Training in progress, step 350, 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 sha256:69c051e80982748283e62391f9d50dafb25b7d7512e849d2f86998e4c03a9ade
|
| 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 sha256:0258fb3a61f9c21fba9073408a4c29b225f464f32d26b71d646753faf70bfbb0
|
| 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 sha256:8128bfd0d10306e924e9b3b9044bc58cc5a5a6f17039fe1395a8e8ed4a46e07b
|
| 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,
|
|
@@ -620,6 +620,24 @@
|
|
| 620 |
"mean_token_accuracy": 0.6472829192876816,
|
| 621 |
"num_tokens": 1240309.0,
|
| 622 |
"step": 340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 623 |
}
|
| 624 |
],
|
| 625 |
"logging_steps": 5,
|
|
@@ -639,7 +657,7 @@
|
|
| 639 |
"attributes": {}
|
| 640 |
}
|
| 641 |
},
|
| 642 |
-
"total_flos": 6.
|
| 643 |
"train_batch_size": 4,
|
| 644 |
"trial_name": null,
|
| 645 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.6923076923076925,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 620 |
"mean_token_accuracy": 0.6472829192876816,
|
| 621 |
"num_tokens": 1240309.0,
|
| 622 |
"step": 340
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.6538461538461537,
|
| 626 |
+
"grad_norm": 0.0,
|
| 627 |
+
"learning_rate": 4.8280000000000005e-05,
|
| 628 |
+
"loss": 1.7343,
|
| 629 |
+
"mean_token_accuracy": 0.6456574499607086,
|
| 630 |
+
"num_tokens": 1258875.0,
|
| 631 |
+
"step": 345
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.6923076923076925,
|
| 635 |
+
"grad_norm": 0.0,
|
| 636 |
+
"learning_rate": 4.8255e-05,
|
| 637 |
+
"loss": 1.7172,
|
| 638 |
+
"mean_token_accuracy": 0.6524255007505417,
|
| 639 |
+
"num_tokens": 1277367.0,
|
| 640 |
+
"step": 350
|
| 641 |
}
|
| 642 |
],
|
| 643 |
"logging_steps": 5,
|
|
|
|
| 657 |
"attributes": {}
|
| 658 |
}
|
| 659 |
},
|
| 660 |
+
"total_flos": 6.468852952793088e+16,
|
| 661 |
"train_batch_size": 4,
|
| 662 |
"trial_name": null,
|
| 663 |
"trial_params": null
|