Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +59 -3
trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -253,6 +253,62 @@
|
|
| 253 |
"learning_rate": 4.3869753251046806e-05,
|
| 254 |
"loss": 1.7233,
|
| 255 |
"step": 3400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 256 |
}
|
| 257 |
],
|
| 258 |
"logging_steps": 100,
|
|
@@ -272,7 +328,7 @@
|
|
| 272 |
"attributes": {}
|
| 273 |
}
|
| 274 |
},
|
| 275 |
-
"total_flos": 1.
|
| 276 |
"train_batch_size": 8,
|
| 277 |
"trial_name": null,
|
| 278 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2814105704845538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 253 |
"learning_rate": 4.3869753251046806e-05,
|
| 254 |
"loss": 1.7233,
|
| 255 |
"step": 3400
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.23450880873712818,
|
| 259 |
+
"grad_norm": 3.0303146839141846,
|
| 260 |
+
"learning_rate": 4.352040947054912e-05,
|
| 261 |
+
"loss": 1.6755,
|
| 262 |
+
"step": 3500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.24120906041533186,
|
| 266 |
+
"grad_norm": 3.0317392349243164,
|
| 267 |
+
"learning_rate": 4.316286017937538e-05,
|
| 268 |
+
"loss": 1.6352,
|
| 269 |
+
"step": 3600
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.2479093120935355,
|
| 273 |
+
"grad_norm": 3.037714958190918,
|
| 274 |
+
"learning_rate": 4.279726379057419e-05,
|
| 275 |
+
"loss": 1.5654,
|
| 276 |
+
"step": 3700
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.25460956377173916,
|
| 280 |
+
"grad_norm": 1.361885666847229,
|
| 281 |
+
"learning_rate": 4.2423782282479595e-05,
|
| 282 |
+
"loss": 17.0804,
|
| 283 |
+
"step": 3800
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.26130981544994286,
|
| 287 |
+
"grad_norm": 1.3709444999694824,
|
| 288 |
+
"learning_rate": 4.2042581126946126e-05,
|
| 289 |
+
"loss": 10.3143,
|
| 290 |
+
"step": 3900
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.2680100671281465,
|
| 294 |
+
"grad_norm": 1.3850795030593872,
|
| 295 |
+
"learning_rate": 4.165382921603614e-05,
|
| 296 |
+
"loss": 9.5243,
|
| 297 |
+
"step": 4000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.27471031880635016,
|
| 301 |
+
"grad_norm": 1.4029041528701782,
|
| 302 |
+
"learning_rate": 4.125769878719184e-05,
|
| 303 |
+
"loss": 8.6121,
|
| 304 |
+
"step": 4100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.2814105704845538,
|
| 308 |
+
"grad_norm": 1.4235178232192993,
|
| 309 |
+
"learning_rate": 4.0854365346925014e-05,
|
| 310 |
+
"loss": 7.5242,
|
| 311 |
+
"step": 4200
|
| 312 |
}
|
| 313 |
],
|
| 314 |
"logging_steps": 100,
|
|
|
|
| 328 |
"attributes": {}
|
| 329 |
}
|
| 330 |
},
|
| 331 |
+
"total_flos": 1.8085779157476917e+19,
|
| 332 |
"train_batch_size": 8,
|
| 333 |
"trial_name": null,
|
| 334 |
"trial_params": null
|