+2 epochs finetuning @ 16384 tokens input
Browse files- config.json +2 -2
- optimizer.pt +3 -0
- pegasus-x-large-book-summary-ft1-booksum-VM_training_metadata.json +1 -0
- pytorch_model.bin +1 -1
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +0 -0
- spiece.model +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- trainer_state.json +754 -244
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "pszemraj/pegasus-x-large-
|
| 3 |
"activation_dropout": 0.1,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"add_bias_logits": false,
|
|
@@ -58,7 +58,7 @@
|
|
| 58 |
"stagger_local_blocks": true,
|
| 59 |
"static_position_embeddings": true,
|
| 60 |
"torch_dtype": "float32",
|
| 61 |
-
"transformers_version": "4.22.
|
| 62 |
"use_cache": false,
|
| 63 |
"vocab_size": 96103
|
| 64 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "pszemraj/pegasus-x-large-book-summary",
|
| 3 |
"activation_dropout": 0.1,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"add_bias_logits": false,
|
|
|
|
| 58 |
"stagger_local_blocks": true,
|
| 59 |
"static_position_embeddings": true,
|
| 60 |
"torch_dtype": "float32",
|
| 61 |
+
"transformers_version": "4.22.1",
|
| 62 |
"use_cache": false,
|
| 63 |
"vocab_size": 96103
|
| 64 |
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146dd0d4c3af260356f5719af968fe848ce7b88bd60a8b12c5ac82d78cc65785
|
| 3 |
+
size 9099282225
|
pegasus-x-large-book-summary-ft1-booksum-VM_training_metadata.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"output_dir": "/workspace/model-checkpoints", "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": 4, "per_device_eval_batch_size": 1, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 16, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 0.0004, "weight_decay": 0.01, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1, "num_train_epochs": 2, "max_steps": -1, "lr_scheduler_type": "cosine", "warmup_ratio": 0.03, "warmup_steps": 0, "log_level": -1, "log_level_replica": -1, "log_on_each_node": true, "logging_dir": "/workspace/logs", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 2, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 10, "save_total_limit": 2, "save_on_each_node": false, "no_cuda": false, "use_mps_device": 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": true, "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": "/workspace/model-checkpoints", "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, "fsdp_transformer_layer_cls_to_wrap": "None", "deepspeed": "None", "label_smoothing_factor": 0.0, "optim": "adamw_hf", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": "['tensorboard', 'wandb']", "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "dataloader_pin_memory": true, "skip_memory_metrics": false, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": "None", "hub_model_id": "pegasus-x-large-book-summary-ft1-booksum-VM", "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", "ddp_timeout": 1800, "sortish_sampler": false, "predict_with_generate": false, "generation_max_length": "None", "generation_num_beams": "None", "train_batch_size": 4, "eval_batch_size": 1, "configs_src": "pegasus-x-large-book-summary-ft1-booksum-VM", "use_adam8bit": false, "use_adan_optim": true, "optim_params": "(Adan (\nParameter Group 0\n betas: (0.01, 0.08, 0.001)\n eps: 1e-08\n lr: 0.0004\n restart_cond: None\n weight_decay: 0.01\n\nParameter Group 1\n betas: (0.01, 0.08, 0.001)\n eps: 1e-08\n lr: 0.0004\n restart_cond: None\n weight_decay: 0.0\n), None)", "decay_rate_ada": -0.8}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2274842165
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0f815b0cf70fc968e46dd77313e5e0388d8dafe5660154d0b2bad6fa91c8bc5
|
| 3 |
size 2274842165
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11e5e9cb51c97260ca4e68dbbcbc7fc22f21f540ffcb907345b110eb28728805
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f2ec3ce41d0570741b3c6ba9754b947077c63ae596208fce62483452e5eac86
|
| 3 |
+
size 623
|
special_tokens_map.json
CHANGED
|
File without changes
|
spiece.model
CHANGED
|
File without changes
|
tokenizer.json
CHANGED
|
File without changes
|
tokenizer_config.json
CHANGED
|
@@ -108,7 +108,7 @@
|
|
| 108 |
"mask_token": "<mask_2>",
|
| 109 |
"mask_token_sent": "<mask_1>",
|
| 110 |
"model_max_length": 1024,
|
| 111 |
-
"name_or_path": "pszemraj/pegasus-x-large-
|
| 112 |
"offset": 103,
|
| 113 |
"pad_token": "<pad>",
|
| 114 |
"sp_model_kwargs": {},
|
|
|
|
| 108 |
"mask_token": "<mask_2>",
|
| 109 |
"mask_token_sent": "<mask_1>",
|
| 110 |
"model_max_length": 1024,
|
| 111 |
+
"name_or_path": "pszemraj/pegasus-x-large-book-summary",
|
| 112 |
"offset": 103,
|
| 113 |
"pad_token": "<pad>",
|
| 114 |
"sp_model_kwargs": {},
|
trainer_state.json
CHANGED
|
@@ -1,496 +1,1006 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.
|
| 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": 2.
|
| 14 |
"step": 2
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 2.
|
| 20 |
"step": 4
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 2.
|
| 26 |
"step": 6
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 2.
|
| 32 |
"step": 8
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 2.
|
| 38 |
"step": 10
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 2.
|
| 44 |
"step": 12
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 2.
|
| 50 |
"step": 14
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch": 0.
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 2.
|
| 56 |
"step": 16
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch": 0.
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 2.
|
| 62 |
"step": 18
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch": 0.
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 2.
|
| 68 |
"step": 20
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch": 0.
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 2.
|
| 74 |
"step": 22
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 0.
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 2.
|
| 80 |
"step": 24
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 2.
|
| 86 |
"step": 26
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 2.
|
| 92 |
"step": 28
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 0.
