
-
"
|
| 183 |
-
"
|
| 184 |
-
"
|
| 185 |
-
"
|
| 186 |
-
"
|
| 187 |
-
"
|
| 188 |
-
"
|
| 189 |
-
"
|
| 190 |
-
"
|
| 191 |
-
"
|
| 192 |
-
"
|
| 193 |
-
"
|
| 194 |
-
"
|
| 195 |
-
"
|
| 196 |
-
"
|
| 197 |
-
"
|
| 198 |
-
"
|
| 199 |
-
"
|
| 200 |
-
"
|
| 201 |
-
"
|
| 202 |
-
"
|
| 203 |
-
"
|
| 204 |
-
"
|
| 205 |
-
"
|
| 206 |
-
"
|
| 207 |
-
"
|
| 208 |
-
"
|
| 209 |
-
"
|
| 210 |
-
"
|
| 211 |
-
"
|
| 212 |
-
"
|
| 213 |
-
"
|
| 214 |
-
"
|
| 215 |
-
"
|
| 216 |
-
"
|
| 217 |
-
"
|
| 218 |
-
"
|
| 219 |
-
"
|
| 220 |
-
"
|
| 221 |
-
"
|
| 222 |
-
"
|
| 223 |
-
"
|
| 224 |
-
"
|
| 225 |
-
"
|
| 226 |
-
"
|
| 227 |
-
"
|
| 228 |
-
"
|
| 229 |
-
"
|
| 230 |
-
"
|
| 231 |
-
"
|
| 232 |
-
"
|
| 233 |
-
"
|
| 234 |
-
"
|
| 235 |
-
"
|
| 236 |
-
"
|
| 237 |
-
"
|
| 238 |
-
"
|
| 239 |
-
"
|
| 240 |
-
"
|
| 241 |
-
"
|
| 242 |
-
"
|
| 243 |
-
"
|
| 244 |
-
"
|
| 245 |
-
"
|
| 246 |
-
"
|
| 247 |
-
"
|
| 248 |
-
"
|
| 249 |
-
"
|
| 250 |
-
"
|
| 251 |
-
"
|
| 252 |
-
"
|
| 253 |
-
"
|
| 254 |
-
"
|
| 255 |
-
"
|
| 256 |
-
"
|
| 257 |
-
"
|
| 258 |
-
"
|
| 259 |
-
"
|
| 260 |
-
"
|
| 261 |
-
"
|
| 262 |
-
"
|
| 263 |
-
"
|
| 264 |
-
"
|
| 265 |
-
"
|
| 266 |
-
"
|
| 267 |
-
"
|
| 268 |
-
"
|
| 269 |
-
"
|
| 270 |
-
"
|
| 271 |
-
"
|
| 272 |
-
"
|
| 273 |
-
"
|
| 274 |
-
"
|
| 275 |
-
"
|
| 276 |
-
"
|
| 277 |
-
"
|
| 278 |
-
"
|
| 279 |
-
"
|
| 280 |
-
"
|
| 281 |
-
"
|
| 282 |
-
"
|
| 283 |
-
"
|
| 284 |
-
"
|
| 285 |
-
"
|
| 286 |
-
"
|
| 287 |
-
"
|
| 288 |
-
"
|
| 289 |
-
"
|
| 290 |
-
"
|
| 291 |
-
"
|
| 292 |
-
"
|
| 293 |
-
"
|
| 294 |
-
"
|
| 295 |
-
"
|
| 296 |
-
"
|
| 297 |
-
"
|
| 298 |
-
"
|
| 299 |
-
"
|
| 300 |
-
"
|
| 301 |
-
"
|
| 302 |
-
"
|
| 303 |
-
"
|
| 304 |
-
"
|
| 305 |
-
"
|
| 306 |
-
"
|
| 307 |
-
"
|
| 308 |
-
"
|
| 309 |
-
"
|
| 310 |
-
"
|
| 311 |
-
"
|
| 312 |
-
"
|
| 313 |
-
"
|
| 314 |
-
"
|
| 315 |
-
"
|
| 316 |
-
"
|
| 317 |
-
"
|
| 318 |
-
"
|
| 319 |
-
"
|
| 320 |
-
"
|
| 321 |
-
"
|
| 322 |
-
"
|
| 323 |
-
"
|
| 324 |
-
"
|
| 325 |
-
"
|
| 326 |
-
"
|
| 327 |
-
"
|
| 328 |
-
"
|
| 329 |
-
"decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 330 |
-
"decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 331 |
-
"decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 332 |
-
"decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 333 |
-
"decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 334 |
-
"decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 335 |
-
"decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 336 |
-
"decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 337 |
-
"decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 338 |
-
"decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 339 |
-
"decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 340 |
-
"decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 341 |
-
"decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 342 |
-
"decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 343 |
-
"decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
| 344 |
-
"decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 345 |
-
"encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 346 |
-
"encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 347 |
-
"encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 348 |
-
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
|
| 349 |
-
"encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 350 |
-
"encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 351 |
-
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 352 |
-
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 353 |
-
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 354 |
-
"encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 355 |
-
"encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 356 |
-
"encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 357 |
-
"encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 358 |
-
"encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 359 |
-
"encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 360 |
-
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 361 |
-
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 362 |
-
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 363 |
-
"encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 364 |
-
"encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 365 |
-
"encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 366 |
-
"encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 367 |
-
"encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 368 |
-
"encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 369 |
-
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 370 |
-
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 371 |
-
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 372 |
-
"encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 373 |
-
"encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 374 |
-
"encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 375 |
-
"encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 376 |
-
"encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 377 |
-
"encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 378 |
-
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 379 |
-
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 380 |
-
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 381 |
-
"encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 382 |
-
"encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 383 |
-
"encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 384 |
-
"encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 385 |
-
"encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 386 |
-
"encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 387 |
-
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 388 |
-
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 389 |
-
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 390 |
-
"encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 391 |
-
"encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 392 |
-
"encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 393 |
-
"encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 394 |
-
"encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 395 |
-
"encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 396 |
-
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 397 |
-
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 398 |
-
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 399 |
-
"encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 400 |
-
"encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 401 |
-
"encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 402 |
-
"encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 403 |
-
"encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 404 |
-
"encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 405 |
-
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 406 |
-
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 407 |
-
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 408 |
-
"encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 409 |
-
"encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 410 |
-
"encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 411 |
-
"encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 412 |
-
"encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 413 |
-
"encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 414 |
-
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 415 |
-
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 416 |
-
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 417 |
-
"encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 418 |
-
"encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 419 |
-
"encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 420 |
-
"encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 421 |
-
"encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 422 |
-
"encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 423 |
-
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 424 |
-
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 425 |
-
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 426 |
-
"encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 427 |
-
"encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 428 |
-
"encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 429 |
-
"encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 430 |
-
"encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 431 |
-
"encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 432 |
-
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 433 |
-
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 434 |
-
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 435 |
-
"encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 436 |
-
"encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 437 |
-
"encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 438 |
-
"encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 439 |
-
"encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 440 |
-
"encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 441 |
-
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 442 |
-
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 443 |
-
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 444 |
-
"encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 445 |
-
"encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 446 |
-
"encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 447 |
-
"encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 448 |
-
"encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 449 |
-
"encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 450 |
-
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 451 |
-
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 452 |
-
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 453 |
-
"encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 454 |
-
"encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 455 |
-
"encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 456 |
-
"encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 457 |
-
"encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 458 |
-
"encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 459 |
-
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 460 |
-
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 461 |
-
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 462 |
-
"encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 463 |
-
"encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 464 |
-
"encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 465 |
-
"encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 466 |
-
"encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 467 |
-
"encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 468 |
-
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 469 |
-
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 470 |
-
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 471 |
-
"encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 472 |
-
"encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 473 |
-
"encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 474 |
-
"encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 475 |
-
"encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 476 |
-
"encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 477 |
-
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 478 |
-
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 479 |
-
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 480 |
-
"encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 481 |
-
"encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 482 |
-
"encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 483 |
-
"encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 484 |
-
"encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 485 |
-
"encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 486 |
-
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 487 |
-
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 488 |
-
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 489 |
-
"encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 490 |
-
"encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 491 |
-
"encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 492 |
-
"encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 493 |
-
"encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 494 |
-
"encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 495 |
-
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 496 |
-
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 497 |
-
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 498 |
-
"encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 499 |
-
"encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 500 |
-
"encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 501 |
-
"encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 502 |
-
"encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 503 |
-
"encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 504 |
-
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 505 |
-
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 506 |
-
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 507 |
-
"encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 508 |
-
"encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 509 |
-
"encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 510 |
-
"encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 511 |
-
"encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 512 |
-
"encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 513 |
-
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 514 |
