update ckpt with 6ish epochs of training with 1024 TOKENS as max output
Browse files- .gitignore +1 -0
- config.json +1 -1
- latest +1 -1
- long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4-ft2-booksum_training_metadata.json +1 -0
- pytorch_model.bin +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +174 -339
- training_args.bin +1 -1
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "pszemraj/
|
| 3 |
"architectures": [
|
| 4 |
"LongT5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4",
|
| 3 |
"architectures": [
|
| 4 |
"LongT5ForConditionalGeneration"
|
| 5 |
],
|
latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step164
|
long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4-ft2-booksum_training_metadata.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"output_dir": "/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4-ft2-booksum", "overwrite_output_dir": true, "do_train": false, "do_eval": false, "do_predict": false, "evaluation_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 1, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 64, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 0.0001, "weight_decay": 0.05, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 0.6, "num_train_epochs": 2, "max_steps": -1, "lr_scheduler_type": "cosine", "warmup_ratio": 0.01, "warmup_steps": 0, "log_level": -1, "log_level_replica": -1, "log_on_each_node": true, "logging_dir": "/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4-ft2-booksum/logs", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 3, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 50, "save_total_limit": 1, "save_on_each_node": false, "no_cuda": false, "seed": 42, "data_seed": "None", "jit_mode_eval": false, "use_ipex": false, "bf16": false, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": "None", "local_rank": 0, "xpu_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": "[]", "dataloader_drop_last": false, "eval_steps": "None", "dataloader_num_workers": 0, "past_index": -1, "run_name": "/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4-ft2-booksum", "disable_tqdm": false, "remove_unused_columns": true, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "sharded_ddp": "[]", "fsdp": "[]", "fsdp_min_num_params": 0, "deepspeed": "/content/ds_config_zero2_bf16.json", "label_smoothing_factor": 0.0, "optim": "adamw_hf", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": "['tensorboard']", "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "dataloader_pin_memory": true, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": true, "resume_from_checkpoint": "None", "hub_model_id": "long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4-ft2-booksum", "hub_strategy": "end", "hub_token": "<HUB_TOKEN>", "hub_private_repo": true, "gradient_checkpointing": true, "include_inputs_for_metrics": false, "fp16_backend": "auto", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "_n_gpu": 1, "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": "None", "ray_scope": "last", "sortish_sampler": false, "predict_with_generate": false, "generation_max_length": "None", "generation_num_beams": "None", "train_batch_size": 2, "eval_batch_size": 1, "configs_src": "long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4-ft2-booksum"}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3132548907
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57a6f0f99f02e2264845cf4e409391ddc7f0a2086349e51663b4164a11601533
|
| 3 |
size 3132548907
|
tokenizer_config.json
CHANGED
|
@@ -103,7 +103,7 @@
|
|
| 103 |
],
|
| 104 |
"eos_token": "</s>",
|
| 105 |
"extra_ids": 100,
|
| 106 |
-
"name_or_path": "pszemraj/
|
| 107 |
"pad_token": "<pad>",
|
| 108 |
"special_tokens_map_file": null,
|
| 109 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
| 103 |
],
|
| 104 |
"eos_token": "</s>",
|
| 105 |
"extra_ids": 100,
|
| 106 |
+
"name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP4",
|
| 107 |
"pad_token": "<pad>",
|
| 108 |
"special_tokens_map_file": null,
|
| 109 |
"tokenizer_class": "T5Tokenizer",
|
trainer_state.json
CHANGED
|
@@ -1,514 +1,349 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 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.
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss":
|
| 14 |
"step": 3
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss":
|
| 20 |
"step": 6
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss":
|
| 26 |
"step": 9
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss":
|
| 32 |
"step": 12
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss":
|
| 38 |
"step": 15
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 18
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss":
|
| 50 |
"step": 21
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch": 0.
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss":
|
| 56 |
"step": 24
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch": 0.
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss":
|
| 62 |
"step": 27
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch": 0.