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 2.
|
| 98 |
"step": 30
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 0.
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 2.
|
| 104 |
"step": 32
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch": 0.
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 2.
|
| 110 |
"step": 34
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch": 0.
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 2.
|
| 116 |
"step": 36
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 0.
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 2.
|
| 122 |
"step": 38
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 0.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 2.
|
| 128 |
"step": 40
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 2.
|
| 134 |
"step": 42
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 0.
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss": 2.
|
| 140 |
"step": 44
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch": 0.
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss": 2.
|
| 146 |
"step": 46
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch": 0.
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 2.
|
| 152 |
"step": 48
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch": 0.
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 2.
|
| 158 |
"step": 50
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch": 0.
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss": 2.
|
| 164 |
"step": 52
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 0.
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 2.
|
| 170 |
"step": 54
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss": 2.
|
| 176 |
"step": 56
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch": 0.
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss": 2.
|
| 182 |
"step": 58
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch": 0.
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss": 2.
|
| 188 |
"step": 60
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch": 0.
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 2.
|
| 194 |
"step": 62
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch": 0.
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss": 2.
|
| 200 |
"step": 64
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch": 0.
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss": 2.
|
| 206 |
"step": 66
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch": 0.
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 2.
|
| 212 |
"step": 68
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 0.
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss": 2.
|
| 218 |
"step": 70
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch": 0.
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss": 2.
|
| 224 |
"step": 72
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch": 0.
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss": 2.
|
| 230 |
"step": 74
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch": 0.
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss": 2.
|
| 236 |
"step": 76
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch": 0.
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss": 2.
|
| 242 |
"step": 78
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch": 0.
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss": 2.
|
| 248 |
"step": 80
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch": 0.
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 2.
|
| 254 |
"step": 82
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch":
|
| 258 |
-
"learning_rate":
|
| 259 |
-
"loss":
|
| 260 |
"step": 84
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch":
|
| 264 |
-
"learning_rate":
|
| 265 |
-
"loss": 2.
|
| 266 |
"step": 86
|
| 267 |
},
|
| 268 |
{
|
| 269 |
-
"epoch":
|
| 270 |
-
"learning_rate":
|
| 271 |
-
"loss": 2.
|
| 272 |
"step": 88
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch":
|
| 276 |
-
"learning_rate":
|
| 277 |
-
"loss": 2.
|
| 278 |
"step": 90
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch":
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss": 2.
|
| 284 |
"step": 92
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch":
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 2.
|
| 290 |
"step": 94
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"epoch":
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 2.
|
| 296 |
"step": 96
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch":
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss": 2.
|
| 302 |
"step": 98
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch":
|
| 306 |
-
"learning_rate":
|
| 307 |
-
"loss": 2.
|
| 308 |
"step": 100
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch":
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss": 2.
|
| 314 |
"step": 102
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch":
|
| 318 |
-
"learning_rate":
|
| 319 |
-
"loss": 2.
|
| 320 |
"step": 104
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch":
|
| 324 |
-
"learning_rate":
|
| 325 |
-
"loss": 2.
|
| 326 |
"step": 106
|
| 327 |
},
|
| 328 |
{
|
| 329 |
-
"epoch":
|
| 330 |
-
"learning_rate":
|
| 331 |
-
"loss": 2.
|
| 332 |
"step": 108
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch":
|
| 336 |
-
"learning_rate":
|
| 337 |
-
"loss": 2.
|
| 338 |
"step": 110
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch":
|
| 342 |
-
"learning_rate":
|
| 343 |
-
"loss": 2.
|
| 344 |
"step": 112
|
| 345 |
},
|
| 346 |
{
|
| 347 |
-
"epoch":
|
| 348 |
-
"learning_rate":
|
| 349 |
-
"loss": 2.
|
| 350 |
"step": 114
|
| 351 |
},
|
| 352 |
{
|
| 353 |
-
"epoch":
|
| 354 |
-
"learning_rate":
|
| 355 |
-
"loss": 2.
|
| 356 |
"step": 116
|
| 357 |
},
|
| 358 |
{
|
| 359 |
-
"epoch":
|
| 360 |
-
"learning_rate":
|
| 361 |
-
"loss": 2.
|
| 362 |
"step": 118
|
| 363 |
},
|
| 364 |
{
|
| 365 |
-
"epoch":
|
| 366 |
-
"learning_rate":
|
| 367 |
-
"loss": 2.
|
| 368 |
"step": 120
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch":
|
| 372 |
-
"learning_rate":
|
| 373 |
-
"loss": 2.
|
| 374 |
"step": 122
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch":
|
| 378 |
-
"learning_rate":
|
| 379 |
-
"loss": 2.
|
| 380 |
"step": 124
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch":
|
| 384 |
-
"learning_rate":
|
| 385 |
-
"loss": 2.
|
| 386 |
"step": 126
|
| 387 |
},
|
| 388 |
{
|
| 389 |
-
"epoch":
|
| 390 |
-
"learning_rate":
|
| 391 |
-
"loss": 2.
|
| 392 |
"step": 128
|
| 393 |
},
|
| 394 |
{
|
| 395 |
-
"epoch":
|
| 396 |
-
"learning_rate":
|
| 397 |
-
"loss": 2.
|
| 398 |
"step": 130
|
| 399 |
},
|
| 400 |
{
|
| 401 |
-
"epoch":
|
| 402 |
-
"learning_rate":
|
| 403 |
-
"loss": 2.