-
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 515 |
-
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 516 |
-
"encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 517 |
-
"encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 518 |
-
"encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 519 |
-
"encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 520 |
-
"encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 521 |
-
"encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 522 |
-
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 523 |
-
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 524 |
-
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 525 |
-
"encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 526 |
-
"encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 527 |
-
"encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 528 |
-
"encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 529 |
-
"encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 530 |
-
"encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 531 |
-
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 532 |
-
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 533 |
-
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 534 |
-
"encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 535 |
-
"encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 536 |
-
"encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 537 |
-
"encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 538 |
-
"encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 539 |
-
"encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 540 |
-
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 541 |
-
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 542 |
-
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 543 |
-
"encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 544 |
-
"encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 545 |
-
"encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 546 |
-
"encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 547 |
-
"encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 548 |
-
"encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 549 |
-
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 550 |
-
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 551 |
-
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 552 |
-
"encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 553 |
-
"encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 554 |
-
"encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 555 |
-
"encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 556 |
-
"encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 557 |
-
"encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 558 |
-
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 559 |
-
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 560 |
-
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 561 |
-
"encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 562 |
-
"encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
| 563 |
-
"encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 564 |
-
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
| 565 |
-
"shared.weight": "pytorch_model-00001-of-00002.bin"
|
| 566 |
}
|
| 567 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 26953670656
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 328 |
+
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 329 |
}
|
| 330 |
}
|
rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e75c96f06b249e57a701db73ce821398e69672027a86d3a44063830602a29ab4
|
| 3 |
size 14583
|
rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dae7f45b6bac644ac207a61f43cba6d4b919a4cac22022bbb02907914422f5d
|
| 3 |
size 14583
|
rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e53c770fe48635faad7fa341007d771781f1397cd47daab5b58f879ffb65f178
|
| 3 |
size 14583
|
rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68692af1001e65d02e07ac9974ccf4c332cfb23bc8f89566e1a908b1f2c4a1ed
|
| 3 |
size 14583
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8078ef448b63bb065c755468450481cc618ba517b813fe5d1dc3d2326638dd4f
|
| 3 |
size 627
|
special_tokens_map.json
CHANGED
|
@@ -1,107 +1,24 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"<
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
"<
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
|
| 24 |
-
"<extra_id_21>",
|
| 25 |
-
"<extra_id_22>",
|
| 26 |
-
"<extra_id_23>",
|
| 27 |
-
"<extra_id_24>",
|
| 28 |
-
"<extra_id_25>",
|
| 29 |
-
"<extra_id_26>",
|
| 30 |
-
"<extra_id_27>",
|
| 31 |
-
"<extra_id_28>",
|
| 32 |
-
"<extra_id_29>",
|
| 33 |
-
"<extra_id_30>",
|
| 34 |
-
"<extra_id_31>",
|
| 35 |
-
"<extra_id_32>",
|
| 36 |
-
"<extra_id_33>",
|
| 37 |
-
"<extra_id_34>",
|
| 38 |
-
"<extra_id_35>",
|
| 39 |
-
"<extra_id_36>",
|
| 40 |
-
"<extra_id_37>",
|
| 41 |
-
"<extra_id_38>",
|
| 42 |
-
"<extra_id_39>",
|
| 43 |
-
"<extra_id_40>",
|
| 44 |
-
"<extra_id_41>",
|
| 45 |
-
"<extra_id_42>",
|
| 46 |
-
"<extra_id_43>",
|
| 47 |
-
"<extra_id_44>",
|
| 48 |
-
"<extra_id_45>",
|
| 49 |
-
"<extra_id_46>",
|
| 50 |
-
"<extra_id_47>",
|
| 51 |
-
"<extra_id_48>",
|
| 52 |
-
"<extra_id_49>",
|
| 53 |
-
"<extra_id_50>",
|
| 54 |
-
"<extra_id_51>",
|
| 55 |
-
"<extra_id_52>",
|
| 56 |
-
"<extra_id_53>",
|
| 57 |
-
"<extra_id_54>",
|
| 58 |
-
"<extra_id_55>",
|
| 59 |
-
"<extra_id_56>",
|
| 60 |
-
"<extra_id_57>",
|
| 61 |
-
"<extra_id_58>",
|
| 62 |
-
"<extra_id_59>",
|
| 63 |
-
"<extra_id_60>",
|
| 64 |
-
"<extra_id_61>",
|
| 65 |
-
"<extra_id_62>",
|
| 66 |
-
"<extra_id_63>",
|
| 67 |
-
"<extra_id_64>",
|
| 68 |
-
"<extra_id_65>",
|
| 69 |
-
"<extra_id_66>",
|
| 70 |
-
"<extra_id_67>",
|
| 71 |
-
"<extra_id_68>",
|
| 72 |
-
"<extra_id_69>",
|
| 73 |
-
"<extra_id_70>",
|
| 74 |
-
"<extra_id_71>",
|
| 75 |
-
"<extra_id_72>",
|
| 76 |
-
"<extra_id_73>",
|
| 77 |
-
"<extra_id_74>",
|
| 78 |
-
"<extra_id_75>",
|
| 79 |
-
"<extra_id_76>",
|
| 80 |
-
"<extra_id_77>",
|
| 81 |
-
"<extra_id_78>",
|
| 82 |
-
"<extra_id_79>",
|
| 83 |
-
"<extra_id_80>",
|
| 84 |
-
"<extra_id_81>",
|
| 85 |
-
"<extra_id_82>",
|
| 86 |
-
"<extra_id_83>",
|
| 87 |
-
"<extra_id_84>",
|
| 88 |
-
"<extra_id_85>",
|
| 89 |
-
"<extra_id_86>",
|
| 90 |
-
"<extra_id_87>",
|
| 91 |
-
"<extra_id_88>",
|
| 92 |
-
"<extra_id_89>",
|
| 93 |
-
"<extra_id_90>",
|
| 94 |
-
"<extra_id_91>",
|
| 95 |
-
"<extra_id_92>",
|
| 96 |
-
"<extra_id_93>",
|
| 97 |
-
"<extra_id_94>",
|
| 98 |
-
"<extra_id_95>",
|
| 99 |
-
"<extra_id_96>",
|
| 100 |
-
"<extra_id_97>",
|
| 101 |
-
"<extra_id_98>",
|
| 102 |
-
"<extra_id_99>"
|
| 103 |
-
],
|
| 104 |
-
"eos_token": "</s>",
|
| 105 |
-
"pad_token": "[PAD]",
|
| 106 |
-
"unk_token": "<unk>"
|
| 107 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
CHANGED
|
@@ -1,114 +1,34 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"
|
| 6 |
-
"<
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
|
| 21 |
-
"<extra_id_18>",
|
| 22 |
-
"<extra_id_19>",
|
| 23 |
-
"<extra_id_20>",
|
| 24 |
-
"<extra_id_21>",
|
| 25 |
-
"<extra_id_22>",
|
| 26 |
-
"<extra_id_23>",
|
| 27 |
-
"<extra_id_24>",
|
| 28 |
-
"<extra_id_25>",
|
| 29 |
-
"<extra_id_26>",
|
| 30 |
-
"<extra_id_27>",
|
| 31 |
-
"<extra_id_28>",
|
| 32 |
-
"<extra_id_29>",
|
| 33 |
-
"<extra_id_30>",
|
| 34 |
-
"<extra_id_31>",
|
| 35 |
-
"<extra_id_32>",
|
| 36 |
-
"<extra_id_33>",
|
| 37 |
-
"<extra_id_34>",
|
| 38 |
-
"<extra_id_35>",
|
| 39 |
-
"<extra_id_36>",
|
| 40 |
-
"<extra_id_37>",
|
| 41 |
-
"<extra_id_38>",
|
| 42 |
-
"<extra_id_39>",
|
| 43 |
-
"<extra_id_40>",
|
| 44 |
-
"<extra_id_41>",
|
| 45 |
-
"<extra_id_42>",
|
| 46 |
-
"<extra_id_43>",
|
| 47 |
-
"<extra_id_44>",
|
| 48 |
-
"<extra_id_45>",
|
| 49 |
-
"<extra_id_46>",
|
| 50 |
-
"<extra_id_47>",
|
| 51 |
-
"<extra_id_48>",
|
| 52 |
-
"<extra_id_49>",
|
| 53 |
-
"<extra_id_50>",
|
| 54 |
-
"<extra_id_51>",
|
| 55 |
-
"<extra_id_52>",
|
| 56 |
-
"<extra_id_53>",
|
| 57 |
-
"<extra_id_54>",
|
| 58 |
-
"<extra_id_55>",
|
| 59 |
-
"<extra_id_56>",
|
| 60 |
-
"<extra_id_57>",
|
| 61 |
-
"<extra_id_58>",
|
| 62 |
-
"<extra_id_59>",
|
| 63 |
-
"<extra_id_60>",
|
| 64 |
-
"<extra_id_61>",
|
| 65 |
-
"<extra_id_62>",
|
| 66 |
-
"<extra_id_63>",
|
| 67 |
-
"<extra_id_64>",
|
| 68 |
-
"<extra_id_65>",
|
| 69 |
-
"<extra_id_66>",
|
| 70 |
-
"<extra_id_67>",
|
| 71 |
-
"<extra_id_68>",
|
| 72 |
-
"<extra_id_69>",
|
| 73 |
-
"<extra_id_70>",
|
| 74 |
-
"<extra_id_71>",
|
| 75 |
-
"<extra_id_72>",
|
| 76 |
-
"<extra_id_73>",
|
| 77 |
-
"<extra_id_74>",
|
| 78 |
-
"<extra_id_75>",
|
| 79 |
-
"<extra_id_76>",
|
| 80 |
-
"<extra_id_77>",
|
| 81 |
-
"<extra_id_78>",
|
| 82 |
-
"<extra_id_79>",
|
| 83 |
-
"<extra_id_80>",
|
| 84 |
-
"<extra_id_81>",
|
| 85 |
-
"<extra_id_82>",
|
| 86 |
-
"<extra_id_83>",
|
| 87 |
-
"<extra_id_84>",
|
| 88 |
-
"<extra_id_85>",
|
| 89 |
-
"<extra_id_86>",
|
| 90 |
-
"<extra_id_87>",
|
| 91 |
-
"<extra_id_88>",
|
| 92 |
-
"<extra_id_89>",
|
| 93 |
-
"<extra_id_90>",
|
| 94 |
-
"<extra_id_91>",
|
| 95 |
-
"<extra_id_92>",
|
| 96 |
-
"<extra_id_93>",
|
| 97 |
-
"<extra_id_94>",
|
| 98 |
-
"<extra_id_95>",
|
| 99 |
-
"<extra_id_96>",
|
| 100 |
-
"<extra_id_97>",
|
| 101 |
-
"<extra_id_98>",
|
| 102 |
-
"<extra_id_99>"
|
| 103 |
-
],
|
| 104 |
-
"clean_up_tokenization_spaces": true,
|
| 105 |
-
"eos_token": "</s>",
|
| 106 |
-
"extra_ids": 100,
|
| 107 |
"model_max_length": 2048,
|
| 108 |
-
"pad_token":
|
| 109 |
"padding_side": "right",
|
| 110 |
"sp_model_kwargs": {},
|
| 111 |
-
"tokenizer_class": "
|
| 112 |
-
"unk_token":
|
| 113 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"model_max_length": 2048,
|
| 22 |
+
"pad_token": null,
|
| 23 |
"padding_side": "right",
|
| 24 |
"sp_model_kwargs": {},
|
| 25 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"__type": "AddedToken",
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1216 +1,916 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.0,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 1.
|
| 14 |
"step": 1
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.0,
|
| 18 |
-
"learning_rate": 1.
|
| 19 |
-
"loss": 1.
|
| 20 |
"step": 2
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 1.
|
| 26 |
"step": 3
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate": 2.
|
| 31 |
-
"loss":
|
| 32 |
"step": 4
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss":
|
| 38 |
"step": 5
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 6
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 1.
|
| 50 |
"step": 7
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch": 0.
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 1.
|
| 56 |
"step": 8
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch": 0.
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss":
|
| 62 |
"step": 9
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch": 0.
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 1.
|
| 68 |
"step": 10
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch": 0.
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 1.
|
| 74 |
"step": 11
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 0.
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss":
|
| 80 |
"step": 12
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 1.
|
| 86 |
"step": 13
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss":
|
| 92 |
"step": 14
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 0.
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss":
|
| 98 |
"step": 15
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 0.
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss":
|
| 104 |
"step": 16
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch": 0.
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss":
|
| 110 |
"step": 17
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch": 0.
|
| 114 |
-
"learning_rate": 1.
|
| 115 |
-
"loss":
|
| 116 |
"step": 18
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 0.
|
| 120 |
-
"learning_rate": 1.
|
| 121 |
-
"loss":
|
| 122 |
"step": 19
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 0.
|
| 126 |
-
"learning_rate": 1.
|
| 127 |
-
"loss":
|
| 128 |
"step": 20
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"learning_rate": 1.
|
| 133 |
-
"loss":
|
| 134 |
"step": 21
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 0.
|
| 138 |
-
"learning_rate": 1.
|
| 139 |
-
"loss":
|
| 140 |
"step": 22
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch": 0.
|
| 144 |
-
"learning_rate": 1.
|
| 145 |
-
"loss":
|
| 146 |
"step": 23
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch": 0.
|
| 150 |
-
"learning_rate": 1.
|
| 151 |
-
"loss":
|
| 152 |
"step": 24
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch": 0.
|
| 156 |
-
"learning_rate": 1.
|
| 157 |
-
"loss":
|
| 158 |
"step": 25
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch": 0.
|
| 162 |
-
"learning_rate": 1.
|
| 163 |
-
"loss":
|
| 164 |
"step": 26
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 0.
|
| 168 |
-
"learning_rate": 1.
|
| 169 |
-
"loss":
|
| 170 |
"step": 27
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"learning_rate": 1.
|
| 175 |
-
"loss":
|
| 176 |
"step": 28
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch": 0.
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss":
|
| 182 |
"step": 29
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch": 0.
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss":
|
| 188 |
"step": 30
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch": 0.
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss":
|
| 194 |
"step": 31
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch": 0.
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss":
|
| 200 |
"step": 32
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch": 0.
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss":
|
| 206 |
"step": 33
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch": 0.