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss":
|
| 68 |
"step": 30
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch": 0.
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss":
|
| 74 |
"step": 33
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 0.
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss":
|
| 80 |
"step": 36
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
"step": 39
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss":
|
| 92 |
"step": 42
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 0.
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss":
|
| 98 |
"step": 45
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 0.
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss":
|
| 104 |
"step": 48
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch": 0.
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss":
|
| 110 |
"step": 51
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch": 0.
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss":
|
| 116 |
"step": 54
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 0.
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss":
|
| 122 |
"step": 57
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 0.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss":
|
| 128 |
"step": 60
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss":
|
| 134 |
"step": 63
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 0.
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss":
|
| 140 |
"step": 66
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch": 0.
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss":
|
| 146 |
"step": 69
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch": 0.
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss":
|
| 152 |
"step": 72
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch": 0.
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss":
|
| 158 |
"step": 75
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch": 0.
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss":
|
| 164 |
"step": 78
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 0.
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss":
|
| 170 |
"step": 81
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss":
|
| 176 |
"step": 84
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch":
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss":
|
| 182 |
"step": 87
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch":
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss":
|
| 188 |
"step": 90
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss":
|
| 194 |
"step": 93
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch":
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss":
|
| 200 |
"step": 96
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch":
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss":
|
| 206 |
"step": 99
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch": 1.
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss":
|
| 212 |
"step": 102
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 1.
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss":
|
| 218 |
"step": 105
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch": 1.
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss":
|
| 224 |
"step": 108
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch": 1.
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss":
|
| 230 |
"step": 111
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch": 1.
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss":
|
| 236 |
"step": 114
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch": 1.
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss":
|
| 242 |
"step": 117
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch": 1.
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss":
|
| 248 |
"step": 120
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch": 1.
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss":
|
| 254 |
"step": 123
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch": 1.
|
| 258 |
-
"learning_rate":
|
| 259 |
-
"loss":
|
| 260 |
"step": 126
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch": 1.
|
| 264 |
-
"learning_rate":
|
| 265 |
-
"loss":
|
| 266 |
"step": 129
|
| 267 |
},
|
| 268 |
{
|
| 269 |
-
"epoch": 1.
|
| 270 |
-
"learning_rate":
|
| 271 |
-
"loss":
|
| 272 |
"step": 132
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch": 1.
|
| 276 |
-
"learning_rate":
|
| 277 |
-
"loss":
|
| 278 |
"step": 135
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch": 1.
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss":
|
| 284 |
"step": 138
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch": 1.
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss":
|
| 290 |
"step": 141
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"epoch": 1.
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss":
|
| 296 |
"step": 144
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch": 1.
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss":
|
| 302 |
"step": 147
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch": 1.
|
| 306 |
-
"learning_rate":
|
| 307 |
-
"loss":
|
| 308 |
"step": 150
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch": 1.
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss":
|
| 314 |
"step": 153
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch": 1.
|
| 318 |
-
"learning_rate":
|
| 319 |
-
"loss":
|
| 320 |
"step": 156
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch": 1.