|
| 404 |
"step": 132
|
| 405 |
},
|
| 406 |
{
|
| 407 |
-
"epoch":
|
| 408 |
-
"learning_rate":
|
| 409 |
-
"loss": 2.
|
| 410 |
"step": 134
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"epoch":
|
| 414 |
-
"learning_rate":
|
| 415 |
-
"loss": 2.
|
| 416 |
"step": 136
|
| 417 |
},
|
| 418 |
{
|
| 419 |
-
"epoch":
|
| 420 |
-
"learning_rate":
|
| 421 |
-
"loss": 2.
|
| 422 |
"step": 138
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch":
|
| 426 |
-
"learning_rate":
|
| 427 |
-
"loss": 2.
|
| 428 |
"step": 140
|
| 429 |
},
|
| 430 |
{
|
| 431 |
-
"epoch":
|
| 432 |
-
"learning_rate":
|
| 433 |
-
"loss": 2.
|
| 434 |
"step": 142
|
| 435 |
},
|
| 436 |
{
|
| 437 |
-
"epoch":
|
| 438 |
-
"learning_rate":
|
| 439 |
-
"loss": 2.
|
| 440 |
"step": 144
|
| 441 |
},
|
| 442 |
{
|
| 443 |
-
"epoch":
|
| 444 |
-
"learning_rate":
|
| 445 |
-
"loss": 2.
|
| 446 |
"step": 146
|
| 447 |
},
|
| 448 |
{
|
| 449 |
-
"epoch":
|
| 450 |
-
"learning_rate":
|
| 451 |
-
"loss": 2.
|
| 452 |
"step": 148
|
| 453 |
},
|
| 454 |
{
|
| 455 |
-
"epoch":
|
| 456 |
-
"learning_rate":
|
| 457 |
-
"loss": 2.
|
| 458 |
"step": 150
|
| 459 |
},
|
| 460 |
{
|
| 461 |
-
"epoch":
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss": 2.
|
| 464 |
"step": 152
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch":
|
| 468 |
-
"learning_rate":
|
| 469 |
-
"loss": 2.
|
| 470 |
"step": 154
|
| 471 |
},
|
| 472 |
{
|
| 473 |
-
"epoch":
|
| 474 |
-
"learning_rate":
|
| 475 |
-
"loss": 2.
|
| 476 |
"step": 156
|
| 477 |
},
|
| 478 |
{
|
| 479 |
-
"epoch":
|
| 480 |
-
"learning_rate":
|
| 481 |
-
"loss": 2.
|
| 482 |
"step": 158
|
| 483 |
},
|
| 484 |
{
|
| 485 |
-
"epoch":
|
| 486 |
-
"learning_rate":
|
| 487 |
-
"loss": 2.
|
| 488 |
"step": 160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 489 |
}
|
| 490 |
],
|
| 491 |
-
"max_steps":
|
| 492 |
"num_train_epochs": 2,
|
| 493 |
-
"total_flos":
|
| 494 |
"trial_name": null,
|
| 495 |
"trial_params": null
|
| 496 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9969788519637461,
|
| 5 |
+
"global_step": 330,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 8e-05,
|
| 13 |
+
"loss": 2.1157,
|
| 14 |
"step": 2
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 0.00016,
|
| 19 |
+
"loss": 2.2075,
|
| 20 |
"step": 4
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 0.00024,
|
| 25 |
+
"loss": 2.1208,
|
| 26 |
"step": 6
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.05,
|
| 30 |
+
"learning_rate": 0.00032,
|
| 31 |
+
"loss": 2.2187,
|
| 32 |
"step": 8
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.06,
|
| 36 |
+
"learning_rate": 0.0004,
|
| 37 |
+
"loss": 2.2193,
|
| 38 |
"step": 10
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.07,
|
| 42 |
+
"learning_rate": 0.000399961448096413,
|
| 43 |
+
"loss": 2.1887,
|
| 44 |
"step": 12
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.08,
|
| 48 |
+
"learning_rate": 0.0003998458072481446,
|
| 49 |
+
"loss": 2.1639,
|
| 50 |
"step": 14
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.1,
|
| 54 |
+
"learning_rate": 0.00039965312203694324,
|
| 55 |
+
"loss": 2.1191,
|
| 56 |
"step": 16
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.11,
|
| 60 |
+
"learning_rate": 0.0003993834667466256,
|
| 61 |
+
"loss": 2.1907,
|
| 62 |
"step": 18
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.12,
|
| 66 |
+
"learning_rate": 0.0003990369453344394,
|
| 67 |
+
"loss": 2.1976,
|
| 68 |
"step": 20
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 0.13,
|
| 72 |
+
"learning_rate": 0.0003986136913909853,
|
| 73 |
+
"loss": 2.163,
|
| 74 |
"step": 22
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.15,
|
| 78 |
+
"learning_rate": 0.00039811386808871546,
|
| 79 |
+
"loss": 2.2323,
|
| 80 |
"step": 24
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.16,
|
| 84 |
+
"learning_rate": 0.00039753766811902755,
|
| 85 |
+
"loss": 2.1354,
|
| 86 |
"step": 26
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.17,
|
| 90 |
+
"learning_rate": 0.00039688531361797835,
|
| 91 |
+
"loss": 2.1643,
|
| 92 |
"step": 28
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.18,
|
| 96 |
+
"learning_rate": 0.0003961570560806461,
|
| 97 |
+
"loss": 2.2129,
|
| 98 |
"step": 30
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.19,
|
| 102 |
+
"learning_rate": 0.0003953531762641745,
|
| 103 |
+
"loss": 2.1702,
|
| 104 |
"step": 32
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 0.21,
|
| 108 |
+
"learning_rate": 0.0003944739840795353,
|
| 109 |
+
"loss": 2.1848,
|
| 110 |
"step": 34
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 0.22,
|
| 114 |
+
"learning_rate": 0.00039351981847205196,
|
| 115 |
+
"loss": 2.1619,
|
| 116 |
"step": 36
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.23,
|