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss":
|
| 212 |
"step": 34
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 0.
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss":
|
| 218 |
"step": 35
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch": 0.
|
| 222 |
-
"learning_rate": 2.
|
| 223 |
-
"loss":
|
| 224 |
"step": 36
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch": 0.
|
| 228 |
-
"learning_rate": 2.
|
| 229 |
-
"loss":
|
| 230 |
"step": 37
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch": 0.
|
| 234 |
-
"learning_rate": 2.
|
| 235 |
-
"loss":
|
| 236 |
"step": 38
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch": 0.
|
| 240 |
-
"learning_rate": 2.
|
| 241 |
-
"loss":
|
| 242 |
"step": 39
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch": 0.
|
| 246 |
-
"learning_rate": 2.
|
| 247 |
-
"loss":
|
| 248 |
"step": 40
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch": 0.
|
| 252 |
-
"learning_rate": 2.
|
| 253 |
-
"loss":
|
| 254 |
"step": 41
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch": 0.
|
| 258 |
-
"learning_rate": 2.
|
| 259 |
-
"loss":
|
| 260 |
"step": 42
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch": 0.
|
| 264 |
-
"learning_rate":
|
| 265 |
-
"loss":
|
| 266 |
"step": 43
|
| 267 |
},
|
| 268 |
{
|
| 269 |
-
"epoch": 0.
|
| 270 |
-
"learning_rate":
|
| 271 |
-
"loss":
|
| 272 |
"step": 44
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch": 0.
|
| 276 |
-
"learning_rate":
|
| 277 |
-
"loss":
|
| 278 |
"step": 45
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch": 0.
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss":
|
| 284 |
"step": 46
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch": 0.
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss":
|
| 290 |
"step": 47
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"epoch": 0.
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss":
|
| 296 |
"step": 48
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch": 0.
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss":
|
| 302 |
"step": 49
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch": 0.
|
| 306 |
-
"learning_rate":
|
| 307 |
-
"loss":
|
| 308 |
"step": 50
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch": 0.
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss":
|
| 314 |
"step": 51
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch": 0.
|
| 318 |
-
"learning_rate":
|
| 319 |
-
"loss":
|
| 320 |
"step": 52
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch": 0.
|
| 324 |
-
"learning_rate": 3.
|
| 325 |
-
"loss":
|
| 326 |
"step": 53
|
| 327 |
},
|
| 328 |
{
|
| 329 |
-
"epoch": 0.
|
| 330 |
-
"learning_rate": 3.
|
| 331 |
-
"loss":
|
| 332 |
"step": 54
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch": 0.
|
| 336 |
-
"learning_rate": 3.
|
| 337 |
-
"loss":
|
| 338 |
"step": 55
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch": 0.
|
| 342 |
-
"learning_rate": 3.
|
| 343 |
-
"loss":
|
| 344 |
"step": 56
|
| 345 |
},
|
| 346 |
{
|
| 347 |
-
"epoch": 0.
|
| 348 |
-
"learning_rate": 3.
|
| 349 |
-
"loss":
|
| 350 |
"step": 57
|
| 351 |
},
|
| 352 |
{
|
| 353 |
-
"epoch": 0.
|
| 354 |
-
"learning_rate":
|
| 355 |
-
"loss":
|
| 356 |
"step": 58
|
| 357 |
},
|
| 358 |
{
|
| 359 |
-
"epoch": 0.
|
| 360 |
-
"learning_rate":
|
| 361 |
-
"loss":
|
| 362 |
"step": 59
|
| 363 |
},
|
| 364 |
{
|
| 365 |
-
"epoch": 0.
|
| 366 |
-
"learning_rate":
|
| 367 |
-
"loss":
|
| 368 |
"step": 60
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch": 0.
|
| 372 |
-
"learning_rate":
|
| 373 |
-
"loss":
|
| 374 |
"step": 61
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch": 0.
|
| 378 |
-
"learning_rate":
|
| 379 |
-
"loss":
|
| 380 |
"step": 62
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch": 0.
|
| 384 |
-
"learning_rate":
|
| 385 |
-
"loss":
|
| 386 |
"step": 63
|
| 387 |
},
|
| 388 |
{
|
| 389 |
-
"epoch": 0.
|
| 390 |
-
"learning_rate":
|
| 391 |
-
"loss":
|
| 392 |
"step": 64
|
| 393 |
},
|
| 394 |
{
|
| 395 |
-
"epoch": 0.
|
| 396 |
-
"learning_rate":
|
| 397 |
-
"loss":
|
| 398 |
"step": 65
|
| 399 |
},
|
| 400 |
{
|
| 401 |
-
"epoch": 0.
|
| 402 |
-
"learning_rate":
|
| 403 |
-
"loss":
|
| 404 |
"step": 66
|
| 405 |
},
|
| 406 |
{
|
| 407 |
-
"epoch": 0.
|
| 408 |
-
"learning_rate":
|
| 409 |
-
"loss":
|
| 410 |
"step": 67
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"epoch": 0.
|
| 414 |
-
"learning_rate":
|
| 415 |
-
"loss":
|
| 416 |
"step": 68
|
| 417 |
},
|
| 418 |
{
|
| 419 |
-
"epoch": 0.
|
| 420 |
-
"learning_rate":
|
| 421 |
-
"loss":
|
| 422 |
"step": 69
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch": 0.
|
| 426 |
-
"learning_rate":
|
| 427 |
-
"loss":
|
| 428 |
"step": 70
|
| 429 |
},
|
| 430 |
{
|
| 431 |
-
"epoch": 0.
|
| 432 |
-
"learning_rate": 4.
|
| 433 |
-
"loss":
|
| 434 |
"step": 71
|
| 435 |
},
|
| 436 |
{
|
| 437 |
-
"epoch": 0.
|
| 438 |
-
"learning_rate":
|
| 439 |
-
"loss":
|
| 440 |
"step": 72
|
| 441 |
},
|
| 442 |
{
|
| 443 |
-
"epoch": 0.
|
| 444 |
-
"learning_rate":
|
| 445 |
-
"loss":
|
| 446 |
"step": 73
|
| 447 |
},
|
| 448 |
{
|
| 449 |
-
"epoch": 0.
|
| 450 |
-
"learning_rate":
|
| 451 |
-
"loss":
|
| 452 |
"step": 74
|
| 453 |
},
|
| 454 |
{
|
| 455 |
-
"epoch": 0.
|
| 456 |
-
"learning_rate":
|
| 457 |
-
"loss":
|
| 458 |
"step": 75
|
| 459 |
},
|
| 460 |
{
|
| 461 |
-
"epoch": 0.
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss":
|
| 464 |
"step": 76
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch": 0.
|
| 468 |
-
"learning_rate":
|
| 469 |
-
"loss":
|
| 470 |
"step": 77
|
| 471 |
},
|
| 472 |
{
|
| 473 |
-
"epoch": 0.
|
| 474 |
-
"learning_rate":
|
| 475 |
-
"loss":
|
| 476 |
"step": 78
|
| 477 |
},
|
| 478 |
{
|
| 479 |
-
"epoch": 0.
|
| 480 |
-
"learning_rate":
|
| 481 |
-
"loss":
|
| 482 |
"step": 79
|
| 483 |
},
|
| 484 |
{
|
| 485 |
-
"epoch": 0.
|
| 486 |
-
"learning_rate":
|
| 487 |
-
"loss":
|
| 488 |
"step": 80
|
| 489 |
},
|
| 490 |
{
|
| 491 |
-
"epoch": 0.
|
| 492 |
-
"learning_rate":
|
| 493 |
-
"loss":
|
| 494 |
"step": 81
|
| 495 |
},
|
| 496 |
{
|
| 497 |
-
"epoch": 0.
|
| 498 |
-
"learning_rate":
|
| 499 |
-
"loss":
|
| 500 |
"step": 82
|
| 501 |
},
|
| 502 |
{
|
| 503 |
-
"epoch": 0.
|
| 504 |
-
"learning_rate":
|
| 505 |
-
"loss":
|
| 506 |
"step": 83
|
| 507 |
},
|
| 508 |
{
|
| 509 |
-
"epoch": 0.
|
| 510 |
-
"learning_rate":
|
| 511 |
-
"loss":
|
| 512 |
"step": 84
|
| 513 |
},
|
| 514 |
{
|
| 515 |
-
"epoch": 0.
|
| 516 |
-
"learning_rate":
|
| 517 |
-
"loss":
|
| 518 |
"step": 85
|
| 519 |
},
|
| 520 |
{
|
| 521 |
-
"epoch": 0.
|
| 522 |
-
"learning_rate":
|
| 523 |
-
"loss":
|
| 524 |
"step": 86
|
| 525 |
},
|
| 526 |
{
|
| 527 |
-
"epoch": 0.
|
| 528 |
-
"learning_rate":
|
| 529 |
-
"loss":
|
| 530 |
"step": 87
|
| 531 |
},
|
| 532 |
{
|
| 533 |
-
"epoch": 0.
|
| 534 |
-
"learning_rate":
|
| 535 |
-
"loss":
|
| 536 |
"step": 88
|
| 537 |
},
|
| 538 |
{
|
| 539 |
-
"epoch": 0.
|
| 540 |
-
"learning_rate":
|
| 541 |
-
"loss":
|
| 542 |
"step": 89
|
| 543 |
},
|
| 544 |
{
|
| 545 |
-
"epoch": 0.
|
| 546 |
-
"learning_rate":
|
| 547 |
-
"loss":
|
| 548 |
"step": 90
|
| 549 |
},
|
| 550 |
{
|
| 551 |
-
"epoch": 0.
|
| 552 |
-
"learning_rate":
|
| 553 |
-
"loss":
|
| 554 |
"step": 91
|
| 555 |
},
|
| 556 |
{
|
| 557 |
-
"epoch": 0.
|
| 558 |
-
"learning_rate":
|
| 559 |
-
"loss":
|
| 560 |
"step": 92
|
| 561 |
},
|
| 562 |
{
|
| 563 |
-
"epoch": 0.
|
| 564 |
-
"learning_rate":
|
| 565 |
-
"loss":
|
| 566 |
"step": 93
|
| 567 |
},
|
| 568 |
{
|
| 569 |
-
"epoch": 0.
|
| 570 |
-
"learning_rate":
|
| 571 |
-
"loss":
|
| 572 |
"step": 94
|
| 573 |
},
|
| 574 |
{
|
| 575 |
-
"epoch": 0.
|
| 576 |
-
"learning_rate":
|
| 577 |
-
"loss":
|
| 578 |
"step": 95
|
| 579 |
},
|
| 580 |
{
|
| 581 |
-
"epoch": 0.
|
| 582 |
-
"learning_rate":
|
| 583 |
-
"loss":
|
| 584 |
"step": 96
|
| 585 |
},
|
| 586 |
{
|
| 587 |
-
"epoch": 0.
|
| 588 |
-
"learning_rate":
|
| 589 |
-
"loss":
|
| 590 |
"step": 97
|
| 591 |
},
|
| 592 |
{
|
| 593 |
-
"epoch": 0.
|
| 594 |
-
"learning_rate":
|
| 595 |
-
"loss":
|
| 596 |
"step": 98
|
| 597 |
},
|
| 598 |
{
|
| 599 |
-
"epoch": 0.
|
| 600 |
-
"learning_rate":
|
| 601 |
-
"loss":
|
| 602 |
"step": 99
|
| 603 |
},
|
| 604 |
{
|
| 605 |
-
"epoch": 0.
|
| 606 |
-
"learning_rate":
|
| 607 |
-
"loss":
|
| 608 |
"step": 100
|
| 609 |
},
|
| 610 |
{
|
| 611 |
-
"epoch": 0.
|
| 612 |
-
"learning_rate":
|
| 613 |
-
"loss":
|
| 614 |
"step": 101
|
| 615 |
},
|
| 616 |
{
|
| 617 |
-
"epoch": 0.
|
| 618 |
-
"learning_rate":
|
| 619 |
-
"loss":
|
| 620 |
"step": 102
|
| 621 |
},
|
| 622 |
{
|
| 623 |
-
"epoch": 0.
|
| 624 |
-
"learning_rate":
|
| 625 |
-
"loss":
|
| 626 |
"step": 103
|
| 627 |
},
|
| 628 |
{
|
| 629 |
-
"epoch": 0.
