Training in progress, step 3650, 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 sha256:703dd5189e6fc4faaf8331377d173638880285c3457e96fa7e4e478b9bea0b33
|
| 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:f783e8a8d9a0d7e5a728001f4a8bfacd62a8536223b5766b672373100d8b532f
|
| 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 sha256:3087393c256ae30b7aaf5091f1489636435ece3c1bf81160f2e05802174a2e17
|
| 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": 28.
|
| 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,
|
|
@@ -6560,6 +6560,24 @@
|
|
| 6560 |
"mean_token_accuracy": 0.6585237294435501,
|
| 6561 |
"num_tokens": 13274940.0,
|
| 6562 |
"step": 3640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6563 |
}
|
| 6564 |
],
|
| 6565 |
"logging_steps": 5,
|
|
@@ -6579,7 +6597,7 @@
|
|
| 6579 |
"attributes": {}
|
| 6580 |
}
|
| 6581 |
},
|
| 6582 |
-
"total_flos": 6.
|
| 6583 |
"train_batch_size": 4,
|
| 6584 |
"trial_name": null,
|
| 6585 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6560 |
"mean_token_accuracy": 0.6585237294435501,
|
| 6561 |
"num_tokens": 13274940.0,
|
| 6562 |
"step": 3640
|
| 6563 |
+
},
|
| 6564 |
+
{
|
| 6565 |
+
"epoch": 28.03846153846154,
|
| 6566 |
+
"grad_norm": 0.0,
|
| 6567 |
+
"learning_rate": 3.1780000000000004e-05,
|
| 6568 |
+
"loss": 1.7343,
|
| 6569 |
+
"mean_token_accuracy": 0.6495951384305954,
|
| 6570 |
+
"num_tokens": 13293159.0,
|
| 6571 |
+
"step": 3645
|
| 6572 |
+
},
|
| 6573 |
+
{
|
| 6574 |
+
"epoch": 28.076923076923077,
|
| 6575 |
+
"grad_norm": 0.0,
|
| 6576 |
+
"learning_rate": 3.1755000000000003e-05,
|
| 6577 |
+
"loss": 1.7448,
|
| 6578 |
+
"mean_token_accuracy": 0.6506305515766144,
|
| 6579 |
+
"num_tokens": 13310902.0,
|
| 6580 |
+
"step": 3650
|
| 6581 |
}
|
| 6582 |
],
|
| 6583 |
"logging_steps": 5,
|
|
|
|
| 6597 |
"attributes": {}
|
| 6598 |
}
|
| 6599 |
},
|
| 6600 |
+
"total_flos": 6.744669795518054e+17,
|
| 6601 |
"train_batch_size": 4,
|
| 6602 |
"trial_name": null,
|
| 6603 |
"trial_params": null
|