| 120 |
+
"learning_rate": 0.00039249104729072946,
|
| 121 |
+
"loss": 2.1781,
|
| 122 |
"step": 38
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.24,
|
| 126 |
+
"learning_rate": 0.0003913880671464418,
|
| 127 |
+
"loss": 2.2253,
|
| 128 |
"step": 40
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.25,
|
| 132 |
+
"learning_rate": 0.00039021130325903074,
|
| 133 |
+
"loss": 2.1372,
|
| 134 |
"step": 42
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 0.27,
|
| 138 |
+
"learning_rate": 0.00038896120929337566,
|
| 139 |
+
"loss": 2.1798,
|
| 140 |
"step": 44
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 0.28,
|
| 144 |
+
"learning_rate": 0.00038763826718449685,
|
| 145 |
+
"loss": 2.1592,
|
| 146 |
"step": 46
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 0.29,
|
| 150 |
+
"learning_rate": 0.00038624298695176073,
|
| 151 |
+
"loss": 2.1695,
|
| 152 |
"step": 48
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 0.3,
|
| 156 |
+
"learning_rate": 0.0003847759065022574,
|
| 157 |
+
"loss": 2.2302,
|
| 158 |
"step": 50
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 0.31,
|
| 162 |
+
"learning_rate": 0.00038323759142342724,
|
| 163 |
+
"loss": 2.2537,
|
| 164 |
"step": 52
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.33,
|
| 168 |
+
"learning_rate": 0.0003816286347650163,
|
| 169 |
+
"loss": 2.2121,
|
| 170 |
"step": 54
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.34,
|
| 174 |
+
"learning_rate": 0.00037994965681044433,
|
| 175 |
+
"loss": 2.1516,
|
| 176 |
"step": 56
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 0.35,
|
| 180 |
+
"learning_rate": 0.0003782013048376736,
|
| 181 |
+
"loss": 2.1707,
|
| 182 |
"step": 58
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 0.36,
|
| 186 |
+
"learning_rate": 0.000376384252869671,
|
| 187 |
+
"loss": 2.202,
|
| 188 |
"step": 60
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 0.37,
|
| 192 |
+
"learning_rate": 0.00037449920141455944,
|
| 193 |
+
"loss": 2.1967,
|
| 194 |
"step": 62
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 0.39,
|
| 198 |
+
"learning_rate": 0.0003725468771955584,
|
| 199 |
+
"loss": 2.1701,
|
| 200 |
"step": 64
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 0.4,
|
| 204 |
+
"learning_rate": 0.00037052803287081844,
|
| 205 |
+
"loss": 2.1082,
|
| 206 |
"step": 66
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 0.41,
|
| 210 |
+
"learning_rate": 0.00036844344674325733,
|
| 211 |
+
"loss": 2.151,
|
| 212 |
"step": 68
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.42,
|
| 216 |
+
"learning_rate": 0.0003662939224605091,
|
| 217 |
+
"loss": 2.2102,
|
| 218 |
"step": 70
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 0.44,
|
| 222 |
+
"learning_rate": 0.0003640802887051027,
|
| 223 |
+
"loss": 2.187,
|
| 224 |
"step": 72
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 0.45,
|
| 228 |
+
"learning_rate": 0.0003618033988749895,
|
| 229 |
+
"loss": 2.2118,
|
| 230 |
"step": 74
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 0.46,
|
| 234 |
+
"learning_rate": 0.00035946413075454146,
|
| 235 |
+
"loss": 2.2232,
|
| 236 |
"step": 76
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 0.47,
|
| 240 |
+
"learning_rate": 0.00035706338617614897,
|
| 241 |
+
"loss": 2.1897,
|
| 242 |
"step": 78
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 0.48,
|
| 246 |
+
"learning_rate": 0.0003546020906725474,
|
| 247 |
+
"loss": 2.2366,
|
| 248 |
"step": 80
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 0.5,
|
| 252 |
+
"learning_rate": 0.0003520811931200062,
|
| 253 |
+
"loss": 2.1615,
|
| 254 |
"step": 82
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.51,
|
| 258 |
+
"learning_rate": 0.0003495016653725194,
|
| 259 |
+
"loss": 2.1765,
|
| 260 |
"step": 84
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 0.52,
|
| 264 |
+
"learning_rate": 0.0003468645018871371,
|
| 265 |
+
"loss": 2.2205,
|
| 266 |
"step": 86
|
| 267 |
},
|
| 268 |
{
|
| 269 |
+
"epoch": 0.53,
|
| 270 |
+
"learning_rate": 0.00034417071934058377,
|
| 271 |
+
"loss": 2.1722,
|
| 272 |
"step": 88
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 0.54,
|
| 276 |
+
"learning_rate": 0.0003414213562373095,
|
| 277 |
+
"loss": 2.1726,
|
| 278 |
"step": 90
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 0.56,
|
| 282 |
+
"learning_rate": 0.0003386174725091272,
|
| 283 |
+
"loss": 2.1401,
|
| 284 |
"step": 92
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 0.57,
|
| 288 |
+
"learning_rate": 0.0003357601491065884,
|
| 289 |
+
"loss": 2.2254,
|
| 290 |
"step": 94
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"epoch": 0.58,
|
| 294 |
+
"learning_rate": 0.00033285048758225635,
|
| 295 |
+
"loss": 2.1489,
|
| 296 |
"step": 96
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 0.59,