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss":
|
| 632 |
"step": 104
|
| 633 |
},
|
| 634 |
{
|
| 635 |
-
"epoch": 0.
|
| 636 |
-
"learning_rate":
|
| 637 |
-
"loss":
|
| 638 |
"step": 105
|
| 639 |
},
|
| 640 |
{
|
| 641 |
-
"epoch": 0.
|
| 642 |
-
"learning_rate":
|
| 643 |
-
"loss":
|
| 644 |
"step": 106
|
| 645 |
},
|
| 646 |
{
|
| 647 |
-
"epoch": 0.
|
| 648 |
-
"learning_rate":
|
| 649 |
-
"loss":
|
| 650 |
"step": 107
|
| 651 |
},
|
| 652 |
{
|
| 653 |
-
"epoch": 0.
|
| 654 |
-
"learning_rate":
|
| 655 |
-
"loss":
|
| 656 |
"step": 108
|
| 657 |
},
|
| 658 |
{
|
| 659 |
-
"epoch": 0.
|
| 660 |
-
"learning_rate":
|
| 661 |
-
"loss":
|
| 662 |
"step": 109
|
| 663 |
},
|
| 664 |
{
|
| 665 |
-
"epoch": 0.
|
| 666 |
-
"learning_rate":
|
| 667 |
-
"loss":
|
| 668 |
"step": 110
|
| 669 |
},
|
| 670 |
{
|
| 671 |
-
"epoch": 0.
|
| 672 |
-
"learning_rate":
|
| 673 |
-
"loss":
|
| 674 |
"step": 111
|
| 675 |
},
|
| 676 |
{
|
| 677 |
-
"epoch": 0.
|
| 678 |
-
"learning_rate":
|
| 679 |
-
"loss":
|
| 680 |
"step": 112
|
| 681 |
},
|
| 682 |
{
|
| 683 |
-
"epoch": 0.
|
| 684 |
-
"learning_rate":
|
| 685 |
-
"loss":
|
| 686 |
"step": 113
|
| 687 |
},
|
| 688 |
{
|
| 689 |
-
"epoch": 0.
|
| 690 |
-
"learning_rate":
|
| 691 |
-
"loss":
|
| 692 |
"step": 114
|
| 693 |
},
|
| 694 |
{
|
| 695 |
-
"epoch": 0.
|
| 696 |
-
"learning_rate":
|
| 697 |
-
"loss":
|
| 698 |
"step": 115
|
| 699 |
},
|
| 700 |
{
|
| 701 |
-
"epoch": 0.
|
| 702 |
-
"learning_rate":
|
| 703 |
-
"loss":
|
| 704 |
"step": 116
|
| 705 |
},
|
| 706 |
{
|
| 707 |
-
"epoch": 0.
|
| 708 |
-
"learning_rate":
|
| 709 |
-
"loss":
|
| 710 |
"step": 117
|
| 711 |
},
|
| 712 |
{
|
| 713 |
-
"epoch": 0.
|
| 714 |
-
"learning_rate":
|
| 715 |
-
"loss":
|
| 716 |
"step": 118
|
| 717 |
},
|
| 718 |
{
|
| 719 |
-
"epoch": 0.
|
| 720 |
-
"learning_rate":
|
| 721 |
-
"loss":
|
| 722 |
"step": 119
|
| 723 |
},
|
| 724 |
{
|
| 725 |
-
"epoch": 0.
|
| 726 |
-
"learning_rate":
|
| 727 |
-
"loss":
|
| 728 |
"step": 120
|
| 729 |
},
|
| 730 |
{
|
| 731 |
-
"epoch": 0.
|
| 732 |
-
"learning_rate":
|
| 733 |
-
"loss":
|
| 734 |
"step": 121
|
| 735 |
},
|
| 736 |
{
|
| 737 |
-
"epoch": 0.
|
| 738 |
-
"learning_rate":
|
| 739 |
-
"loss":
|
| 740 |
"step": 122
|
| 741 |
},
|
| 742 |
{
|
| 743 |
-
"epoch": 0.
|
| 744 |
-
"learning_rate":
|
| 745 |
-
"loss":
|
| 746 |
"step": 123
|
| 747 |
},
|
| 748 |
{
|
| 749 |
-
"epoch": 0.
|
| 750 |
-
"learning_rate":
|
| 751 |
-
"loss":
|
| 752 |
"step": 124
|
| 753 |
},
|
| 754 |
{
|
| 755 |
-
"epoch": 0.
|
| 756 |
-
"learning_rate":
|
| 757 |
-
"loss":
|
| 758 |
"step": 125
|
| 759 |
},
|
| 760 |
{
|
| 761 |
-
"epoch": 0.
|
| 762 |
-
"learning_rate":
|
| 763 |
-
"loss":
|
| 764 |
"step": 126
|
| 765 |
},
|
| 766 |
{
|
| 767 |
-
"epoch": 0.
|
| 768 |
-
"learning_rate":
|
| 769 |
-
"loss":
|
| 770 |
"step": 127
|
| 771 |
},
|
| 772 |
{
|
| 773 |
-
"epoch": 0.
|
| 774 |
-
"learning_rate":
|
| 775 |
-
"loss":
|
| 776 |
"step": 128
|
| 777 |
},
|
| 778 |
{
|
| 779 |
-
"epoch": 0.
|
| 780 |
-
"learning_rate":
|
| 781 |
-
"loss":
|
| 782 |
"step": 129
|
| 783 |
},
|
| 784 |
{
|
| 785 |
-
"epoch": 0.
|
| 786 |
-
"learning_rate":
|
| 787 |
-
"loss":
|
| 788 |
"step": 130
|
| 789 |
},
|
| 790 |
{
|
| 791 |
-
"epoch": 0.
|
| 792 |
-
"learning_rate":
|
| 793 |
-
"loss":
|
| 794 |
"step": 131
|
| 795 |
},
|
| 796 |
{
|
| 797 |
-
"epoch": 0.
|
| 798 |
-
"learning_rate":
|
| 799 |
-
"loss":
|
| 800 |
"step": 132
|
| 801 |
},
|
| 802 |
{
|
| 803 |
-
"epoch": 0.
|
| 804 |
-
"learning_rate":
|
| 805 |
-
"loss":
|
| 806 |
"step": 133
|
| 807 |
},
|
| 808 |
{
|
| 809 |
-
"epoch": 0.
|
| 810 |
-
"learning_rate":
|
| 811 |
-
"loss":
|
| 812 |
"step": 134
|
| 813 |
},
|
| 814 |
{
|
| 815 |
-
"epoch": 0.
|
| 816 |
-
"learning_rate":
|
| 817 |
-
"loss":
|
| 818 |
"step": 135
|
| 819 |
},
|
| 820 |
{
|
| 821 |
-
"epoch": 0.
|
| 822 |
-
"learning_rate":
|
| 823 |
-
"loss":
|
| 824 |
"step": 136
|
| 825 |
},
|
| 826 |
{
|
| 827 |
-
"epoch": 0.
|
| 828 |
-
"learning_rate":
|
| 829 |
-
"loss":
|
| 830 |
"step": 137
|
| 831 |
},
|
| 832 |
{
|
| 833 |
-
"epoch": 0.
|
| 834 |
-
"learning_rate":
|
| 835 |
-
"loss":
|
| 836 |
"step": 138
|
| 837 |
},
|
| 838 |
{
|
| 839 |
-
"epoch": 0.
|
| 840 |
-
"learning_rate":
|
| 841 |
-
"loss":
|
| 842 |
"step": 139
|
| 843 |
},
|
| 844 |
{
|
| 845 |
-
"epoch": 0.
|
| 846 |
-
"learning_rate":
|
| 847 |
-
"loss":
|
| 848 |
"step": 140
|
| 849 |
},
|
| 850 |
{
|
| 851 |
-
"epoch": 0.
|
| 852 |
-
"learning_rate":
|
| 853 |
-
"loss":
|
| 854 |
"step": 141
|
| 855 |
},
|
| 856 |
{
|
| 857 |
-
"epoch": 0.
|
| 858 |
-
"learning_rate":
|
| 859 |
-
"loss":
|
| 860 |
"step": 142
|
| 861 |
},
|
| 862 |
{
|
| 863 |
-
"epoch": 0.
|
| 864 |
-
"learning_rate":
|
| 865 |
-
"loss":
|
| 866 |
"step": 143
|
| 867 |
},
|
| 868 |
{
|
| 869 |
-
"epoch": 0.
|
| 870 |
-
"learning_rate":
|
| 871 |
-
"loss":
|
| 872 |
"step": 144
|
| 873 |
},
|
| 874 |
{
|
| 875 |
-
"epoch": 0.
|
| 876 |
-
"learning_rate":
|
| 877 |
-
"loss":
|
| 878 |
"step": 145
|
| 879 |
},
|
| 880 |
{
|
| 881 |
-
"epoch": 0.
|
| 882 |
-
"learning_rate":
|
| 883 |
-
"loss":
|
| 884 |
"step": 146
|
| 885 |
},
|
| 886 |
{
|
| 887 |
-
"epoch": 0.
|
| 888 |
-
"learning_rate":
|
| 889 |
-
"loss":
|
| 890 |
"step": 147
|
| 891 |
},
|
| 892 |
{
|
| 893 |
-
"epoch": 0.
|
| 894 |
-
"learning_rate":
|
| 895 |
-
"loss":
|
| 896 |
"step": 148
|
| 897 |
},
|
| 898 |
{
|
| 899 |
-
"epoch": 0.
|
| 900 |
-
"learning_rate":
|
| 901 |
-
"loss":
|
| 902 |
"step": 149
|
| 903 |
},
|
| 904 |
{
|
| 905 |
-
"epoch": 0.
