Upload 12 files
Browse files- adapter_model.safetensors +1 -1
- trainer_state.json +58 -2
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3941712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e88d32f77b6c403109c628d79eac0d181ee3f464d3aec5d1b3cc08268982923
|
| 3 |
size 3941712
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -315,6 +315,62 @@
|
|
| 315 |
"learning_rate": 0.00019565316861130177,
|
| 316 |
"loss": 0.1047,
|
| 317 |
"step": 2200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 318 |
}
|
| 319 |
],
|
| 320 |
"logging_steps": 50,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.1855905152758779,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 315 |
"learning_rate": 0.00019565316861130177,
|
| 316 |
"loss": 0.1047,
|
| 317 |
"step": 2200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.0259917920656634,
|
| 321 |
+
"grad_norm": 1.078125,
|
| 322 |
+
"learning_rate": 0.00019553877831159918,
|
| 323 |
+
"loss": 0.1052,
|
| 324 |
+
"step": 2250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.0487916096671226,
|
| 328 |
+
"grad_norm": 0.5703125,
|
| 329 |
+
"learning_rate": 0.0001954243880118966,
|
| 330 |
+
"loss": 0.0921,
|
| 331 |
+
"step": 2300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0715914272685818,
|
| 335 |
+
"grad_norm": 0.82421875,
|
| 336 |
+
"learning_rate": 0.000195309997712194,
|
| 337 |
+
"loss": 0.0987,
|
| 338 |
+
"step": 2350
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.094391244870041,
|
| 342 |
+
"grad_norm": 0.91796875,
|
| 343 |
+
"learning_rate": 0.00019519560741249143,
|
| 344 |
+
"loss": 0.1039,
|
| 345 |
+
"step": 2400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.1171910624715002,
|
| 349 |
+
"grad_norm": 0.984375,
|
| 350 |
+
"learning_rate": 0.00019508121711278885,
|
| 351 |
+
"loss": 0.1031,
|
| 352 |
+
"step": 2450
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.1399908800729595,
|
| 356 |
+
"grad_norm": 0.51171875,
|
| 357 |
+
"learning_rate": 0.00019496682681308626,
|
| 358 |
+
"loss": 0.0728,
|
| 359 |
+
"step": 2500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.1627906976744187,
|
| 363 |
+
"grad_norm": 0.83203125,
|
| 364 |
+
"learning_rate": 0.00019485243651338368,
|
| 365 |
+
"loss": 0.0728,
|
| 366 |
+
"step": 2550
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.1855905152758779,
|
| 370 |
+
"grad_norm": 0.5234375,
|
| 371 |
+
"learning_rate": 0.0001947380462136811,
|
| 372 |
+
"loss": 0.0701,
|
| 373 |
+
"step": 2600
|
| 374 |
}
|
| 375 |
],
|
| 376 |
"logging_steps": 50,
|