Training in progress, step 5940, 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:ea27519919482b063c1ba6b6bdb7b8a86083a5b69e80e327e7341c37ae3ce2fa
|
| 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:bafee745c4dffc7ba3dbda72a39d049ef47861f0ea3784f1fdc36127353109cb
|
| 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 sha256:6982db3971a16c8eaa18d62d5e2c755a171803167ac8ac5a2cce56bed90d84bd
|
| 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": 45.
|
| 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,
|
|
@@ -10682,6 +10682,24 @@
|
|
| 10682 |
"mean_token_accuracy": 0.6519896745681762,
|
| 10683 |
"num_tokens": 21626524.0,
|
| 10684 |
"step": 5930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10685 |
}
|
| 10686 |
],
|
| 10687 |
"logging_steps": 5,
|
|
@@ -10701,7 +10719,7 @@
|
|
| 10701 |
"attributes": {}
|
| 10702 |
}
|
| 10703 |
},
|
| 10704 |
-
"total_flos": 1.
|
| 10705 |
"train_batch_size": 4,
|
| 10706 |
"trial_name": null,
|
| 10707 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10682 |
"mean_token_accuracy": 0.6519896745681762,
|
| 10683 |
"num_tokens": 21626524.0,
|
| 10684 |
"step": 5930
|
| 10685 |
+
},
|
| 10686 |
+
{
|
| 10687 |
+
"epoch": 45.65384615384615,
|
| 10688 |
+
"grad_norm": 0.0,
|
| 10689 |
+
"learning_rate": 2.033e-05,
|
| 10690 |
+
"loss": 1.7864,
|
| 10691 |
+
"mean_token_accuracy": 0.6421408951282501,
|
| 10692 |
+
"num_tokens": 21644165.0,
|
| 10693 |
+
"step": 5935
|
| 10694 |
+
},
|
| 10695 |
+
{
|
| 10696 |
+
"epoch": 45.69230769230769,
|
| 10697 |
+
"grad_norm": 0.0,
|
| 10698 |
+
"learning_rate": 2.0305000000000003e-05,
|
| 10699 |
+
"loss": 1.8047,
|
| 10700 |
+
"mean_token_accuracy": 0.6421581089496613,
|
| 10701 |
+
"num_tokens": 21661822.0,
|
| 10702 |
+
"step": 5940
|
| 10703 |
}
|
| 10704 |
],
|
| 10705 |
"logging_steps": 5,
|
|
|
|
| 10719 |
"attributes": {}
|
| 10720 |
}
|
| 10721 |
},
|
| 10722 |
+
"total_flos": 1.0977012091492762e+18,
|
| 10723 |
"train_batch_size": 4,
|
| 10724 |
"trial_name": null,
|
| 10725 |
"trial_params": null
|