|
| 906 |
-
"learning_rate":
|
| 907 |
-
"loss":
|
| 908 |
"step": 150
|
| 909 |
-
},
|
| 910 |
-
{
|
| 911 |
-
"epoch": 0.04,
|
| 912 |
-
"learning_rate": 1.0548375829549424e-06,
|
| 913 |
-
"loss": 1.2911,
|
| 914 |
-
"step": 151
|
| 915 |
-
},
|
| 916 |
-
{
|
| 917 |
-
"epoch": 0.04,
|
| 918 |
-
"learning_rate": 1.06182326231226e-06,
|
| 919 |
-
"loss": 1.3891,
|
| 920 |
-
"step": 152
|
| 921 |
-
},
|
| 922 |
-
{
|
| 923 |
-
"epoch": 0.04,
|
| 924 |
-
"learning_rate": 1.0688089416695776e-06,
|
| 925 |
-
"loss": 1.3481,
|
| 926 |
-
"step": 153
|
| 927 |
-
},
|
| 928 |
-
{
|
| 929 |
-
"epoch": 0.04,
|
| 930 |
-
"learning_rate": 1.075794621026895e-06,
|
| 931 |
-
"loss": 1.2061,
|
| 932 |
-
"step": 154
|
| 933 |
-
},
|
| 934 |
-
{
|
| 935 |
-
"epoch": 0.04,
|
| 936 |
-
"learning_rate": 1.0827803003842124e-06,
|
| 937 |
-
"loss": 1.3228,
|
| 938 |
-
"step": 155
|
| 939 |
-
},
|
| 940 |
-
{
|
| 941 |
-
"epoch": 0.04,
|
| 942 |
-
"learning_rate": 1.08976597974153e-06,
|
| 943 |
-
"loss": 1.4932,
|
| 944 |
-
"step": 156
|
| 945 |
-
},
|
| 946 |
-
{
|
| 947 |
-
"epoch": 0.04,
|
| 948 |
-
"learning_rate": 1.0967516590988476e-06,
|
| 949 |
-
"loss": 1.0902,
|
| 950 |
-
"step": 157
|
| 951 |
-
},
|
| 952 |
-
{
|
| 953 |
-
"epoch": 0.04,
|
| 954 |
-
"learning_rate": 1.103737338456165e-06,
|
| 955 |
-
"loss": 1.4818,
|
| 956 |
-
"step": 158
|
| 957 |
-
},
|
| 958 |
-
{
|
| 959 |
-
"epoch": 0.04,
|
| 960 |
-
"learning_rate": 1.1107230178134824e-06,
|
| 961 |
-
"loss": 1.3129,
|
| 962 |
-
"step": 159
|
| 963 |
-
},
|
| 964 |
-
{
|
| 965 |
-
"epoch": 0.04,
|
| 966 |
-
"learning_rate": 1.1177086971708e-06,
|
| 967 |
-
"loss": 1.3357,
|
| 968 |
-
"step": 160
|
| 969 |
-
},
|
| 970 |
-
{
|
| 971 |
-
"epoch": 0.04,
|
| 972 |
-
"learning_rate": 1.1246943765281176e-06,
|
| 973 |
-
"loss": 1.609,
|
| 974 |
-
"step": 161
|
| 975 |
-
},
|
| 976 |
-
{
|
| 977 |
-
"epoch": 0.04,
|
| 978 |
-
"learning_rate": 1.131680055885435e-06,
|
| 979 |
-
"loss": 1.2163,
|
| 980 |
-
"step": 162
|
| 981 |
-
},
|
| 982 |
-
{
|
| 983 |
-
"epoch": 0.04,
|
| 984 |
-
"learning_rate": 1.1386657352427523e-06,
|
| 985 |
-
"loss": 1.3282,
|
| 986 |
-
"step": 163
|
| 987 |
-
},
|
| 988 |
-
{
|
| 989 |
-
"epoch": 0.04,
|
| 990 |
-
"learning_rate": 1.14565141460007e-06,
|
| 991 |
-
"loss": 1.3166,
|
| 992 |
-
"step": 164
|
| 993 |
-
},
|
| 994 |
-
{
|
| 995 |
-
"epoch": 0.04,
|
| 996 |
-
"learning_rate": 1.1526370939573875e-06,
|
| 997 |
-
"loss": 1.3252,
|
| 998 |
-
"step": 165
|
| 999 |
-
},
|
| 1000 |
-
{
|
| 1001 |
-
"epoch": 0.04,
|
| 1002 |
-
"learning_rate": 1.159622773314705e-06,
|
| 1003 |
-
"loss": 1.4827,
|
| 1004 |
-
"step": 166
|
| 1005 |
-
},
|
| 1006 |
-
{
|
| 1007 |
-
"epoch": 0.04,
|
| 1008 |
-
"learning_rate": 1.1666084526720223e-06,
|
| 1009 |
-
"loss": 1.4112,
|
| 1010 |
-
"step": 167
|
| 1011 |
-
},
|
| 1012 |
-
{
|
| 1013 |
-
"epoch": 0.04,
|
| 1014 |
-
"learning_rate": 1.17359413202934e-06,
|
| 1015 |
-
"loss": 1.3811,
|
| 1016 |
-
"step": 168
|
| 1017 |
-
},
|
| 1018 |
-
{
|
| 1019 |
-
"epoch": 0.04,
|
| 1020 |
-
"learning_rate": 1.1805798113866575e-06,
|
| 1021 |
-
"loss": 1.2234,
|
| 1022 |
-
"step": 169
|
| 1023 |
-
},
|
| 1024 |
-
{
|
| 1025 |
-
"epoch": 0.04,
|
| 1026 |
-
"learning_rate": 1.187565490743975e-06,
|
| 1027 |
-
"loss": 1.5784,
|
| 1028 |
-
"step": 170
|
| 1029 |
-
},
|
| 1030 |
-
{
|
| 1031 |
-
"epoch": 0.04,
|
| 1032 |
-
"learning_rate": 1.1945511701012923e-06,
|
| 1033 |
-
"loss": 1.4294,
|
| 1034 |
-
"step": 171
|
| 1035 |
-
},
|
| 1036 |
-
{
|
| 1037 |
-
"epoch": 0.05,
|
| 1038 |
-
"learning_rate": 1.20153684945861e-06,
|
| 1039 |
-
"loss": 1.2927,
|
| 1040 |
-
"step": 172
|
| 1041 |
-
},
|
| 1042 |
-
{
|
| 1043 |
-
"epoch": 0.05,
|
| 1044 |
-
"learning_rate": 1.2085225288159275e-06,
|
| 1045 |
-
"loss": 1.3468,
|
| 1046 |
-
"step": 173
|
| 1047 |
-
},
|
| 1048 |
-
{
|
| 1049 |
-
"epoch": 0.05,
|
| 1050 |
-
"learning_rate": 1.215508208173245e-06,
|
| 1051 |
-
"loss": 1.39,
|
| 1052 |
-
"step": 174
|
| 1053 |
-
},
|
| 1054 |
-
{
|
| 1055 |
-
"epoch": 0.05,
|
| 1056 |
-
"learning_rate": 1.2224938875305625e-06,
|
| 1057 |
-
"loss": 1.6262,
|
| 1058 |
-
"step": 175
|
| 1059 |
-
},
|
| 1060 |
-
{
|
| 1061 |
-
"epoch": 0.05,
|
| 1062 |
-
"learning_rate": 1.2294795668878799e-06,
|
| 1063 |
-
"loss": 1.273,
|
| 1064 |
-
"step": 176
|
| 1065 |
-
},
|
| 1066 |
-
{
|
| 1067 |
-
"epoch": 0.05,
|
| 1068 |
-
"learning_rate": 1.2364652462451975e-06,
|
| 1069 |
-
"loss": 1.3019,
|
| 1070 |
-
"step": 177
|
| 1071 |
-
},
|
| 1072 |
-
{
|
| 1073 |
-
"epoch": 0.05,
|
| 1074 |
-
"learning_rate": 1.243450925602515e-06,
|
| 1075 |
-
"loss": 1.4669,
|
| 1076 |
-
"step": 178
|
| 1077 |
-
},
|
| 1078 |
-
{
|
| 1079 |
-
"epoch": 0.05,
|
| 1080 |
-
"learning_rate": 1.2504366049598325e-06,
|
| 1081 |
-
"loss": 1.388,
|
| 1082 |
-
"step": 179
|
| 1083 |
-
},
|
| 1084 |
-
{
|
| 1085 |
-
"epoch": 0.05,
|
| 1086 |
-
"learning_rate": 1.2574222843171499e-06,
|
| 1087 |
-
"loss": 1.2819,
|
| 1088 |
-
"step": 180
|
| 1089 |
-
},
|
| 1090 |
-
{
|
| 1091 |
-
"epoch": 0.05,
|
| 1092 |
-
"learning_rate": 1.2644079636744675e-06,
|
| 1093 |
-
"loss": 1.4056,
|
| 1094 |
-
"step": 181
|
| 1095 |
-
},
|
| 1096 |
-
{
|
| 1097 |
-
"epoch": 0.05,
|
| 1098 |
-
"learning_rate": 1.271393643031785e-06,
|
| 1099 |
-
"loss": 1.4843,
|
| 1100 |
-
"step": 182
|
| 1101 |
-
},
|
| 1102 |
-
{
|
| 1103 |
-
"epoch": 0.05,
|
| 1104 |
-
"learning_rate": 1.2783793223891024e-06,
|
| 1105 |
-
"loss": 1.2905,
|
| 1106 |
-
"step": 183
|
| 1107 |
-
},
|
| 1108 |
-
{
|
| 1109 |
-
"epoch": 0.05,
|
| 1110 |
-
"learning_rate": 1.28536500174642e-06,
|
| 1111 |
-
"loss": 1.4571,
|
| 1112 |
-
"step": 184
|
| 1113 |
-
},
|
| 1114 |
-
{
|
| 1115 |
-
"epoch": 0.05,
|
| 1116 |
-
"learning_rate": 1.2923506811037376e-06,
|
| 1117 |
-
"loss": 1.3495,
|
| 1118 |
-
"step": 185
|
| 1119 |
-
},
|
| 1120 |
-
{
|
| 1121 |
-
"epoch": 0.05,
|
| 1122 |
-
"learning_rate": 1.2993363604610548e-06,
|
| 1123 |
-
"loss": 1.2697,
|
| 1124 |
-
"step": 186
|
| 1125 |
-
},
|
| 1126 |
-
{
|
| 1127 |
-
"epoch": 0.05,
|
| 1128 |
-
"learning_rate": 1.3063220398183724e-06,
|
| 1129 |
-
"loss": 1.3934,
|
| 1130 |
-
"step": 187
|
| 1131 |
-
},
|
| 1132 |
-
{
|
| 1133 |
-
"epoch": 0.05,
|
| 1134 |
-
"learning_rate": 1.3133077191756898e-06,
|
| 1135 |
-
"loss": 1.2987,
|
| 1136 |
-
"step": 188
|
| 1137 |
-
},
|
| 1138 |
-
{
|
| 1139 |
-
"epoch": 0.05,
|
| 1140 |
-
"learning_rate": 1.3202933985330074e-06,
|
| 1141 |
-
"loss": 1.2335,
|
| 1142 |
-
"step": 189
|
| 1143 |
-
},
|
| 1144 |
-
{
|
| 1145 |
-
"epoch": 0.05,
|
| 1146 |
-
"learning_rate": 1.327279077890325e-06,
|
| 1147 |
-
"loss": 1.3375,
|
| 1148 |
-
"step": 190
|
| 1149 |
-
},
|
| 1150 |
-
{
|
| 1151 |
-
"epoch": 0.05,
|
| 1152 |
-
"learning_rate": 1.3342647572476424e-06,
|
| 1153 |
-
"loss": 1.3014,
|
| 1154 |
-
"step": 191
|
| 1155 |
-
},
|
| 1156 |
-
{
|
| 1157 |
-
"epoch": 0.05,
|
| 1158 |
-
"learning_rate": 1.34125043660496e-06,
|
| 1159 |
-
"loss": 1.2776,
|
| 1160 |
-
"step": 192
|
| 1161 |
-
},
|
| 1162 |
-
{
|
| 1163 |
-
"epoch": 0.05,
|
| 1164 |
-
"learning_rate": 1.3482361159622776e-06,
|
| 1165 |
-
"loss": 1.1337,
|
| 1166 |
-
"step": 193
|
| 1167 |
-
},
|
| 1168 |
-
{
|
| 1169 |
-
"epoch": 0.05,
|
| 1170 |
-
"learning_rate": 1.355221795319595e-06,
|
| 1171 |
-
"loss": 1.3029,
|
| 1172 |
-
"step": 194
|
| 1173 |
-
},
|
| 1174 |
-
{
|
| 1175 |
-
"epoch": 0.05,
|
| 1176 |
-
"learning_rate": 1.3622074746769124e-06,
|
| 1177 |
-
"loss": 1.4668,
|
| 1178 |
-
"step": 195
|
| 1179 |
-
},
|
| 1180 |
-
{
|
| 1181 |
-
"epoch": 0.05,
|
| 1182 |
-
"learning_rate": 1.3691931540342298e-06,
|
| 1183 |
-
"loss": 1.3451,
|
| 1184 |
-
"step": 196
|
| 1185 |
-
},
|
| 1186 |
-
{
|
| 1187 |
-
"epoch": 0.05,
|
| 1188 |
-
"learning_rate": 1.3761788333915474e-06,
|
| 1189 |
-
"loss": 1.3971,
|
| 1190 |
-
"step": 197
|
| 1191 |
-
},
|
| 1192 |
-
{
|
| 1193 |
-
"epoch": 0.05,
|
| 1194 |
-
"learning_rate": 1.383164512748865e-06,
|
| 1195 |
-
"loss": 1.3155,
|
| 1196 |
-
"step": 198
|
| 1197 |
-
},
|
| 1198 |
-
{
|
| 1199 |
-
"epoch": 0.05,
|
| 1200 |
-
"learning_rate": 1.3901501921061826e-06,
|