|
| 324 |
-
"learning_rate":
|
| 325 |
-
"loss":
|
| 326 |
"step": 159
|
| 327 |
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 1.59,
|
| 330 |
-
"learning_rate": 8e-05,
|
| 331 |
-
"loss": 2.8048,
|
| 332 |
-
"step": 162
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 1.62,
|
| 336 |
-
"learning_rate": 8e-05,
|
| 337 |
-
"loss": 2.6799,
|
| 338 |
-
"step": 165
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 1.65,
|
| 342 |
-
"learning_rate": 8e-05,
|
| 343 |
-
"loss": 2.6929,
|
| 344 |
-
"step": 168
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 1.68,
|
| 348 |
-
"learning_rate": 8e-05,
|
| 349 |
-
"loss": 2.797,
|
| 350 |
-
"step": 171
|
| 351 |
-
},
|
| 352 |
-
{
|
| 353 |
-
"epoch": 1.71,
|
| 354 |
-
"learning_rate": 8e-05,
|
| 355 |
-
"loss": 2.7406,
|
| 356 |
-
"step": 174
|
| 357 |
-
},
|
| 358 |
-
{
|
| 359 |
-
"epoch": 1.74,
|
| 360 |
-
"learning_rate": 8e-05,
|
| 361 |
-
"loss": 2.7053,
|
| 362 |
-
"step": 177
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 1.76,
|
| 366 |
-
"learning_rate": 8e-05,
|
| 367 |
-
"loss": 2.7513,
|
| 368 |
-
"step": 180
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 1.79,
|
| 372 |
-
"learning_rate": 8e-05,
|
| 373 |
-
"loss": 2.7608,
|
| 374 |
-
"step": 183
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 1.82,
|
| 378 |
-
"learning_rate": 8e-05,
|
| 379 |
-
"loss": 2.6898,
|
| 380 |
-
"step": 186
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 1.85,
|
| 384 |
-
"learning_rate": 8e-05,
|
| 385 |
-
"loss": 2.7014,
|
| 386 |
-
"step": 189
|
| 387 |
-
},
|
| 388 |
-
{
|
| 389 |
-
"epoch": 1.88,
|
| 390 |
-
"learning_rate": 8e-05,
|
| 391 |
-
"loss": 2.7365,
|
| 392 |
-
"step": 192
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 1.91,
|
| 396 |
-
"learning_rate": 8e-05,
|
| 397 |
-
"loss": 2.7513,
|
| 398 |
-
"step": 195
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 1.94,
|
| 402 |
-
"learning_rate": 8e-05,
|
| 403 |
-
"loss": 2.7584,
|
| 404 |
-
"step": 198
|
| 405 |
-
},
|
| 406 |
{
|
| 407 |
"epoch": 1.97,
|
| 408 |
-
"learning_rate":
|
| 409 |
-
"loss":
|
| 410 |
-
"step":
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 2.0,
|
| 414 |
-
"learning_rate": 8e-05,
|
| 415 |
-
"loss": 2.7855,
|
| 416 |
-
"step": 204
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 2.03,
|
| 420 |
-
"learning_rate": 8e-05,
|
| 421 |
-
"loss": 2.7826,
|
| 422 |
-
"step": 207
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 2.06,
|
| 426 |
-
"learning_rate": 8e-05,
|
| 427 |
-
"loss": 2.7339,
|
| 428 |
-
"step": 210
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 2.09,
|
| 432 |
-
"learning_rate": 8e-05,
|
| 433 |
-
"loss": 2.7663,
|
| 434 |
-
"step": 213
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 2.12,
|
| 438 |
-
"learning_rate": 8e-05,
|
| 439 |
-
"loss": 2.775,
|
| 440 |
-
"step": 216
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 2.15,
|
| 444 |
-
"learning_rate": 8e-05,
|
| 445 |
-
"loss": 2.7496,
|
| 446 |
-
"step": 219
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 2.18,
|
| 450 |
-
"learning_rate": 8e-05,
|
| 451 |
-
"loss": 2.6277,
|
| 452 |
-
"step": 222
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 2.21,
|
| 456 |
-
"learning_rate": 8e-05,
|
| 457 |
-
"loss": 2.6725,
|
| 458 |
-
"step": 225
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 2.24,
|
| 462 |
-
"learning_rate": 8e-05,
|
| 463 |
-
"loss": 2.6692,
|
| 464 |
-
"step": 228
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 2.26,
|
