Training in progress, step 6370, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96eea81f7a30502030723be9bf152111d2bfd879faeff39bfa236aced175645c
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cda5d1beda0461cebe14db2f5cdb2eb8187ac84b8077ed482d4c5a5fa60d475
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ff063d31756ee3128b3a9e2ab553fd039a501adb6dd30959324a7ba009fdf3c
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 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,
|
|
@@ -11456,6 +11456,24 @@
|
|
| 11456 |
"mean_token_accuracy": 0.6469810694456101,
|
| 11457 |
"num_tokens": 23193876.0,
|
| 11458 |
"step": 6360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11459 |
}
|
| 11460 |
],
|
| 11461 |
"logging_steps": 5,
|
|
@@ -11475,7 +11493,7 @@
|
|
| 11475 |
"attributes": {}
|
| 11476 |
}
|
| 11477 |
},
|
| 11478 |
-
"total_flos": 1.
|
| 11479 |
"train_batch_size": 4,
|
| 11480 |
"trial_name": null,
|
| 11481 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11456 |
"mean_token_accuracy": 0.6469810694456101,
|
| 11457 |
"num_tokens": 23193876.0,
|
| 11458 |
"step": 6360
|
| 11459 |
+
},
|
| 11460 |
+
{
|
| 11461 |
+
"epoch": 48.96153846153846,
|
| 11462 |
+
"grad_norm": 0.0,
|
| 11463 |
+
"learning_rate": 1.818e-05,
|
| 11464 |
+
"loss": 1.6923,
|
| 11465 |
+
"mean_token_accuracy": 0.6596918433904648,
|
| 11466 |
+
"num_tokens": 23212532.0,
|
| 11467 |
+
"step": 6365
|
| 11468 |
+
},
|
| 11469 |
+
{
|
| 11470 |
+
"epoch": 49.0,
|
| 11471 |
+
"grad_norm": 0.0,
|
| 11472 |
+
"learning_rate": 1.8154999999999998e-05,
|
| 11473 |
+
"loss": 1.7207,
|
| 11474 |
+
"mean_token_accuracy": 0.6570287615060806,
|
| 11475 |
+
"num_tokens": 23231145.0,
|
| 11476 |
+
"step": 6370
|
| 11477 |
}
|
| 11478 |
],
|
| 11479 |
"logging_steps": 5,
|
|
|
|
| 11493 |
"attributes": {}
|
| 11494 |
}
|
| 11495 |
},
|
| 11496 |
+
"total_flos": 1.177609990077481e+18,
|
| 11497 |
"train_batch_size": 4,
|
| 11498 |
"trial_name": null,
|
| 11499 |
"trial_params": null
|