|
| 300 |
+
"learning_rate": 0.0003298896096660367,
|
| 301 |
+
"loss": 2.2459,
|
| 302 |
"step": 98
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 0.6,
|
| 306 |
+
"learning_rate": 0.0003268786568327291,
|
| 307 |
+
"loss": 2.2103,
|
| 308 |
"step": 100
|
| 309 |
},
|
| 310 |
{
|
| 311 |
+
"epoch": 0.62,
|
| 312 |
+
"learning_rate": 0.00032381878986196687,
|
| 313 |
+
"loss": 2.1864,
|
| 314 |
"step": 102
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 0.63,
|
| 318 |
+
"learning_rate": 0.0003207111883907143,
|
| 319 |
+
"loss": 2.1641,
|
| 320 |
"step": 104
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 0.64,
|
| 324 |
+
"learning_rate": 0.00031755705045849464,
|
| 325 |
+
"loss": 2.1346,
|
| 326 |
"step": 106
|
| 327 |
},
|
| 328 |
{
|
| 329 |
+
"epoch": 0.65,
|
| 330 |
+
"learning_rate": 0.00031435759204552244,
|
| 331 |
+
"loss": 2.1639,
|
| 332 |
"step": 108
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 0.66,
|
| 336 |
+
"learning_rate": 0.00031111404660392046,
|
| 337 |
+
"loss": 2.2032,
|
| 338 |
"step": 110
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 0.68,
|
| 342 |
+
"learning_rate": 0.00030782766458220014,
|
| 343 |
+
"loss": 2.2095,
|
| 344 |
"step": 112
|
| 345 |
},
|
| 346 |
{
|
| 347 |
+
"epoch": 0.69,
|
| 348 |
+
"learning_rate": 0.0003044997129431898,
|
| 349 |
+
"loss": 2.1789,
|
| 350 |
"step": 114
|
| 351 |
},
|
| 352 |
{
|
| 353 |
+
"epoch": 0.7,
|
| 354 |
+
"learning_rate": 0.00030113147467559695,
|
| 355 |
+
"loss": 2.1947,
|
| 356 |
"step": 116
|
| 357 |
},
|
| 358 |
{
|
| 359 |
+
"epoch": 0.71,
|
| 360 |
+
"learning_rate": 0.00029772424829939106,
|
| 361 |
+
"loss": 2.2011,
|
| 362 |
"step": 118
|
| 363 |
},
|
| 364 |
{
|
| 365 |
+
"epoch": 0.73,
|
| 366 |
+
"learning_rate": 0.0002942793473651996,
|
| 367 |
+
"loss": 2.1956,
|
| 368 |
"step": 120
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 0.74,
|
| 372 |
+
"learning_rate": 0.00029079809994790937,
|
| 373 |
+
"loss": 2.2043,
|
| 374 |
"step": 122
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 0.75,
|
| 378 |
+
"learning_rate": 0.0002872818481346684,
|
| 379 |
+
"loss": 2.1571,
|
| 380 |
"step": 124
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 0.76,
|
| 384 |
+
"learning_rate": 0.0002837319475074856,
|
| 385 |
+
"loss": 2.2016,
|
| 386 |
"step": 126
|
| 387 |
},
|
| 388 |
{
|
| 389 |
+
"epoch": 0.77,
|
| 390 |
+
"learning_rate": 0.0002801497666206282,
|
| 391 |
+
"loss": 2.182,
|
| 392 |
"step": 128
|
| 393 |
},
|
| 394 |
{
|
| 395 |
+
"epoch": 0.79,
|
| 396 |
+
"learning_rate": 0.000276536686473018,
|
| 397 |
+
"loss": 2.1583,
|
| 398 |
"step": 130
|
| 399 |
},
|
| 400 |
{
|
| 401 |
+
"epoch": 0.8,
|
| 402 |
+
"learning_rate": 0.00027289409997583,
|
| 403 |
+
"loss": 2.2161,
|
| 404 |
"step": 132
|
| 405 |
},
|
| 406 |
{
|
| 407 |
+
"epoch": 0.81,
|
| 408 |
+
"learning_rate": 0.0002692234114154986,
|
| 409 |
+
"loss": 2.2267,
|
| 410 |
"step": 134
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"epoch": 0.82,
|
| 414 |
+
"learning_rate": 0.00026552603591233873,
|
| 415 |
+
"loss": 2.2418,
|
| 416 |
"step": 136
|
| 417 |
},
|
| 418 |
{
|
| 419 |
+
"epoch": 0.83,
|
| 420 |
+
"learning_rate": 0.00026180339887498953,
|
| 421 |
+
"loss": 2.1828,
|
| 422 |
"step": 138
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 0.85,
|
| 426 |
+
"learning_rate": 0.00025805693545089247,
|
| 427 |
+
"loss": 2.1103,
|
| 428 |
"step": 140
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"epoch": 0.86,
|
| 432 |
+
"learning_rate": 0.00025428808997301485,
|
| 433 |
+
"loss": 2.2022,
|
| 434 |
"step": 142
|
| 435 |
},
|
| 436 |
{
|
| 437 |
+
"epoch": 0.87,
|
| 438 |
+
"learning_rate": 0.0002504983154030316,
|
| 439 |
+
"loss": 2.1691,
|
| 440 |
"step": 144
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"epoch": 0.88,
|
| 444 |
+
"learning_rate": 0.00024668907277118114,
|
| 445 |
+
"loss": 2.1787,
|
| 446 |
"step": 146
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 0.89,
|
| 450 |
+
"learning_rate": 0.00024286183061301015,
|
| 451 |
+
"loss": 2.2069,
|
| 452 |
"step": 148
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"epoch": 0.91,
|
| 456 |
+
"learning_rate": 0.0002390180644032257,
|
| 457 |
+
"loss": 2.2609,
|
| 458 |
"step": 150
|
| 459 |
},
|
| 460 |
{
|
| 461 |
+
"epoch": 0.92,
|
| 462 |
+
"learning_rate": 0.00023515925598687094,
|
| 463 |
+
"loss": 2.2089,
|
| 464 |
"step": 152
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 0.93,
|
| 468 |
+
"learning_rate": 0.0002312868930080462,
|
| 469 |
+
"loss": 2.1889,
|
| 470 |
"step": 154
|
| 471 |
},
|
| 472 |
{
|
| 473 |
+
"epoch": 0.94,
|
| 474 |
+
"learning_rate": 0.00022740246833639365,
|
| 475 |
+
"loss": 2.2167,
|
| 476 |
"step": 156
|
| 477 |
},
|
| 478 |
{
|
| 479 |
+