| 468 |
-
"learning_rate": 8e-05,
|
| 469 |
-
"loss": 2.7542,
|
| 470 |
-
"step": 231
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 2.29,
|
| 474 |
-
"learning_rate": 8e-05,
|
| 475 |
-
"loss": 2.7232,
|
| 476 |
-
"step": 234
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"epoch": 2.32,
|
| 480 |
-
"learning_rate": 8e-05,
|
| 481 |
-
"loss": 2.6342,
|
| 482 |
-
"step": 237
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 2.35,
|
| 486 |
-
"learning_rate": 8e-05,
|
| 487 |
-
"loss": 2.7458,
|
| 488 |
-
"step": 240
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 2.38,
|
| 492 |
-
"learning_rate": 8e-05,
|
| 493 |
-
"loss": 2.5471,
|
| 494 |
-
"step": 243
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 2.41,
|
| 498 |
-
"learning_rate": 8e-05,
|
| 499 |
-
"loss": 2.7454,
|
| 500 |
-
"step": 246
|
| 501 |
},
|
| 502 |
{
|
| 503 |
-
"epoch":
|
| 504 |
-
"
|
| 505 |
-
"
|
| 506 |
-
"
|
|
|
|
|
|
|
|
|
|
| 507 |
}
|
| 508 |
],
|
| 509 |
-
"max_steps":
|
| 510 |
-
"num_train_epochs":
|
| 511 |
-
"total_flos":
|
| 512 |
"trial_name": null,
|
| 513 |
"trial_params": null
|
| 514 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.991123701605288,
|
| 5 |
+
"global_step": 164,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 9.999059852242507e-05,
|
| 13 |
+
"loss": 3.0887,
|
| 14 |
"step": 3
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 9.98496470583896e-05,
|
| 19 |
+
"loss": 3.0765,
|
| 20 |
"step": 6
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.11,
|
| 24 |
+
"learning_rate": 9.954002016824227e-05,
|
| 25 |
+
"loss": 3.0999,
|
| 26 |
"step": 9
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.15,
|
| 30 |
+
"learning_rate": 9.906276553136923e-05,
|
| 31 |
+
"loss": 3.1509,
|
| 32 |
"step": 12
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.18,
|
| 36 |
+
"learning_rate": 9.84194980263903e-05,
|
| 37 |
+
"loss": 3.0782,
|
| 38 |
"step": 15
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.22,
|
| 42 |
+
"learning_rate": 9.761239426692077e-05,
|
| 43 |
+
"loss": 3.1602,
|
| 44 |
"step": 18
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.25,
|
| 48 |
+
"learning_rate": 9.664418523660004e-05,
|
| 49 |
+
"loss": 3.1038,
|
| 50 |
"step": 21
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.29,
|
| 54 |
+
"learning_rate": 9.551814704830734e-05,
|
| 55 |
+
"loss": 3.1121,
|
| 56 |
"step": 24
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.33,
|
| 60 |
+
"learning_rate": 9.423808985883289e-05,
|
| 61 |
+
"loss": 3.1254,
|
| 62 |
"step": 27
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.36,
|
| 66 |
+
"learning_rate": 9.280834497651334e-05,
|
| 67 |
+
"loss": 3.0885,
|
| 68 |
"step": 30
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 0.4,
|
| 72 |
+
"learning_rate": 9.123375020545535e-05,
|
| 73 |
+
"loss": 3.1051,
|
| 74 |
"step": 33
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.44,
|
| 78 |
+
"learning_rate": 8.951963347593797e-05,
|
| 79 |
+
"loss": 3.0836,
|
| 80 |
"step": 36
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.47,
|
| 84 |
+
"learning_rate": 8.767179481638303e-05,
|
| 85 |
+
"loss": 3.1576,
|
| 86 |
"step": 39
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.51,
|
| 90 |
+
"learning_rate": 8.569648672789497e-05,
|
| 91 |
+
"loss": 3.0979,
|
| 92 |
"step": 42
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.54,
|
| 96 |
+
"learning_rate": 8.360039302777612e-05,
|
| 97 |
+
"loss": 3.0679,
|
| 98 |
"step": 45
