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 sha256:64d1e5dc6310fddcc8efa379b1218fa5b0cdbaec095f87d04bde9979f447c76c
|
| 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,
|
|
@@ -371,6 +371,62 @@
|
|
| 371 |
"learning_rate": 0.0001947380462136811,
|
| 372 |
"loss": 0.0701,
|
| 373 |
"step": 2600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 374 |
}
|
| 375 |
],
|
| 376 |
"logging_steps": 50,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.3679890560875512,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 371 |
"learning_rate": 0.0001947380462136811,
|
| 372 |
"loss": 0.0701,
|
| 373 |
"step": 2600
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.2083903328773369,
|
| 377 |
+
"grad_norm": 0.5234375,
|
| 378 |
+
"learning_rate": 0.0001946236559139785,
|
| 379 |
+
"loss": 0.0753,
|
| 380 |
+
"step": 2650
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.231190150478796,
|
| 384 |
+
"grad_norm": 0.96484375,
|
| 385 |
+
"learning_rate": 0.00019450926561427593,
|
| 386 |
+
"loss": 0.0708,
|
| 387 |
+
"step": 2700
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.2539899680802553,
|
| 391 |
+
"grad_norm": 0.625,
|
| 392 |
+
"learning_rate": 0.00019439487531457334,
|
| 393 |
+
"loss": 0.0955,
|
| 394 |
+
"step": 2750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.2767897856817145,
|
| 398 |
+
"grad_norm": 1.171875,
|
| 399 |
+
"learning_rate": 0.00019428048501487076,
|
| 400 |
+
"loss": 0.0866,
|
| 401 |
+
"step": 2800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.2995896032831737,
|
| 405 |
+
"grad_norm": 0.45703125,
|
| 406 |
+
"learning_rate": 0.00019416609471516815,
|
| 407 |
+
"loss": 0.0736,
|
| 408 |
+
"step": 2850
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.322389420884633,
|
| 412 |
+
"grad_norm": 0.76171875,
|
| 413 |
+
"learning_rate": 0.0001940517044154656,
|
| 414 |
+
"loss": 0.0751,
|
| 415 |
+
"step": 2900
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.3451892384860922,
|
| 419 |
+
"grad_norm": 1.203125,
|
| 420 |
+
"learning_rate": 0.00019393731411576298,
|
| 421 |
+
"loss": 0.0648,
|
| 422 |
+
"step": 2950
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.3679890560875512,
|
| 426 |
+
"grad_norm": 0.77734375,
|
| 427 |
+
"learning_rate": 0.0001938229238160604,
|
| 428 |
+
"loss": 0.0824,
|
| 429 |
+
"step": 3000
|
| 430 |
}
|
| 431 |
],
|
| 432 |
"logging_steps": 50,
|