Training in progress, step 6440, 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 sha256:117534a903dc69c454ba50f4f5391ebd3d3360e6e1ca41a3f0128332c7661ebc
|
| 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:d1d7fabb1307ea7133db33ecc03c9d8af9d206faeef4e271c1389ce90d8ff284
|
| 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 sha256:9c7b8ac93799645fe5a6e38e02dcaf726a44228fbc4b2213a4b0bd4724fc43a6
|
| 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": 49.
|
| 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,
|
|
@@ -11582,6 +11582,24 @@
|
|
| 11582 |
"mean_token_accuracy": 0.6465479761362076,
|
| 11583 |
"num_tokens": 23449644.0,
|
| 11584 |
"step": 6430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11585 |
}
|
| 11586 |
],
|
| 11587 |
"logging_steps": 5,
|
|
@@ -11601,7 +11619,7 @@
|
|
| 11601 |
"attributes": {}
|
| 11602 |
}
|
| 11603 |
},
|
| 11604 |
-
"total_flos": 1.
|
| 11605 |
"train_batch_size": 4,
|
| 11606 |
"trial_name": null,
|
| 11607 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11582 |
"mean_token_accuracy": 0.6465479761362076,
|
| 11583 |
"num_tokens": 23449644.0,
|
| 11584 |
"step": 6430
|
| 11585 |
+
},
|
| 11586 |
+
{
|
| 11587 |
+
"epoch": 49.5,
|
| 11588 |
+
"grad_norm": 0.0,
|
| 11589 |
+
"learning_rate": 1.783e-05,
|
| 11590 |
+
"loss": 1.7867,
|
| 11591 |
+
"mean_token_accuracy": 0.6393932700157166,
|
| 11592 |
+
"num_tokens": 23466835.0,
|
| 11593 |
+
"step": 6435
|
| 11594 |
+
},
|
| 11595 |
+
{
|
| 11596 |
+
"epoch": 49.53846153846154,
|
| 11597 |
+
"grad_norm": 0.0,
|
| 11598 |
+
"learning_rate": 1.7805000000000003e-05,
|
| 11599 |
+
"loss": 1.6852,
|
| 11600 |
+
"mean_token_accuracy": 0.6625799834728241,
|
| 11601 |
+
"num_tokens": 23485932.0,
|
| 11602 |
+
"step": 6440
|
| 11603 |
}
|
| 11604 |
],
|
| 11605 |
"logging_steps": 5,
|
|
|
|
| 11619 |
"attributes": {}
|
| 11620 |
}
|
| 11621 |
},
|
| 11622 |
+
"total_flos": 1.190502856752169e+18,
|
| 11623 |
"train_batch_size": 4,
|
| 11624 |
"trial_name": null,
|
| 11625 |
"trial_params": null
|