Training in progress, step 390, 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 sha256:9e54df6ca55e0f5a3d5ede1aba8632380d26a118cbb163f07d47f9b747a1cf4b
|
| 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 sha256:874425eebca4f2867316cf20fb1678840af5b8ff0172d9f1609af47557259261
|
| 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 sha256:5852a8d92d63b62ff13c988e5d2a2245fdda3dd42b997c06e812b362446e1736
|
| 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":
|
| 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,
|
|
@@ -692,6 +692,24 @@
|
|
| 692 |
"mean_token_accuracy": 0.6489187270402909,
|
| 693 |
"num_tokens": 1387456.0,
|
| 694 |
"step": 380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 695 |
}
|
| 696 |
],
|
| 697 |
"logging_steps": 5,
|
|
@@ -711,7 +729,7 @@
|
|
| 711 |
"attributes": {}
|
| 712 |
}
|
| 713 |
},
|
| 714 |
-
"total_flos": 7.
|
| 715 |
"train_batch_size": 4,
|
| 716 |
"trial_name": null,
|
| 717 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 692 |
"mean_token_accuracy": 0.6489187270402909,
|
| 693 |
"num_tokens": 1387456.0,
|
| 694 |
"step": 380
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.9615384615384617,
|
| 698 |
+
"grad_norm": 0.0,
|
| 699 |
+
"learning_rate": 4.808e-05,
|
| 700 |
+
"loss": 1.7578,
|
| 701 |
+
"mean_token_accuracy": 0.6475874185562134,
|
| 702 |
+
"num_tokens": 1404820.0,
|
| 703 |
+
"step": 385
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 3.0,
|
| 707 |
+
"grad_norm": 0.0,
|
| 708 |
+
"learning_rate": 4.8055e-05,
|
| 709 |
+
"loss": 1.8244,
|
| 710 |
+
"mean_token_accuracy": 0.636838635802269,
|
| 711 |
+
"num_tokens": 1422315.0,
|
| 712 |
+
"step": 390
|
| 713 |
}
|
| 714 |
],
|
| 715 |
"logging_steps": 5,
|
|
|
|
| 729 |
"attributes": {}
|
| 730 |
}
|
| 731 |
},
|
| 732 |
+
"total_flos": 7.19674419290112e+16,
|
| 733 |
"train_batch_size": 4,
|
| 734 |
"trial_name": null,
|
| 735 |
"trial_params": null
|