Training in progress, step 370, 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:bdde1c1c3d841833174ec6a0b3a2c939404284cb3e50356e45bc1c429d515c9d
|
| 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 sha256:24bb2b535663990e33f654dce32797ed40027427b320637aea72fadcb1f2f3ac
|
| 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 sha256:51a4319d7a835989d84438cc208b16b7188ac0e28cdf07e656382117030ebfa6
|
| 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,
|
|
@@ -656,6 +656,24 @@
|
|
| 656 |
"mean_token_accuracy": 0.662646809220314,
|
| 657 |
"num_tokens": 1315690.0,
|
| 658 |
"step": 360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 659 |
}
|
| 660 |
],
|
| 661 |
"logging_steps": 5,
|
|
@@ -675,7 +693,7 @@
|
|
| 675 |
"attributes": {}
|
| 676 |
}
|
| 677 |
},
|
| 678 |
-
"total_flos": 6.
|
| 679 |
"train_batch_size": 4,
|
| 680 |
"trial_name": null,
|
| 681 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.8461538461538463,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 656 |
"mean_token_accuracy": 0.662646809220314,
|
| 657 |
"num_tokens": 1315690.0,
|
| 658 |
"step": 360
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.8076923076923075,
|
| 662 |
+
"grad_norm": 0.0,
|
| 663 |
+
"learning_rate": 4.818e-05,
|
| 664 |
+
"loss": 1.7963,
|
| 665 |
+
"mean_token_accuracy": 0.6397953987121582,
|
| 666 |
+
"num_tokens": 1333332.0,
|
| 667 |
+
"step": 365
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.8461538461538463,
|
| 671 |
+
"grad_norm": 0.0,
|
| 672 |
+
"learning_rate": 4.8155e-05,
|
| 673 |
+
"loss": 1.7771,
|
| 674 |
+
"mean_token_accuracy": 0.6447630435228348,
|
| 675 |
+
"num_tokens": 1351095.0,
|
| 676 |
+
"step": 370
|
| 677 |
}
|
| 678 |
],
|
| 679 |
"logging_steps": 5,
|
|
|
|
| 693 |
"attributes": {}
|
| 694 |
}
|
| 695 |
},
|
| 696 |
+
"total_flos": 6.830186655891456e+16,
|
| 697 |
"train_batch_size": 4,
|
| 698 |
"trial_name": null,
|
| 699 |
"trial_params": null
|