| 1201 |
-
"loss": 1.2804,
|
| 1202 |
-
"step": 199
|
| 1203 |
-
},
|
| 1204 |
-
{
|
| 1205 |
-
"epoch": 0.05,
|
| 1206 |
-
"learning_rate": 1.3971358714635e-06,
|
| 1207 |
-
"loss": 1.3541,
|
| 1208 |
-
"step": 200
|
| 1209 |
}
|
| 1210 |
],
|
| 1211 |
-
"max_steps":
|
| 1212 |
"num_train_epochs": 25,
|
| 1213 |
-
"total_flos":
|
| 1214 |
"trial_name": null,
|
| 1215 |
"trial_params": null
|
| 1216 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.31978680879413723,
|
| 5 |
+
"global_step": 150,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 5.681818181818182e-08,
|
| 13 |
+
"loss": 1.4294,
|
| 14 |
"step": 1
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.0,
|
| 18 |
+
"learning_rate": 1.1363636363636364e-07,
|
| 19 |
+
"loss": 1.3293,
|
| 20 |
"step": 2
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 1.7045454545454545e-07,
|
| 25 |
+
"loss": 1.0797,
|
| 26 |
"step": 3
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.01,
|
| 30 |
+
"learning_rate": 2.2727272727272729e-07,
|
| 31 |
+
"loss": 0.9853,
|
| 32 |
"step": 4
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.01,
|
| 36 |
+
"learning_rate": 2.840909090909091e-07,
|
| 37 |
+
"loss": 0.983,
|
| 38 |
"step": 5
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.01,
|
| 42 |
+
"learning_rate": 3.409090909090909e-07,
|
| 43 |
+
"loss": 0.9868,
|
| 44 |
"step": 6
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.01,
|
| 48 |
+
"learning_rate": 3.9772727272727276e-07,
|
| 49 |
+
"loss": 1.0148,
|
| 50 |
"step": 7
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.02,
|
| 54 |
+
"learning_rate": 4.5454545454545457e-07,
|
| 55 |
+
"loss": 1.0126,
|
| 56 |
"step": 8
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.02,
|
| 60 |
+
"learning_rate": 5.113636363636364e-07,
|
| 61 |
+
"loss": 0.9555,
|
| 62 |
"step": 9
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.02,
|
| 66 |
+
"learning_rate": 5.681818181818182e-07,
|
| 67 |
+
"loss": 1.0721,
|
| 68 |
"step": 10
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 0.02,
|
| 72 |
+
"learning_rate": 6.25e-07,
|
| 73 |
+
"loss": 1.0352,
|
| 74 |
"step": 11
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.03,
|
| 78 |
+
"learning_rate": 6.818181818181818e-07,
|
| 79 |
+
"loss": 0.9382,
|
| 80 |
"step": 12
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.03,
|
| 84 |
+
"learning_rate": 7.386363636363638e-07,
|
| 85 |
+
"loss": 1.0059,
|
| 86 |
"step": 13
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.03,
|
| 90 |
+
"learning_rate": 7.954545454545455e-07,
|
| 91 |
+
"loss": 0.9997,
|
| 92 |
"step": 14
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.03,
|
| 96 |
+
"learning_rate": 8.522727272727273e-07,
|
| 97 |
+
"loss": 0.9663,
|
| 98 |
"step": 15
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.03,
|
| 102 |
+
"learning_rate": 9.090909090909091e-07,
|
| 103 |
+
"loss": 0.9601,
|
| 104 |
"step": 16
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 0.04,
|
| 108 |
+
"learning_rate": 9.65909090909091e-07,
|
| 109 |
+
"loss": 0.9271,
|
| 110 |
"step": 17
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 0.04,
|
| 114 |
+
"learning_rate": 1.0227272727272729e-06,
|
| 115 |
+
"loss": 0.9655,
|
| 116 |
"step": 18
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.04,
|
| 120 |
+
"learning_rate": 1.0795454545454546e-06,
|
| 121 |
+
"loss": 0.8991,
|
| 122 |
"step": 19
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.04,
|
| 126 |
+
"learning_rate": 1.1363636363636364e-06,
|
| 127 |
+
"loss": 0.9081,
|
| 128 |
"step": 20
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.04,
|
| 132 |
+
"learning_rate": 1.1931818181818183e-06,
|
| 133 |
+
"loss": 0.9127,
|
| 134 |
"step": 21
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 0.05,
|
| 138 |
+
"learning_rate": 1.25e-06,
|
| 139 |
+
"loss": 0.9912,
|
| 140 |
"step": 22
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 0.05,
|
| 144 |
+
"learning_rate": 1.3068181818181819e-06,
|
| 145 |
+
"loss": 0.9077,
|
| 146 |
"step": 23
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 0.05,
|
| 150 |
+
"learning_rate": 1.3636363636363636e-06,
|
| 151 |
+
"loss": 0.9739,
|
| 152 |
"step": 24
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 0.05,
|
| 156 |
+
"learning_rate": 1.4204545454545458e-06,
|
| 157 |
+
"loss": 0.9148,
|
| 158 |
"step": 25
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 0.06,
|
| 162 |
+
"learning_rate": 1.4772727272727275e-06,
|
| 163 |
+
"loss": 0.8668,
|
| 164 |
"step": 26
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.06,
|
| 168 |
+
"learning_rate": 1.5340909090909093e-06,
|
| 169 |
+
"loss": 0.8951,
|
| 170 |
"step": 27
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.06,
|
| 174 |
+
"learning_rate": 1.590909090909091e-06,
|
| 175 |
+
"loss": 0.842,
|
| 176 |
"step": 28
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 0.06,
|
| 180 |
+
"learning_rate": 1.6477272727272728e-06,
|
| 181 |
+
"loss": 0.8439,
|
| 182 |
"step": 29
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 0.06,
|
| 186 |
+
"learning_rate": 1.7045454545454546e-06,
|
| 187 |
+
"loss": 0.8471,
|
| 188 |
"step": 30
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 0.07,
|
| 192 |
+
"learning_rate": 1.7613636363636365e-06,
|
| 193 |
+
"loss": 0.9474,
|
| 194 |
"step": 31
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 0.07,
|
| 198 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 199 |
+
"loss": 0.8957,
|
| 200 |
"step": 32
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 0.07,
|
| 204 |
+
"learning_rate": 1.8750000000000003e-06,
|
| 205 |
+
"loss": 0.8596,
|
| 206 |
"step": 33
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 0.07,
|
| 210 |
+
"learning_rate": 1.931818181818182e-06,
|
| 211 |
+
"loss": 0.8183,
|
| 212 |
"step": 34
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.07,
|
| 216 |
+
"learning_rate": 1.9886363636363638e-06,
|
| 217 |
+
"loss": 0.9198,
|
| 218 |
"step": 35
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 0.08,
|
| 222 |
+
"learning_rate": 2.0454545454545457e-06,
|
| 223 |
+
"loss": 0.8402,
|
| 224 |
"step": 36
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 0.08,
|
| 228 |
+
"learning_rate": 2.1022727272727277e-06,
|
| 229 |
+
"loss": 0.9209,
|
| 230 |
"step": 37
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 0.08,
|
| 234 |
+
"learning_rate": 2.1590909090909092e-06,
|
| 235 |
+
"loss": 0.8554,
|
| 236 |
"step": 38
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 0.08,
|
| 240 |
+
"learning_rate": 2.2159090909090912e-06,
|
| 241 |
+
"loss": 0.9276,
|
| 242 |
"step": 39
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 0.09,
|
| 246 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 247 |
+
"loss": 0.8872,
|
| 248 |
"step": 40
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 0.09,
|
| 252 |
+
"learning_rate": 2.3295454545454547e-06,
|
| 253 |
+
"loss": 0.9047,
|
| 254 |
"step": 41
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.09,
|
| 258 |
+
"learning_rate": 2.3863636363636367e-06,
|
| 259 |
+
"loss": 0.8514,
|
| 260 |
"step": 42
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 0.09,
|
| 264 |
+
"learning_rate": 2.4431818181818182e-06,
|
| 265 |
+
"loss": 0.7976,
|
| 266 |
"step": 43
|
| 267 |
},
|
| 268 |
{
|
| 269 |
+
"epoch": 0.09,
|
| 270 |
+
"learning_rate": 2.5e-06,
|
| 271 |
+
"loss": 0.8126,
|
| 272 |
"step": 44
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 0.1,
|
| 276 |
+
"learning_rate": 2.556818181818182e-06,
|
| 277 |
+
"loss": 0.8536,
|
| 278 |
"step": 45
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 0.1,
|
| 282 |
+
"learning_rate": 2.6136363636363637e-06,
|
| 283 |
+
"loss": 0.8228,
|
| 284 |
"step": 46
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 0.1,
|
| 288 |
+
"learning_rate": 2.6704545454545457e-06,
|
| 289 |
+
"loss": 0.8439,
|
| 290 |
"step": 47
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"epoch": 0.1,
|
| 294 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 295 |
+
"loss": 0.7859,
|
| 296 |
"step": 48
