Training in progress, step 3279
Browse files- adapter_model.safetensors +1 -1
- trainer_state.json +39 -4
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1027183888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c847bc17d277eb86fbe8ca0a4e5b38216918f9c73feb41200488b5e012afe7f
|
| 3 |
size 1027183888
|
trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 3000,
|
| 3 |
"best_metric": 3.9151711463928223,
|
| 4 |
"best_model_checkpoint": "/kaggle/working/checkpoints/checkpoint-3000",
|
| 5 |
-
"epoch":
|
| 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,
|
|
@@ -476,6 +476,41 @@
|
|
| 476 |
"eval_samples_per_second": 59.195,
|
| 477 |
"eval_steps_per_second": 7.462,
|
| 478 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 479 |
}
|
| 480 |
],
|
| 481 |
"logging_steps": 50,
|
|
@@ -490,12 +525,12 @@
|
|
| 490 |
"should_evaluate": false,
|
| 491 |
"should_log": false,
|
| 492 |
"should_save": true,
|
| 493 |
-
"should_training_stop":
|
| 494 |
},
|
| 495 |
"attributes": {}
|
| 496 |
}
|
| 497 |
},
|
| 498 |
-
"total_flos": 2.
|
| 499 |
"train_batch_size": 16,
|
| 500 |
"trial_name": null,
|
| 501 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 3000,
|
| 3 |
"best_metric": 3.9151711463928223,
|
| 4 |
"best_model_checkpoint": "/kaggle/working/checkpoints/checkpoint-3000",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3279,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 476 |
"eval_samples_per_second": 59.195,
|
| 477 |
"eval_steps_per_second": 7.462,
|
| 478 |
"step": 3000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.7910276951247424,
|
| 482 |
+
"grad_norm": 0.7813104391098022,
|
| 483 |
+
"learning_rate": 3.6163522012578618e-06,
|
| 484 |
+
"loss": 20.85503662109375,
|
| 485 |
+
"step": 3050
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.836804760814832,
|
| 489 |
+
"grad_norm": 0.7470929026603699,
|
| 490 |
+
"learning_rate": 2.830188679245283e-06,
|
| 491 |
+
"loss": 20.86689697265625,
|
| 492 |
+
"step": 3100
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.882581826504921,
|
| 496 |
+
"grad_norm": 0.7827481031417847,
|
| 497 |
+
"learning_rate": 2.0440251572327044e-06,
|
| 498 |
+
"loss": 20.801142578125,
|
| 499 |
+
"step": 3150
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.9283588921950106,
|
| 503 |
+
"grad_norm": 0.8394864201545715,
|
| 504 |
+
"learning_rate": 1.257861635220126e-06,
|
| 505 |
+
"loss": 20.861923828125,
|
| 506 |
+
"step": 3200
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.9741359578850997,
|
| 510 |
+
"grad_norm": 0.7399877905845642,
|
| 511 |
+
"learning_rate": 4.7169811320754717e-07,
|
| 512 |
+
"loss": 20.7888671875,
|
| 513 |
+
"step": 3250
|
| 514 |
}
|
| 515 |
],
|
| 516 |
"logging_steps": 50,
|
|
|
|
| 525 |
"should_evaluate": false,
|
| 526 |
"should_log": false,
|
| 527 |
"should_save": true,
|
| 528 |
+
"should_training_stop": true
|
| 529 |
},
|
| 530 |
"attributes": {}
|
| 531 |
}
|
| 532 |
},
|
| 533 |
+
"total_flos": 2.782532121447629e+16,
|
| 534 |
"train_batch_size": 16,
|
| 535 |
"trial_name": null,
|
| 536 |
"trial_params": null
|