Training in progress, step 5840, 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:c0784805d08f14aedab0777ef5448605b96e8ccbd9eb4d142ea2cc58967d1321
|
| 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:c43f08388b006b95c5ea64e30ca6b8993fef1b05de466030120be4d1d0a775cd
|
| 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:dbeb8b40d221a64b6bb1e9ecb07e8a68dd26ddc76f4ded738145987248cb6cdf
|
| 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": 44.
|
| 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,
|
|
@@ -10502,6 +10502,24 @@
|
|
| 10502 |
"mean_token_accuracy": 0.6482422709465027,
|
| 10503 |
"num_tokens": 21262701.0,
|
| 10504 |
"step": 5830
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10505 |
}
|
| 10506 |
],
|
| 10507 |
"logging_steps": 5,
|
|
@@ -10521,7 +10539,7 @@
|
|
| 10521 |
"attributes": {}
|
| 10522 |
}
|
| 10523 |
},
|
| 10524 |
-
"total_flos": 1.
|
| 10525 |
"train_batch_size": 4,
|
| 10526 |
"trial_name": null,
|
| 10527 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10502 |
"mean_token_accuracy": 0.6482422709465027,
|
| 10503 |
"num_tokens": 21262701.0,
|
| 10504 |
"step": 5830
|
| 10505 |
+
},
|
| 10506 |
+
{
|
| 10507 |
+
"epoch": 44.88461538461539,
|
| 10508 |
+
"grad_norm": 0.0,
|
| 10509 |
+
"learning_rate": 2.0830000000000002e-05,
|
| 10510 |
+
"loss": 1.79,
|
| 10511 |
+
"mean_token_accuracy": 0.6363201081752777,
|
| 10512 |
+
"num_tokens": 21280639.0,
|
| 10513 |
+
"step": 5835
|
| 10514 |
+
},
|
| 10515 |
+
{
|
| 10516 |
+
"epoch": 44.92307692307692,
|
| 10517 |
+
"grad_norm": 0.0,
|
| 10518 |
+
"learning_rate": 2.0805e-05,
|
| 10519 |
+
"loss": 1.7229,
|
| 10520 |
+
"mean_token_accuracy": 0.6573170632123947,
|
| 10521 |
+
"num_tokens": 21298845.0,
|
| 10522 |
+
"step": 5840
|
| 10523 |
}
|
| 10524 |
],
|
| 10525 |
"logging_steps": 5,
|
|
|
|
| 10539 |
"attributes": {}
|
| 10540 |
}
|
| 10541 |
},
|
| 10542 |
+
"total_flos": 1.0792113775696282e+18,
|
| 10543 |
"train_batch_size": 4,
|
| 10544 |
"trial_name": null,
|
| 10545 |
"trial_params": null
|