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.58,
|
| 102 |
+
"learning_rate": 8.139060623360493e-05,
|
| 103 |
+
"loss": 3.1112,
|
| 104 |
"step": 48
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 0.62,
|
| 108 |
+
"learning_rate": 7.907460356440133e-05,
|
| 109 |
+
"loss": 3.1174,
|
| 110 |
"step": 51
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 0.65,
|
| 114 |
+
"learning_rate": 7.666022164008457e-05,
|
| 115 |
+
"loss": 3.102,
|
| 116 |
"step": 54
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.69,
|
| 120 |
+
"learning_rate": 7.415562996483192e-05,
|
| 121 |
+
"loss": 3.1074,
|
| 122 |
"step": 57
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.73,
|
| 126 |
+
"learning_rate": 7.156930328406268e-05,
|
| 127 |
+
"loss": 3.1113,
|
| 128 |
"step": 60
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.76,
|
| 132 |
+
"learning_rate": 6.890999290858214e-05,
|
| 133 |
+
"loss": 3.0953,
|
| 134 |
"step": 63
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 0.8,
|
| 138 |
+
"learning_rate": 6.618669710291606e-05,
|
| 139 |
+
"loss": 3.1204,
|
| 140 |
"step": 66
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 0.83,
|
| 144 |
+
"learning_rate": 6.340863063803188e-05,
|
| 145 |
+
"loss": 3.1302,
|
| 146 |
"step": 69
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 0.87,
|
| 150 |
+
"learning_rate": 6.058519361147055e-05,
|
| 151 |
+
"loss": 3.0968,
|
| 152 |
"step": 72
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 0.91,
|
| 156 |
+
"learning_rate": 5.772593964039203e-05,
|
| 157 |
+
"loss": 3.0979,
|
| 158 |
"step": 75
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 0.94,
|
| 162 |
+
"learning_rate": 5.484054353515896e-05,
|
| 163 |
+
"loss": 3.0957,
|
| 164 |
"step": 78
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.98,
|
| 168 |
+
"learning_rate": 5.193876856284085e-05,
|
| 169 |
+
"loss": 3.1284,
|
| 170 |
"step": 81
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 1.02,
|
| 174 |
+
"learning_rate": 4.903043341140879e-05,
|
| 175 |
+
"loss": 3.8455,
|
| 176 |
"step": 84
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 1.06,
|
| 180 |
+
"learning_rate": 4.612537896640346e-05,
|
| 181 |
+
"loss": 3.0487,
|
| 182 |
"step": 87
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 1.1,
|
| 186 |
+
"learning_rate": 4.323343501249346e-05,
|
| 187 |
+
"loss": 3.0762,
|
| 188 |
"step": 90
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 1.13,
|
| 192 |
+
"learning_rate": 4.036438697259551e-05,
|
| 193 |
+
"loss": 3.1029,
|
| 194 |
"step": 93
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 1.17,
|
| 198 |
+
"learning_rate": 3.752794279710094e-05,
|
| 199 |
+
"loss": 3.0846,
|
| 200 |
"step": 96
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 1.21,
|
| 204 |
+
"learning_rate": 3.473370011524435e-05,
|
| 205 |
+
"loss": 3.0986,
|
| 206 |
"step": 99
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 1.24,
|
| 210 |
+
"learning_rate": 3.199111375976449e-05,
|
| 211 |
+
"loss": 3.1148,
|
| 212 |
"step": 102
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 1.28,
|
| 216 |
+
"learning_rate": 2.9309463774743046e-05,
|
| 217 |
+
"loss": 3.076,
|
| 218 |
"step": 105
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 1.31,
|
| 222 |
+
"learning_rate": 2.6697824014873075e-05,
|
| 223 |
+
"loss": 3.0731,
|
| 224 |
"step": 108
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 1.35,
|
| 228 |
+
"learning_rate": 2.4165031442406855e-05,
|
| 229 |
+
"loss": 3.1045,
|
| 230 |
"step": 111
