Training in progress, step 380, 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 sha256:6b61558297bf08dfcb3dcc9291bb1d2bc27f41e8b622d70e30bb02c2ec50573f
|
| 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 sha256:614b0d1017a5faa9d96ae9bf839132e7856c799f4e6af6682e52660e47cba542
|
| 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:ba8a137da868466e33cdbd18e4fde3e7afd4bacc15c9670e55fb87058c4f3ec1
|
| 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": 2.
|
| 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,
|
|
@@ -674,6 +674,24 @@
|
|
| 674 |
"mean_token_accuracy": 0.6447630435228348,
|
| 675 |
"num_tokens": 1351095.0,
|
| 676 |
"step": 370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 677 |
}
|
| 678 |
],
|
| 679 |
"logging_steps": 5,
|
|
@@ -693,7 +711,7 @@
|
|
| 693 |
"attributes": {}
|
| 694 |
}
|
| 695 |
},
|
| 696 |
-
"total_flos":
|
| 697 |
"train_batch_size": 4,
|
| 698 |
"trial_name": null,
|
| 699 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.9230769230769234,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 674 |
"mean_token_accuracy": 0.6447630435228348,
|
| 675 |
"num_tokens": 1351095.0,
|
| 676 |
"step": 370
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.8846153846153846,
|
| 680 |
+
"grad_norm": 0.0,
|
| 681 |
+
"learning_rate": 4.813e-05,
|
| 682 |
+
"loss": 1.7453,
|
| 683 |
+
"mean_token_accuracy": 0.6486737489700317,
|
| 684 |
+
"num_tokens": 1369302.0,
|
| 685 |
+
"step": 375
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.9230769230769234,
|
| 689 |
+
"grad_norm": 0.0,
|
| 690 |
+
"learning_rate": 4.8105e-05,
|
| 691 |
+
"loss": 1.7446,
|
| 692 |
+
"mean_token_accuracy": 0.6489187270402909,
|
| 693 |
+
"num_tokens": 1387456.0,
|
| 694 |
+
"step": 380
|
| 695 |
}
|
| 696 |
],
|
| 697 |
"logging_steps": 5,
|
|
|
|
| 711 |
"attributes": {}
|
| 712 |
}
|
| 713 |
},
|
| 714 |
+
"total_flos": 7.018562234990592e+16,
|
| 715 |
"train_batch_size": 4,
|
| 716 |
"trial_name": null,
|
| 717 |
"trial_params": null
|