Training in progress, step 5920, 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 sha256:3fcc004c0900540b369e5f2f163c20acbde61fedc8dd3de3d01332f54dd1b4fe
|
| 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:afd61b57a14d5df13594e3e1c6dab097d85dc21b9d78afc44ae252732fb345ba
|
| 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:cd22ad498b67865de90ccc9e79805e65fe1de20f9cfe97362d12dce66245c640
|
| 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,
|
|
@@ -10646,6 +10646,24 @@
|
|
| 10646 |
"mean_token_accuracy": 0.658150565624237,
|
| 10647 |
"num_tokens": 21555889.0,
|
| 10648 |
"step": 5910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10649 |
}
|
| 10650 |
],
|
| 10651 |
"logging_steps": 5,
|
|
@@ -10665,7 +10683,7 @@
|
|
| 10665 |
"attributes": {}
|
| 10666 |
}
|
| 10667 |
},
|
| 10668 |
-
"total_flos": 1.
|
| 10669 |
"train_batch_size": 4,
|
| 10670 |
"trial_name": null,
|
| 10671 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5920,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10646 |
"mean_token_accuracy": 0.658150565624237,
|
| 10647 |
"num_tokens": 21555889.0,
|
| 10648 |
"step": 5910
|
| 10649 |
+
},
|
| 10650 |
+
{
|
| 10651 |
+
"epoch": 45.5,
|
| 10652 |
+
"grad_norm": 0.0,
|
| 10653 |
+
"learning_rate": 2.0430000000000003e-05,
|
| 10654 |
+
"loss": 1.7755,
|
| 10655 |
+
"mean_token_accuracy": 0.6407826870679856,
|
| 10656 |
+
"num_tokens": 21574267.0,
|
| 10657 |
+
"step": 5915
|
| 10658 |
+
},
|
| 10659 |
+
{
|
| 10660 |
+
"epoch": 45.53846153846154,
|
| 10661 |
+
"grad_norm": 0.0,
|
| 10662 |
+
"learning_rate": 2.0405000000000002e-05,
|
| 10663 |
+
"loss": 1.7662,
|
| 10664 |
+
"mean_token_accuracy": 0.6452647089958191,
|
| 10665 |
+
"num_tokens": 21591748.0,
|
| 10666 |
+
"step": 5920
|
| 10667 |
}
|
| 10668 |
],
|
| 10669 |
"logging_steps": 5,
|
|
|
|
| 10683 |
"attributes": {}
|
| 10684 |
}
|
| 10685 |
},
|
| 10686 |
+
"total_flos": 1.0941799640231117e+18,
|
| 10687 |
"train_batch_size": 4,
|
| 10688 |
"trial_name": null,
|
| 10689 |
"trial_params": null
|