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 0.1,
|
| 300 |
+
"learning_rate": 2.784090909090909e-06,
|
| 301 |
+
"loss": 0.8424,
|
| 302 |
"step": 49
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 0.11,
|
| 306 |
+
"learning_rate": 2.8409090909090916e-06,
|
| 307 |
+
"loss": 0.7674,
|
| 308 |
"step": 50
|
| 309 |
},
|
| 310 |
{
|
| 311 |
+
"epoch": 0.11,
|
| 312 |
+
"learning_rate": 2.897727272727273e-06,
|
| 313 |
+
"loss": 0.8022,
|
| 314 |
"step": 51
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 0.11,
|
| 318 |
+
"learning_rate": 2.954545454545455e-06,
|
| 319 |
+
"loss": 0.7343,
|
| 320 |
"step": 52
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 0.11,
|
| 324 |
+
"learning_rate": 3.0113636363636366e-06,
|
| 325 |
+
"loss": 0.7343,
|
| 326 |
"step": 53
|
| 327 |
},
|
| 328 |
{
|
| 329 |
+
"epoch": 0.12,
|
| 330 |
+
"learning_rate": 3.0681818181818186e-06,
|
| 331 |
+
"loss": 0.7848,
|
| 332 |
"step": 54
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 0.12,
|
| 336 |
+
"learning_rate": 3.125e-06,
|
| 337 |
+
"loss": 0.8391,
|
| 338 |
"step": 55
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 0.12,
|
| 342 |
+
"learning_rate": 3.181818181818182e-06,
|
| 343 |
+
"loss": 0.7934,
|
| 344 |
"step": 56
|
| 345 |
},
|
| 346 |
{
|
| 347 |
+
"epoch": 0.12,
|
| 348 |
+
"learning_rate": 3.2386363636363637e-06,
|
| 349 |
+
"loss": 0.774,
|
| 350 |
"step": 57
|
| 351 |
},
|
| 352 |
{
|
| 353 |
+
"epoch": 0.12,
|
| 354 |
+
"learning_rate": 3.2954545454545456e-06,
|
| 355 |
+
"loss": 0.7292,
|
| 356 |
"step": 58
|
| 357 |
},
|
| 358 |
{
|
| 359 |
+
"epoch": 0.13,
|
| 360 |
+
"learning_rate": 3.352272727272727e-06,
|
| 361 |
+
"loss": 0.7393,
|
| 362 |
"step": 59
|
| 363 |
},
|
| 364 |
{
|
| 365 |
+
"epoch": 0.13,
|
| 366 |
+
"learning_rate": 3.409090909090909e-06,
|
| 367 |
+
"loss": 0.7484,
|
| 368 |
"step": 60
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 0.13,
|
| 372 |
+
"learning_rate": 3.4659090909090915e-06,
|
| 373 |
+
"loss": 0.7077,
|
| 374 |
"step": 61
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 0.13,
|
| 378 |
+
"learning_rate": 3.522727272727273e-06,
|
| 379 |
+
"loss": 0.8003,
|
| 380 |
"step": 62
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 0.13,
|
| 384 |
+
"learning_rate": 3.579545454545455e-06,
|
| 385 |
+
"loss": 0.7998,
|
| 386 |
"step": 63
|
| 387 |
},
|
| 388 |
{
|
| 389 |
+
"epoch": 0.14,
|
| 390 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 391 |
+
"loss": 0.7882,
|
| 392 |
"step": 64
|
| 393 |
},
|
| 394 |
{
|
| 395 |
+
"epoch": 0.14,
|
| 396 |
+
"learning_rate": 3.6931818181818186e-06,
|
| 397 |
+
"loss": 0.7326,
|
| 398 |
"step": 65
|
| 399 |
},
|
| 400 |
{
|
| 401 |
+
"epoch": 0.14,
|
| 402 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 403 |
+
"loss": 0.7945,
|
| 404 |
"step": 66
|
| 405 |
},
|
| 406 |
{
|
| 407 |
+
"epoch": 0.14,
|
| 408 |
+
"learning_rate": 3.806818181818182e-06,
|
| 409 |
+
"loss": 0.7518,
|
| 410 |
"step": 67
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"epoch": 0.14,
|
| 414 |
+
"learning_rate": 3.863636363636364e-06,
|
| 415 |
+
"loss": 0.711,
|
| 416 |
"step": 68
|
| 417 |
},
|
| 418 |
{
|
| 419 |
+
"epoch": 0.15,
|
| 420 |
+
"learning_rate": 3.9204545454545456e-06,
|
| 421 |
+
"loss": 0.7393,
|
| 422 |
"step": 69
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 0.15,
|
| 426 |
+
"learning_rate": 3.9772727272727275e-06,
|
| 427 |
+
"loss": 0.7285,
|
| 428 |
"step": 70
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"epoch": 0.15,
|
| 432 |
+
"learning_rate": 4.0340909090909095e-06,
|
| 433 |
+
"loss": 0.6976,
|
| 434 |
"step": 71
|
| 435 |
},
|
| 436 |
{
|
| 437 |
+
"epoch": 0.15,
|
| 438 |
+
"learning_rate": 4.0909090909090915e-06,
|
| 439 |
+
"loss": 0.7845,
|
| 440 |
"step": 72
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"epoch": 0.16,
|
| 444 |
+
"learning_rate": 4.1477272727272734e-06,
|
| 445 |
+
"loss": 0.7104,
|
| 446 |
"step": 73
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 0.16,
|
| 450 |
+
"learning_rate": 4.204545454545455e-06,
|
| 451 |
+
"loss": 0.7021,
|
| 452 |
"step": 74
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"epoch": 0.16,
|
| 456 |
+
"learning_rate": 4.2613636363636365e-06,
|
| 457 |
+
"loss": 0.7425,
|
| 458 |
"step": 75
|
| 459 |
},
|
| 460 |
{
|
| 461 |
+
"epoch": 0.16,
|
| 462 |
+
"learning_rate": 4.3181818181818185e-06,
|
| 463 |
+
"loss": 0.6481,
|
| 464 |
"step": 76
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 0.16,
|
| 468 |
+
"learning_rate": 4.3750000000000005e-06,
|
| 469 |
+
"loss": 0.7236,
|
| 470 |
"step": 77
|
| 471 |
},
|
| 472 |
{
|
| 473 |
+
"epoch": 0.17,
|
| 474 |
+
"learning_rate": 4.4318181818181824e-06,
|
| 475 |
+
"loss": 0.6932,
|
| 476 |
"step": 78
|
| 477 |
},
|
| 478 |
{
|
| 479 |
+
"epoch": 0.17,
|
| 480 |
+
"learning_rate": 4.4886363636363636e-06,
|
| 481 |
+
"loss": 0.805,
|
| 482 |
"step": 79
|
| 483 |
},
|
| 484 |
{
|
| 485 |
+
"epoch": 0.17,
|
| 486 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 487 |
+
"loss": 0.7581,
|
| 488 |
"step": 80
|
| 489 |
},
|
| 490 |
{
|
| 491 |
+
"epoch": 0.17,
|
| 492 |
+
"learning_rate": 4.6022727272727275e-06,
|
| 493 |
+
"loss": 0.7845,
|
| 494 |
"step": 81
|
| 495 |
},
|
| 496 |
{
|
| 497 |
+
"epoch": 0.17,
|
| 498 |
+
"learning_rate": 4.6590909090909095e-06,
|
| 499 |
+
"loss": 0.722,
|
| 500 |
"step": 82
|
| 501 |
},
|
| 502 |
{
|
| 503 |
+
"epoch": 0.18,
|
| 504 |
+
"learning_rate": 4.715909090909091e-06,
|
| 505 |
+
"loss": 0.7098,
|
| 506 |
"step": 83
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 0.18,
|
| 510 |
+
"learning_rate": 4.772727272727273e-06,
|
| 511 |
+
"loss": 0.6372,
|
| 512 |
"step": 84
|
| 513 |
},
|
| 514 |
{
|
| 515 |
+
"epoch": 0.18,
|
| 516 |
+
"learning_rate": 4.829545454545455e-06,
|
| 517 |
+
"loss": 0.6828,
|
| 518 |
"step": 85
|
| 519 |
},
|
| 520 |
{
|
| 521 |
+
"epoch": 0.18,
|
| 522 |
+
"learning_rate": 4.8863636363636365e-06,
|
| 523 |
+
"loss": 0.655,
|
| 524 |
"step": 86
|
| 525 |
},
|
| 526 |
{
|
| 527 |
+
"epoch": 0.19,
|
| 528 |
+
"learning_rate": 4.9431818181818184e-06,
|
| 529 |
+
"loss": 0.7154,
|
| 530 |
"step": 87
|
| 531 |
},
|
| 532 |
{
|
| 533 |
+
"epoch": 0.19,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.7593,
|
| 536 |
"step": 88
|
| 537 |
},
|
| 538 |
{
|
| 539 |
+
"epoch": 0.19,
|
| 540 |
+
"learning_rate": 5.056818181818182e-06,
|
| 541 |
+
"loss": 0.7319,
|
| 542 |
"step": 89
|
| 543 |
},
|
| 544 |
{
|
| 545 |
+
"epoch": 0.19,
|
| 546 |
+
"learning_rate": 5.113636363636364e-06,
|
| 547 |
+
"loss": 0.7033,
|
| 548 |
"step": 90
|
| 549 |
},
|
| 550 |
{
|
| 551 |
+
"epoch": 0.19,
|
| 552 |
+
"learning_rate": 5.170454545454546e-06,
|
| 553 |
+
"loss": 0.6835,
|
| 554 |
"step": 91
|
| 555 |
},
|
| 556 |
{
|
| 557 |
+
"epoch": 0.2,
|
| 558 |
+
"learning_rate": 5.2272727272727274e-06,
|
| 559 |
+
"loss": 0.7718,
|
| 560 |
"step": 92
|
| 561 |
},
|
| 562 |
{
|
| 563 |
+
"epoch": 0.2,
|
| 564 |
+
"learning_rate": 5.28409090909091e-06,
|
| 565 |
+
"loss": 0.7964,
|
| 566 |
"step": 93
|
| 567 |
},
|
| 568 |
{
|
| 569 |
+
"epoch": 0.2,
|
| 570 |
+
"learning_rate": 5.340909090909091e-06,
|
| 571 |
+
"loss": 0.727,
|
| 572 |
"step": 94
|
| 573 |
},
|
| 574 |
{
|
| 575 |
+
"epoch": 0.2,
|
| 576 |
+
"learning_rate": 5.397727272727273e-06,
|
| 577 |
+
"loss": 0.7526,
|
| 578 |
"step": 95
|
| 579 |
},
|
| 580 |
{
|
| 581 |
+
"epoch": 0.2,
|
| 582 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 583 |
+
"loss": 0.7241,
|
| 584 |
"step": 96
|
| 585 |
},
|
| 586 |
{
|
| 587 |
+
"epoch": 0.21,
|
| 588 |
+
"learning_rate": 5.511363636363637e-06,
|
| 589 |
+
"loss": 0.7246,
|
| 590 |
"step": 97
|
| 591 |
},
|
| 592 |
{
|
| 593 |
+
"epoch": 0.21,
|
| 594 |
+
"learning_rate": 5.568181818181818e-06,
|
| 595 |
+
"loss": 0.7095,
|
| 596 |
"step": 98
|
| 597 |
},
|
| 598 |
{
|
| 599 |
+
"epoch": 0.21,
|
| 600 |
+
"learning_rate": 5.625e-06,
|
| 601 |
+
"loss": 0.6755,
|
| 602 |
"step": 99
|
| 603 |
},
|
| 604 |
{
|
| 605 |
+
"epoch": 0.21,
|
| 606 |
+
"learning_rate": 5.681818181818183e-06,
|
| 607 |
+
"loss": 0.6322,
