Commit
·
743c776
1
Parent(s):
d9a1606
Training in progress, step 75, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11e42786d49cfe41cfcaa54d5091ee6e85eeaff37d1a87d017da8498e1f1156f
|
| 3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 42545748
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1693edb689091d1d86be591036d1ecbf67b627bcf824db2357c4dbe37a987704
|
| 3 |
size 42545748
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a2343c093429d43a756778ff280bf9733e4758b7f37beec7554cba6baaf362e
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -427,13 +427,43 @@
|
|
| 427 |
"learning_rate": 1.388888888888889e-05,
|
| 428 |
"loss": 1.7016,
|
| 429 |
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 430 |
}
|
| 431 |
],
|
| 432 |
"logging_steps": 1,
|
| 433 |
"max_steps": 75,
|
| 434 |
"num_train_epochs": 1,
|
| 435 |
"save_steps": 5,
|
| 436 |
-
"total_flos":
|
| 437 |
"trial_name": null,
|
| 438 |
"trial_params": null
|
| 439 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 75,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 427 |
"learning_rate": 1.388888888888889e-05,
|
| 428 |
"loss": 1.7016,
|
| 429 |
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.03,
|
| 433 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 434 |
+
"loss": 2.2515,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.03,
|
| 439 |
+
"learning_rate": 8.333333333333334e-06,
|
| 440 |
+
"loss": 2.047,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.03,
|
| 445 |
+
"learning_rate": 5.555555555555556e-06,
|
| 446 |
+
"loss": 1.3849,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.03,
|
| 451 |
+
"learning_rate": 2.777777777777778e-06,
|
| 452 |
+
"loss": 1.4436,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.03,
|
| 457 |
+
"learning_rate": 0.0,
|
| 458 |
+
"loss": 1.6971,
|
| 459 |
+
"step": 75
|
| 460 |
}
|
| 461 |
],
|
| 462 |
"logging_steps": 1,
|
| 463 |
"max_steps": 75,
|
| 464 |
"num_train_epochs": 1,
|
| 465 |
"save_steps": 5,
|
| 466 |
+
"total_flos": 4668793953730560.0,
|
| 467 |
"trial_name": null,
|
| 468 |
"trial_params": null
|
| 469 |
}
|