Training in progress, step 7590, 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 sha256:117b9e46415870fd61383bd01ff6ea36f1be15e76a71f71f6698b38105570876
|
| 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 sha256:63ebb6aa3d776f55d44f456ac7a1d14e73459badd056ccc754ed58830b819440
|
| 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:c240262e3a4126f778a5443d72cca1a419ff47181742ad85d7cc7f19bc6af524
|
| 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": 58.
|
| 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,
|
|
@@ -13652,6 +13652,24 @@
|
|
| 13652 |
"mean_token_accuracy": 0.6520835846662522,
|
| 13653 |
"num_tokens": 27641906.0,
|
| 13654 |
"step": 7580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13655 |
}
|
| 13656 |
],
|
| 13657 |
"logging_steps": 5,
|
|
@@ -13671,7 +13689,7 @@
|
|
| 13671 |
"attributes": {}
|
| 13672 |
}
|
| 13673 |
},
|
| 13674 |
-
"total_flos": 1.
|
| 13675 |
"train_batch_size": 4,
|
| 13676 |
"trial_name": null,
|
| 13677 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7590,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13652 |
"mean_token_accuracy": 0.6520835846662522,
|
| 13653 |
"num_tokens": 27641906.0,
|
| 13654 |
"step": 7580
|
| 13655 |
+
},
|
| 13656 |
+
{
|
| 13657 |
+
"epoch": 58.34615384615385,
|
| 13658 |
+
"grad_norm": 0.0,
|
| 13659 |
+
"learning_rate": 1.2080000000000001e-05,
|
| 13660 |
+
"loss": 1.7482,
|
| 13661 |
+
"mean_token_accuracy": 0.6481060594320297,
|
| 13662 |
+
"num_tokens": 27660198.0,
|
| 13663 |
+
"step": 7585
|
| 13664 |
+
},
|
| 13665 |
+
{
|
| 13666 |
+
"epoch": 58.38461538461539,
|
| 13667 |
+
"grad_norm": 0.0,
|
| 13668 |
+
"learning_rate": 1.2055e-05,
|
| 13669 |
+
"loss": 1.8091,
|
| 13670 |
+
"mean_token_accuracy": 0.6401431083679199,
|
| 13671 |
+
"num_tokens": 27677904.0,
|
| 13672 |
+
"step": 7590
|
| 13673 |
}
|
| 13674 |
],
|
| 13675 |
"logging_steps": 5,
|
|
|
|
| 13689 |
"attributes": {}
|
| 13690 |
}
|
| 13691 |
},
|
| 13692 |
+
"total_flos": 1.4032626256768205e+18,
|
| 13693 |
"train_batch_size": 4,
|
| 13694 |
"trial_name": null,
|
| 13695 |
"trial_params": null
|