|
| 608 |
"step": 100
|
| 609 |
},
|
| 610 |
{
|
| 611 |
+
"epoch": 0.22,
|
| 612 |
+
"learning_rate": 5.738636363636364e-06,
|
| 613 |
+
"loss": 0.7094,
|
| 614 |
"step": 101
|
| 615 |
},
|
| 616 |
{
|
| 617 |
+
"epoch": 0.22,
|
| 618 |
+
"learning_rate": 5.795454545454546e-06,
|
| 619 |
+
"loss": 0.7256,
|
| 620 |
"step": 102
|
| 621 |
},
|
| 622 |
{
|
| 623 |
+
"epoch": 0.22,
|
| 624 |
+
"learning_rate": 5.852272727272727e-06,
|
| 625 |
+
"loss": 0.7096,
|
| 626 |
"step": 103
|
| 627 |
},
|
| 628 |
{
|
| 629 |
+
"epoch": 0.22,
|
| 630 |
+
"learning_rate": 5.90909090909091e-06,
|
| 631 |
+
"loss": 0.7148,
|
| 632 |
"step": 104
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 0.22,
|
| 636 |
+
"learning_rate": 5.965909090909091e-06,
|
| 637 |
+
"loss": 0.6763,
|
| 638 |
"step": 105
|
| 639 |
},
|
| 640 |
{
|
| 641 |
+
"epoch": 0.23,
|
| 642 |
+
"learning_rate": 6.022727272727273e-06,
|
| 643 |
+
"loss": 0.6761,
|
| 644 |
"step": 106
|
| 645 |
},
|
| 646 |
{
|
| 647 |
+
"epoch": 0.23,
|
| 648 |
+
"learning_rate": 6.079545454545454e-06,
|
| 649 |
+
"loss": 0.7454,
|
| 650 |
"step": 107
|
| 651 |
},
|
| 652 |
{
|
| 653 |
+
"epoch": 0.23,
|
| 654 |
+
"learning_rate": 6.136363636363637e-06,
|
| 655 |
+
"loss": 0.694,
|
| 656 |
"step": 108
|
| 657 |
},
|
| 658 |
{
|
| 659 |
+
"epoch": 0.23,
|
| 660 |
+
"learning_rate": 6.193181818181818e-06,
|
| 661 |
+
"loss": 0.6797,
|
| 662 |
"step": 109
|
| 663 |
},
|
| 664 |
{
|
| 665 |
+
"epoch": 0.23,
|
| 666 |
+
"learning_rate": 6.25e-06,
|
| 667 |
+
"loss": 0.6294,
|
| 668 |
"step": 110
|
| 669 |
},
|
| 670 |
{
|
| 671 |
+
"epoch": 0.24,
|
| 672 |
+
"learning_rate": 6.306818181818183e-06,
|
| 673 |
+
"loss": 0.709,
|
| 674 |
"step": 111
|
| 675 |
},
|
| 676 |
{
|
| 677 |
+
"epoch": 0.24,
|
| 678 |
+
"learning_rate": 6.363636363636364e-06,
|
| 679 |
+
"loss": 0.6536,
|
| 680 |
"step": 112
|
| 681 |
},
|
| 682 |
{
|
| 683 |
+
"epoch": 0.24,
|
| 684 |
+
"learning_rate": 6.420454545454546e-06,
|
| 685 |
+
"loss": 0.7591,
|
| 686 |
"step": 113
|
| 687 |
},
|
| 688 |
{
|
| 689 |
+
"epoch": 0.24,
|
| 690 |
+
"learning_rate": 6.477272727272727e-06,
|
| 691 |
+
"loss": 0.6292,
|
| 692 |
"step": 114
|
| 693 |
},
|
| 694 |
{
|
| 695 |
+
"epoch": 0.25,
|
| 696 |
+
"learning_rate": 6.53409090909091e-06,
|
| 697 |
+
"loss": 0.7554,
|
| 698 |
"step": 115
|
| 699 |
},
|
| 700 |
{
|
| 701 |
+
"epoch": 0.25,
|
| 702 |
+
"learning_rate": 6.590909090909091e-06,
|
| 703 |
+
"loss": 0.6496,
|
| 704 |
"step": 116
|
| 705 |
},
|
| 706 |
{
|
| 707 |
+
"epoch": 0.25,
|
| 708 |
+
"learning_rate": 6.647727272727273e-06,
|
| 709 |
+
"loss": 0.7014,
|
| 710 |
"step": 117
|
| 711 |
},
|
| 712 |
{
|
| 713 |
+
"epoch": 0.25,
|
| 714 |
+
"learning_rate": 6.704545454545454e-06,
|
| 715 |
+
"loss": 0.6783,
|
| 716 |
"step": 118
|
| 717 |
},
|
| 718 |
{
|
| 719 |
+
"epoch": 0.25,
|
| 720 |
+
"learning_rate": 6.761363636363637e-06,
|
| 721 |
+
"loss": 0.6998,
|
| 722 |
"step": 119
|
| 723 |
},
|
| 724 |
{
|
| 725 |
+
"epoch": 0.26,
|
| 726 |
+
"learning_rate": 6.818181818181818e-06,
|
| 727 |
+
"loss": 0.6159,
|
| 728 |
"step": 120
|
| 729 |
},
|
| 730 |
{
|
| 731 |
+
"epoch": 0.26,
|
| 732 |
+
"learning_rate": 6.875e-06,
|
| 733 |
+
"loss": 0.7181,
|
| 734 |
"step": 121
|
| 735 |
},
|
| 736 |
{
|
| 737 |
+
"epoch": 0.26,
|
| 738 |
+
"learning_rate": 6.931818181818183e-06,
|
| 739 |
+
"loss": 0.7008,
|
| 740 |
"step": 122
|
| 741 |
},
|
| 742 |
{
|
| 743 |
+
"epoch": 0.26,
|
| 744 |
+
"learning_rate": 6.988636363636364e-06,
|
| 745 |
+
"loss": 0.6097,
|
| 746 |
"step": 123
|
| 747 |
},
|
| 748 |
{
|
| 749 |
+
"epoch": 0.26,
|
| 750 |
+
"learning_rate": 7.045454545454546e-06,
|
| 751 |
+
"loss": 0.7091,
|
| 752 |
"step": 124
|
| 753 |
},
|
| 754 |
{
|
| 755 |
+
"epoch": 0.27,
|
| 756 |
+
"learning_rate": 7.102272727272727e-06,
|
| 757 |
+
"loss": 0.6313,
|
| 758 |
"step": 125
|
| 759 |
},
|
| 760 |
{
|
| 761 |
+
"epoch": 0.27,
|
| 762 |
+
"learning_rate": 7.15909090909091e-06,
|
| 763 |
+
"loss": 0.6355,
|
| 764 |
"step": 126
|
| 765 |
},
|
| 766 |
{
|
| 767 |
+
"epoch": 0.27,
|
| 768 |
+
"learning_rate": 7.215909090909091e-06,
|
| 769 |
+
"loss": 0.6559,
|
| 770 |
"step": 127
|
| 771 |
},
|
| 772 |
{
|
| 773 |
+
"epoch": 0.27,
|
| 774 |
+
"learning_rate": 7.272727272727273e-06,
|
| 775 |
+
"loss": 0.6066,
|
| 776 |
"step": 128
|
| 777 |
},
|
| 778 |
{
|
| 779 |
+
"epoch": 0.28,
|
| 780 |
+
"learning_rate": 7.329545454545455e-06,
|
| 781 |
+
"loss": 0.6655,
|
| 782 |
"step": 129
|
| 783 |
},
|
| 784 |
{
|
| 785 |
+
"epoch": 0.28,
|
| 786 |
+
"learning_rate": 7.386363636363637e-06,
|
| 787 |
+
"loss": 0.6623,
|
| 788 |
"step": 130
|
| 789 |
},
|
| 790 |
{
|
| 791 |
+
"epoch": 0.28,
|
| 792 |
+
"learning_rate": 7.443181818181818e-06,
|
| 793 |
+
"loss": 0.6746,
|
| 794 |
"step": 131
|
| 795 |
},
|
| 796 |
{
|
| 797 |
+
"epoch": 0.28,
|
| 798 |
+
"learning_rate": 7.500000000000001e-06,
|
| 799 |
+
"loss": 0.6795,
|
| 800 |
"step": 132
|
| 801 |
},
|
| 802 |
{
|
| 803 |
+
"epoch": 0.28,
|
| 804 |
+
"learning_rate": 7.556818181818183e-06,
|
| 805 |
+
"loss": 0.6885,
|
| 806 |
"step": 133
|
| 807 |
},
|
| 808 |
{
|
| 809 |
+
"epoch": 0.29,
|
| 810 |
+
"learning_rate": 7.613636363636364e-06,
|
| 811 |
+
"loss": 0.6868,
|
| 812 |
"step": 134
|
| 813 |
},
|
| 814 |
{
|
| 815 |
+
"epoch": 0.29,
|
| 816 |
+
"learning_rate": 7.670454545454547e-06,
|
| 817 |
+
"loss": 0.6539,
|
| 818 |
"step": 135
|
| 819 |
},
|
| 820 |
{
|
| 821 |
+
"epoch": 0.29,
|
| 822 |
+
"learning_rate": 7.727272727272727e-06,
|
| 823 |
+
"loss": 0.6463,
|
| 824 |
"step": 136
|
| 825 |
},
|
| 826 |
{
|
| 827 |
+
"epoch": 0.29,
|
| 828 |
+
"learning_rate": 7.784090909090911e-06,
|
| 829 |
+
"loss": 0.6706,
|
| 830 |
"step": 137
|
| 831 |
},
|
| 832 |
{
|
| 833 |
+
"epoch": 0.29,
|
| 834 |
+
"learning_rate": 7.840909090909091e-06,
|
| 835 |
+
"loss": 0.6806,
|
| 836 |
"step": 138
|
| 837 |
},
|
| 838 |
{
|
| 839 |
+
"epoch": 0.3,
|
| 840 |
+
"learning_rate": 7.897727272727273e-06,
|
| 841 |
+
"loss": 0.6643,
|
| 842 |
"step": 139
|
| 843 |
},
|
| 844 |
{
|
| 845 |
+
"epoch": 0.3,
|
| 846 |
+
"learning_rate": 7.954545454545455e-06,
|
| 847 |
+
"loss": 0.6554,
|
| 848 |
"step": 140
|
| 849 |
},
|
| 850 |
{
|
| 851 |
+
"epoch": 0.3,
|
| 852 |
+
"learning_rate": 8.011363636363637e-06,
|
| 853 |
+
"loss": 0.6783,
|
| 854 |
"step": 141
|
| 855 |
},
|
| 856 |
{
|
| 857 |
+
"epoch": 0.3,
|
| 858 |
+
"learning_rate": 8.068181818181819e-06,
|
| 859 |
+
"loss": 0.6641,
|
| 860 |
"step": 142
|
| 861 |
},
|
| 862 |
{
|
| 863 |
+
"epoch": 0.3,
|
| 864 |
+
"learning_rate": 8.125000000000001e-06,
|
| 865 |
+
"loss": 0.6763,
|
| 866 |
"step": 143
|
| 867 |
},
|
| 868 |
{
|
| 869 |
+
"epoch": 0.31,
|
| 870 |
+
"learning_rate": 8.181818181818183e-06,
|
| 871 |
+
"loss": 0.7325,
|
| 872 |
"step": 144
|
| 873 |
},
|
| 874 |
{
|
| 875 |
+
"epoch": 0.31,
|
| 876 |
+
"learning_rate": 8.238636363636365e-06,
|
| 877 |
+
"loss": 0.6366,
|
| 878 |
"step": 145
|
| 879 |
},
|
| 880 |
{
|
| 881 |
+
"epoch": 0.31,
|
| 882 |
+
"learning_rate": 8.295454545454547e-06,
|
| 883 |
+
"loss": 0.7373,
|
| 884 |
"step": 146
|
| 885 |
},
|
| 886 |
{
|
| 887 |
+
"epoch": 0.31,
|
| 888 |
+
"learning_rate": 8.352272727272727e-06,
|
| 889 |
+
"loss": 0.7105,
|
| 890 |
"step": 147
|
| 891 |
},
|
| 892 |
{
|
| 893 |
+
"epoch": 0.32,
|
| 894 |
+
"learning_rate": 8.40909090909091e-06,
|
| 895 |
+
"loss": 0.6865,
|
| 896 |
"step": 148
|
| 897 |
},
|
| 898 |
{
|
| 899 |
+
"epoch": 0.32,
|
| 900 |
+
"learning_rate": 8.465909090909091e-06,
|
| 901 |
+
"loss": 0.6784,
|
| 902 |
"step": 149
|
| 903 |
},
|
| 904 |
{
|
| 905 |
+
"epoch": 0.32,
|
| 906 |
+
"learning_rate": 8.522727272727273e-06,
|
| 907 |
+
"loss": 0.6769,
|
| 908 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 909 |
}
|
| 910 |
],
|
| 911 |
+
"max_steps": 11725,
|
| 912 |
"num_train_epochs": 25,
|
| 913 |
+
"total_flos": 3.974479252291584e+17,
|
| 914 |
"trial_name": null,
|
| 915 |
"trial_params": null
|
| 916 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2694e65878114e56cf098ae35983b751a7d3942a83bdcf5cca40a623501a6e7f
|
| 3 |
+
size 3707
|