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 1.39,
|
| 234 |
+
"learning_rate": 2.171965622567308e-05,
|
| 235 |
+
"loss": 3.1026,
|
| 236 |
"step": 114
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 1.42,
|
| 240 |
+
"learning_rate": 1.936997274033986e-05,
|
| 241 |
+
"loss": 3.0352,
|
| 242 |
"step": 117
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 1.46,
|
| 246 |
+
"learning_rate": 1.7123931571546827e-05,
|
| 247 |
+
"loss": 3.0999,
|
| 248 |
"step": 120
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 1.5,
|
| 252 |
+
"learning_rate": 1.4989132611641576e-05,
|
| 253 |
+
"loss": 3.0609,
|
| 254 |
"step": 123
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 1.53,
|
| 258 |
+
"learning_rate": 1.297279934454978e-05,
|
| 259 |
+
"loss": 3.0611,
|
| 260 |
"step": 126
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 1.57,
|
| 264 |
+
"learning_rate": 1.1081754403791999e-05,
|
| 265 |
+
"loss": 3.1195,
|
| 266 |
"step": 129
|
| 267 |
},
|
| 268 |
{
|
| 269 |
+
"epoch": 1.6,
|
| 270 |
+
"learning_rate": 9.322396486851626e-06,
|
| 271 |
+
"loss": 3.0566,
|
| 272 |
"step": 132
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 1.64,
|
| 276 |
+
"learning_rate": 7.700678704007947e-06,
|
| 277 |
+
"loss": 3.1333,
|
| 278 |
"step": 135
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 1.68,
|
| 282 |
+
"learning_rate": 6.222088434895462e-06,
|
| 283 |
+
"loss": 3.0838,
|
| 284 |
"step": 138
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 1.71,
|
| 288 |
+
"learning_rate": 4.891628760948114e-06,
|
| 289 |
+
"loss": 3.1032,
|
| 290 |
"step": 141
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"epoch": 1.75,
|
| 294 |
+
"learning_rate": 3.7138015365554833e-06,
|
| 295 |
+
"loss": 3.0524,
|
| 296 |
"step": 144
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 1.79,
|
| 300 |
+
"learning_rate": 2.692592156212487e-06,
|
| 301 |
+
"loss": 3.0527,
|
| 302 |
"step": 147
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 1.82,
|
| 306 |
+
"learning_rate": 1.8314560692059835e-06,
|
| 307 |
+
"loss": 3.0637,
|
| 308 |
"step": 150
|
| 309 |
},
|
| 310 |
{
|
| 311 |
+
"epoch": 1.86,
|
| 312 |
+
"learning_rate": 1.1333070874682216e-06,
|
| 313 |
+
"loss": 3.0875,
|
| 314 |
"step": 153
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 1.89,
|
| 318 |
+
"learning_rate": 6.005075261595494e-07,
|
| 319 |
+
"loss": 3.0881,
|
| 320 |
"step": 156
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 1.93,
|
| 324 |
+
"learning_rate": 2.3486021034170857e-07,
|
| 325 |
+
"loss": 3.0721,
|
| 326 |
"step": 159
|
| 327 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 328 |
{
|
| 329 |
"epoch": 1.97,
|
| 330 |
+
"learning_rate": 3.760237478849793e-08,
|
| 331 |
+
"loss": 3.0953,
|
| 332 |
+
"step": 162
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 1.99,
|
| 336 |
+
"step": 164,
|
| 337 |
+
"total_flos": 1.5551382941597696e+18,
|
| 338 |
+
"train_loss": 3.1085294397865852,
|
| 339 |
+
"train_runtime": 68661.2713,
|
| 340 |
+
"train_samples_per_second": 0.308,
|
| 341 |
+
"train_steps_per_second": 0.002
|
| 342 |
}
|
| 343 |
],
|
| 344 |
+
"max_steps": 164,
|
| 345 |
+
"num_train_epochs": 2,
|
| 346 |
+
"total_flos": 1.5551382941597696e+18,
|
| 347 |
"trial_name": null,
|
| 348 |
"trial_params": null
|
| 349 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4527
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc21bf03b7dee18113f5e242548f50beac3112d633843f73cbb60625e5d61dc4
|
| 3 |
size 4527
|