"epoch": 0.95,
|
| 480 |
+
"learning_rate": 0.00022350747949156756,
|
| 481 |
+
"loss": 2.1636,
|
| 482 |
"step": 158
|
| 483 |
},
|
| 484 |
{
|
| 485 |
+
"epoch": 0.97,
|
| 486 |
+
"learning_rate": 0.0002196034280659122,
|
| 487 |
+
"loss": 2.2215,
|
| 488 |
"step": 160
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.98,
|
| 492 |
+
"learning_rate": 0.000215691819145569,
|
| 493 |
+
"loss": 2.1903,
|
| 494 |
+
"step": 162
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.99,
|
| 498 |
+
"learning_rate": 0.0002117741607302378,
|
| 499 |
+
"loss": 2.2131,
|
| 500 |
+
"step": 164
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.01,
|
| 504 |
+
"learning_rate": 0.00020785196315181376,
|
| 505 |
+
"loss": 2.6465,
|
| 506 |
+
"step": 166
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.02,
|
| 510 |
+
"learning_rate": 0.00020392673849212566,
|
| 511 |
+
"loss": 2.18,
|
| 512 |
+
"step": 168
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.03,
|
| 516 |
+
"learning_rate": 0.0002,
|
| 517 |
+
"loss": 2.0911,
|
| 518 |
+
"step": 170
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.04,
|
| 522 |
+
"learning_rate": 0.00019607326150787436,
|
| 523 |
+
"loss": 2.1044,
|
| 524 |
+
"step": 172
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.05,
|
| 528 |
+
"learning_rate": 0.00019214803684818634,
|
| 529 |
+
"loss": 2.1266,
|
| 530 |
+
"step": 174
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.07,
|
| 534 |
+
"learning_rate": 0.00018822583926976218,
|
| 535 |
+
"loss": 2.1559,
|
| 536 |
+
"step": 176
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.08,
|
| 540 |
+
"learning_rate": 0.00018430818085443104,
|
| 541 |
+
"loss": 2.1522,
|
| 542 |
+
"step": 178
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.09,
|
| 546 |
+
"learning_rate": 0.00018039657193408788,
|
| 547 |
+
"loss": 2.1535,
|
| 548 |
+
"step": 180
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.1,
|
| 552 |
+
"learning_rate": 0.00017649252050843252,
|
| 553 |
+
"loss": 2.2344,
|
| 554 |
+
"step": 182
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.11,
|
| 558 |
+
"learning_rate": 0.00017259753166360642,
|
| 559 |
+
"loss": 2.121,
|
| 560 |
+
"step": 184
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.13,
|
| 564 |
+
"learning_rate": 0.00016871310699195379,
|
| 565 |
+
"loss": 2.1426,
|
| 566 |
+
"step": 186
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.14,
|
| 570 |
+
"learning_rate": 0.0001648407440131291,
|
| 571 |
+
"loss": 2.1322,
|
| 572 |
+
"step": 188
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.15,
|
| 576 |
+
"learning_rate": 0.00016098193559677438,
|
| 577 |
+
"loss": 2.1529,
|
| 578 |
+
"step": 190
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.16,
|
| 582 |
+
"learning_rate": 0.0001571381693869899,
|
| 583 |
+
"loss": 2.18,
|
| 584 |
+
"step": 192
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.18,
|
| 588 |
+
"learning_rate": 0.000153310927228819,
|
| 589 |
+
"loss": 2.1437,
|
| 590 |
+
"step": 194
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.19,
|
| 594 |
+
"learning_rate": 0.0001495016845969684,
|
| 595 |
+
"loss": 2.1725,
|
| 596 |
+
"step": 196
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.2,
|
| 600 |
+
"learning_rate": 0.00014571191002698517,
|
| 601 |
+
"loss": 2.1208,
|
| 602 |
+
"step": 198
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.21,
|
| 606 |
+
"learning_rate": 0.00014194306454910757,
|
| 607 |
+
"loss": 2.1427,
|
| 608 |
+
"step": 200
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.22,
|
| 612 |
+
"learning_rate": 0.00013819660112501054,
|
| 613 |
+
"loss": 2.1056,
|
| 614 |
+
"step": 202
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.24,
|
| 618 |
+
"learning_rate": 0.00013447396408766132,
|
| 619 |
+
"loss": 2.1255,
|
| 620 |
+
"step": 204
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.25,
|
| 624 |
+
"learning_rate": 0.00013077658858450138,
|
| 625 |
+
"loss": 2.1658,
|
| 626 |
+
"step": 206
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.26,
|
| 630 |
+
"learning_rate": 0.00012710590002417007,
|
| 631 |
+
"loss": 2.1443,
|
| 632 |
+
"step": 208
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.27,
|
| 636 |
+
"learning_rate": 0.00012346331352698205,
|
| 637 |
+
"loss": 2.1308,
|
| 638 |
+
"step": 210
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.28,
|
| 642 |
+
"learning_rate": 0.00011985023337937184,
|
| 643 |
+
"loss": 2.1563,
|
| 644 |
+
"step": 212
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.3,
|
| 648 |
+
"learning_rate": 0.00011626805249251445,
|
| 649 |
+
"loss": 2.1129,
|
| 650 |
+
"step": 214
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.31,
|
| 654 |
+
"learning_rate": 0.00011271815186533155,
|
| 655 |
+
"loss": 2.1279,
|
| 656 |
+
