Training in progress, step 4150, 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 sha256:0b417981964a5ed9282da4fc240fc387fcd452369c4264d8e9dc625de8456742
|
| 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 sha256:3a005df8505f6a73b2f5285b3cdac3b9def9f32ec8b89d97338ad7f7a6ccc064
|
| 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 sha256:699799b28835ae08fb02ec79e900d7cf4e38d921342b6a5b487be3b2a5565195
|
| 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": 31.
|
| 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,
|
|
@@ -7460,6 +7460,24 @@
|
|
| 7460 |
"mean_token_accuracy": 0.6659055262804031,
|
| 7461 |
"num_tokens": 15098047.0,
|
| 7462 |
"step": 4140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7463 |
}
|
| 7464 |
],
|
| 7465 |
"logging_steps": 5,
|
|
@@ -7479,7 +7497,7 @@
|
|
| 7479 |
"attributes": {}
|
| 7480 |
}
|
| 7481 |
},
|
| 7482 |
-
"total_flos": 7.
|
| 7483 |
"train_batch_size": 4,
|
| 7484 |
"trial_name": null,
|
| 7485 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 31.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7460 |
"mean_token_accuracy": 0.6659055262804031,
|
| 7461 |
"num_tokens": 15098047.0,
|
| 7462 |
"step": 4140
|
| 7463 |
+
},
|
| 7464 |
+
{
|
| 7465 |
+
"epoch": 31.884615384615383,
|
| 7466 |
+
"grad_norm": 0.0,
|
| 7467 |
+
"learning_rate": 2.928e-05,
|
| 7468 |
+
"loss": 1.7187,
|
| 7469 |
+
"mean_token_accuracy": 0.6543934553861618,
|
| 7470 |
+
"num_tokens": 15116367.0,
|
| 7471 |
+
"step": 4145
|
| 7472 |
+
},
|
| 7473 |
+
{
|
| 7474 |
+
"epoch": 31.923076923076923,
|
| 7475 |
+
"grad_norm": 0.0,
|
| 7476 |
+
"learning_rate": 2.9255e-05,
|
| 7477 |
+
"loss": 1.7361,
|
| 7478 |
+
"mean_token_accuracy": 0.6480780899524688,
|
| 7479 |
+
"num_tokens": 15135132.0,
|
| 7480 |
+
"step": 4150
|
| 7481 |
}
|
| 7482 |
],
|
| 7483 |
"logging_steps": 5,
|
|
|
|
| 7497 |
"attributes": {}
|
| 7498 |
}
|
| 7499 |
},
|
| 7500 |
+
"total_flos": 7.670001316184064e+17,
|
| 7501 |
"train_batch_size": 4,
|
| 7502 |
"trial_name": null,
|
| 7503 |
"trial_params": null
|