Training in progress, step 3700, 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 sha256:205b379ecbc87b86206780726193f8174dd6cbcff5ca4b7c6a2e02381731d45a
|
| 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 sha256:0e4b42d7d30c5bf2e6be46ba7d06e02339ed83ce7ccffec23756f77f375f28b5
|
| 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 sha256:5b6c795dc7cb2fca36c9f7621e468a883f6d4272679915c6d6cff703ce29f3e6
|
| 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,
|
|
@@ -6650,6 +6650,24 @@
|
|
| 6650 |
"mean_token_accuracy": 0.6578160703182221,
|
| 6651 |
"num_tokens": 13457841.0,
|
| 6652 |
"step": 3690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6653 |
}
|
| 6654 |
],
|
| 6655 |
"logging_steps": 5,
|
|
@@ -6669,7 +6687,7 @@
|
|
| 6669 |
"attributes": {}
|
| 6670 |
}
|
| 6671 |
},
|
| 6672 |
-
"total_flos": 6.
|
| 6673 |
"train_batch_size": 4,
|
| 6674 |
"trial_name": null,
|
| 6675 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6650 |
"mean_token_accuracy": 0.6578160703182221,
|
| 6651 |
"num_tokens": 13457841.0,
|
| 6652 |
"step": 3690
|
| 6653 |
+
},
|
| 6654 |
+
{
|
| 6655 |
+
"epoch": 28.423076923076923,
|
| 6656 |
+
"grad_norm": 0.0,
|
| 6657 |
+
"learning_rate": 3.1530000000000005e-05,
|
| 6658 |
+
"loss": 1.7291,
|
| 6659 |
+
"mean_token_accuracy": 0.6534811556339264,
|
| 6660 |
+
"num_tokens": 13476489.0,
|
| 6661 |
+
"step": 3695
|
| 6662 |
+
},
|
| 6663 |
+
{
|
| 6664 |
+
"epoch": 28.46153846153846,
|
| 6665 |
+
"grad_norm": 0.0,
|
| 6666 |
+
"learning_rate": 3.1505000000000004e-05,
|
| 6667 |
+
"loss": 1.7142,
|
| 6668 |
+
"mean_token_accuracy": 0.6544462114572525,
|
| 6669 |
+
"num_tokens": 13494620.0,
|
| 6670 |
+
"step": 3700
|
| 6671 |
}
|
| 6672 |
],
|
| 6673 |
"logging_steps": 5,
|
|
|
|
| 6687 |
"attributes": {}
|
| 6688 |
}
|
| 6689 |
},
|
| 6690 |
+
"total_flos": 6.838963967095603e+17,
|
| 6691 |
"train_batch_size": 4,
|
| 6692 |
"trial_name": null,
|
| 6693 |
"trial_params": null
|