"step": 216
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 1.32,
|
| 660 |
+
"learning_rate": 0.00010920190005209065,
|
| 661 |
+
"loss": 2.0998,
|
| 662 |
+
"step": 218
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.33,
|
| 666 |
+
"learning_rate": 0.00010572065263480046,
|
| 667 |
+
"loss": 2.1541,
|
| 668 |
+
"step": 220
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.34,
|
| 672 |
+
"learning_rate": 0.00010227575170060909,
|
| 673 |
+
"loss": 2.162,
|
| 674 |
+
"step": 222
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.36,
|
| 678 |
+
"learning_rate": 9.886852532440312e-05,
|
| 679 |
+
"loss": 2.1697,
|
| 680 |
+
"step": 224
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.37,
|
| 684 |
+
"learning_rate": 9.550028705681025e-05,
|
| 685 |
+
"loss": 2.1428,
|
| 686 |
+
"step": 226
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.38,
|
| 690 |
+
"learning_rate": 9.217233541779995e-05,
|
| 691 |
+
"loss": 2.0846,
|
| 692 |
+
"step": 228
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.39,
|
| 696 |
+
"learning_rate": 8.888595339607961e-05,
|
| 697 |
+
"loss": 2.136,
|
| 698 |
+
"step": 230
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.4,
|
| 702 |
+
"learning_rate": 8.564240795447758e-05,
|
| 703 |
+
"loss": 2.2081,
|
| 704 |
+
"step": 232
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.42,
|
| 708 |
+
"learning_rate": 8.24429495415054e-05,
|
| 709 |
+
"loss": 2.097,
|
| 710 |
+
"step": 234
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.43,
|
| 714 |
+
"learning_rate": 7.928881160928572e-05,
|
| 715 |
+
"loss": 2.1502,
|
| 716 |
+
"step": 236
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.44,
|
| 720 |
+
"learning_rate": 7.618121013803319e-05,
|
| 721 |
+
"loss": 2.1683,
|
| 722 |
+
"step": 238
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.45,
|
| 726 |
+
"learning_rate": 7.312134316727093e-05,
|
| 727 |
+
"loss": 2.1311,
|
| 728 |
+
"step": 240
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.47,
|
| 732 |
+
"learning_rate": 7.011039033396329e-05,
|
| 733 |
+
"loss": 2.15,
|
| 734 |
+
"step": 242
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.48,
|
| 738 |
+
"learning_rate": 6.714951241774372e-05,
|
| 739 |
+
"loss": 2.1618,
|
| 740 |
+
"step": 244
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.49,
|
| 744 |
+
"learning_rate": 6.423985089341164e-05,
|
| 745 |
+
"loss": 2.1256,
|
| 746 |
+
"step": 246
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.5,
|
| 750 |
+
"learning_rate": 6.138252749087286e-05,
|
| 751 |
+
"loss": 2.194,
|
| 752 |
+
"step": 248
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.51,
|
| 756 |
+
"learning_rate": 5.857864376269051e-05,
|
| 757 |
+
"loss": 2.1898,
|
| 758 |
+
"step": 250
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.53,
|
| 762 |
+
"learning_rate": 5.5829280659416237e-05,
|
| 763 |
+
"loss": 2.1065,
|
| 764 |
+
"step": 252
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.54,
|
| 768 |
+
"learning_rate": 5.313549811286293e-05,
|
| 769 |
+
"loss": 2.0985,
|
| 770 |
+
"step": 254
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.55,
|
| 774 |
+
"learning_rate": 5.0498334627480615e-05,
|
| 775 |
+
"loss": 2.1658,
|
| 776 |
+
"step": 256
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.56,
|
| 780 |
+
"learning_rate": 4.7918806879993814e-05,
|
| 781 |
+
"loss": 2.1722,
|
| 782 |
+
"step": 258
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.57,
|
| 786 |
+
"learning_rate": 4.53979093274526e-05,
|
| 787 |
+
"loss": 2.083,
|
| 788 |
+
"step": 260
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.59,
|
| 792 |
+
"learning_rate": 4.293661382385106e-05,
|
| 793 |
+
"loss": 2.1665,
|
| 794 |
+
"step": 262
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.6,
|
| 798 |
+
"learning_rate": 4.05358692454586e-05,
|
| 799 |
+
"loss": 2.133,
|
| 800 |
+
"step": 264
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.61,
|
| 804 |
+
"learning_rate": 3.819660112501053e-05,
|
| 805 |
+
"loss": 2.1471,
|
| 806 |
+
"step": 266
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 1.62,
|
| 810 |
+
"learning_rate": 3.591971129489728e-05,
|
| 811 |
+
"loss": 2.1791,
|
| 812 |
+
"step": 268
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.63,
|
| 816 |
+
"learning_rate": 3.370607753949093e-05,
|
| 817 |
+
"loss": 2.072,
|
| 818 |
+
"step": 270
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.65,
|
| 822 |
+
"learning_rate": 3.1556553256742713e-05,
|
| 823 |
+
"loss": 2.1349,
|
| 824 |
+
"step": 272
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.66,
|
| 828 |
+
"learning_rate": 2.9471967129181565e-05,
|
| 829 |
+
"loss": 2.1705,
|
| 830 |
+
"step": 274
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.67,
|
| 834 |
+
