Training in progress, step 3680, 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 sha256:12d01854b7d063e2e53d14757df61c2fbd43032cb23ff1987130c2ad01e4cabe
|
| 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 sha256:71047d88db3d7de5e5b7036c2b9817117dc6425aea02413bc89cbc992d01930e
|
| 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 sha256:6acae512e6849722afa59dbad414a8478d9cfb91ac8506f65da3b4a6cc3bd68c
|
| 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,
|
|
@@ -6614,6 +6614,24 @@
|
|
| 6614 |
"mean_token_accuracy": 0.6530542701482773,
|
| 6615 |
"num_tokens": 13384925.0,
|
| 6616 |
"step": 3670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6617 |
}
|
| 6618 |
],
|
| 6619 |
"logging_steps": 5,
|
|
@@ -6633,7 +6651,7 @@
|
|
| 6633 |
"attributes": {}
|
| 6634 |
}
|
| 6635 |
},
|
| 6636 |
-
"total_flos": 6.
|
| 6637 |
"train_batch_size": 4,
|
| 6638 |
"trial_name": null,
|
| 6639 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6614 |
"mean_token_accuracy": 0.6530542701482773,
|
| 6615 |
"num_tokens": 13384925.0,
|
| 6616 |
"step": 3670
|
| 6617 |
+
},
|
| 6618 |
+
{
|
| 6619 |
+
"epoch": 28.26923076923077,
|
| 6620 |
+
"grad_norm": 0.0,
|
| 6621 |
+
"learning_rate": 3.163000000000001e-05,
|
| 6622 |
+
"loss": 1.77,
|
| 6623 |
+
"mean_token_accuracy": 0.6439873456954956,
|
| 6624 |
+
"num_tokens": 13402589.0,
|
| 6625 |
+
"step": 3675
|
| 6626 |
+
},
|
| 6627 |
+
{
|
| 6628 |
+
"epoch": 28.307692307692307,
|
| 6629 |
+
"grad_norm": 0.0,
|
| 6630 |
+
"learning_rate": 3.1605e-05,
|
| 6631 |
+
"loss": 1.7013,
|
| 6632 |
+
"mean_token_accuracy": 0.6571666300296783,
|
| 6633 |
+
"num_tokens": 13421123.0,
|
| 6634 |
+
"step": 3680
|
| 6635 |
}
|
| 6636 |
],
|
| 6637 |
"logging_steps": 5,
|
|
|
|
| 6651 |
"attributes": {}
|
| 6652 |
}
|
| 6653 |
},
|
| 6654 |
+
"total_flos": 6.801453981587866e+17,
|
| 6655 |
"train_batch_size": 4,
|
| 6656 |
"trial_name": null,
|
| 6657 |
"trial_params": null
|