"learning_rate": 2.7453122804441634e-05,
|
| 835 |
+
"loss": 2.1388,
|
| 836 |
+
"step": 276
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.68,
|
| 840 |
+
"learning_rate": 2.5500798585440567e-05,
|
| 841 |
+
"loss": 2.1586,
|
| 842 |
+
"step": 278
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.69,
|
| 846 |
+
"learning_rate": 2.3615747130329013e-05,
|
| 847 |
+
"loss": 2.1193,
|
| 848 |
+
"step": 280
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 1.71,
|
| 852 |
+
"learning_rate": 2.1798695162326442e-05,
|
| 853 |
+
"loss": 2.0693,
|
| 854 |
+
"step": 282
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.72,
|
| 858 |
+
"learning_rate": 2.0050343189555743e-05,
|
| 859 |
+
"loss": 2.1118,
|
| 860 |
+
"step": 284
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.73,
|
| 864 |
+
"learning_rate": 1.8371365234983727e-05,
|
| 865 |
+
"loss": 2.1395,
|
| 866 |
+
"step": 286
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.74,
|
| 870 |
+
"learning_rate": 1.676240857657283e-05,
|
| 871 |
+
"loss": 2.1948,
|
| 872 |
+
"step": 288
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.76,
|
| 876 |
+
"learning_rate": 1.5224093497742653e-05,
|
| 877 |
+
"loss": 2.1251,
|
| 878 |
+
"step": 290
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.77,
|
| 882 |
+
"learning_rate": 1.3757013048239286e-05,
|
| 883 |
+
"loss": 2.0808,
|
| 884 |
+
"step": 292
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.78,
|
| 888 |
+
"learning_rate": 1.236173281550319e-05,
|
| 889 |
+
"loss": 2.1342,
|
| 890 |
+
"step": 294
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.79,
|
| 894 |
+
"learning_rate": 1.1038790706624391e-05,
|
| 895 |
+
"loss": 2.0986,
|
| 896 |
+
"step": 296
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.8,
|
| 900 |
+
"learning_rate": 9.788696740969295e-06,
|
| 901 |
+
"loss": 2.123,
|
| 902 |
+
"step": 298
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.82,
|
| 906 |
+
"learning_rate": 8.611932853558236e-06,
|
| 907 |
+
"loss": 2.094,
|
| 908 |
+
"step": 300
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 1.83,
|
| 912 |
+
"learning_rate": 7.508952709270567e-06,
|
| 913 |
+
"loss": 2.1003,
|
| 914 |
+
"step": 302
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.84,
|
| 918 |
+
"learning_rate": 6.480181527948048e-06,
|
| 919 |
+
"loss": 2.188,
|
| 920 |
+
"step": 304
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.85,
|
| 924 |
+
"learning_rate": 5.5260159204646885e-06,
|
| 925 |
+
"loss": 2.1912,
|
| 926 |
+
"step": 306
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.86,
|
| 930 |
+
"learning_rate": 4.646823735825523e-06,
|
| 931 |
+
"loss": 2.1468,
|
| 932 |
+
"step": 308
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.88,
|
| 936 |
+
"learning_rate": 3.842943919353914e-06,
|
| 937 |
+
"loss": 2.1543,
|
| 938 |
+
"step": 310
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.89,
|
| 942 |
+
"learning_rate": 3.114686382021681e-06,
|
| 943 |
+
"loss": 2.0745,
|
| 944 |
+
"step": 312
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.9,
|
| 948 |
+
"learning_rate": 2.462331880972468e-06,
|
| 949 |
+
"loss": 2.1252,
|
| 950 |
+
"step": 314
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.91,
|
| 954 |
+
"learning_rate": 1.88613191128455e-06,
|
| 955 |
+
"loss": 2.1826,
|
| 956 |
+
"step": 316
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 1.92,
|
| 960 |
+
"learning_rate": 1.3863086090147415e-06,
|
| 961 |
+
"loss": 2.159,
|
| 962 |
+
"step": 318
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.94,
|
| 966 |
+
"learning_rate": 9.630546655606364e-07,
|
| 967 |
+
"loss": 2.1398,
|
| 968 |
+
"step": 320
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.95,
|
| 972 |
+
"learning_rate": 6.165332533744073e-07,
|
| 973 |
+
"loss": 2.1637,
|
| 974 |
+
"step": 322
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.96,
|
| 978 |
+
"learning_rate": 3.468779630568353e-07,
|
| 979 |
+
"loss": 2.0743,
|
| 980 |
+
"step": 324
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 1.97,
|
| 984 |
+
"learning_rate": 1.5419275185541982e-07,
|
| 985 |
+
"loss": 2.1162,
|
| 986 |
+
"step": 326
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.98,
|
| 990 |
+
"learning_rate": 3.855190358703631e-08,
|
| 991 |
+
"loss": 2.1847,
|
| 992 |
+
"step": 328
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.0,
|
| 996 |
+
"learning_rate": 0.0,
|
| 997 |
+
"loss": 2.092,
|
| 998 |
+
"step": 330
|
| 999 |
}
|
| 1000 |
],
|
| 1001 |
+
"max_steps": 330,
|
| 1002 |
"num_train_epochs": 2,
|
| 1003 |
+
"total_flos": 9.774541129058877e+17,
|
| 1004 |
"trial_name": null,
|
| 1005 |
"trial_params": null
|
| 1006 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ce3ce2d6417e5b5c48328b9d255c1dbf86521b5f18a92a9700d1a579456cc91
|
| 3 |
size 3567
|