Training in progress, step 7610, 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 sha256:6e5487c2df6d0b38f783d9a2cd64da0dbd60aa8d96b0d5669470a2a6df50b301
|
| 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 sha256:0110a1f84e70403de8b346795834fae299e64f7937a168e8c560b83055176dc4
|
| 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 sha256:235c6e77d268a83e7380adb2bebef246e9faffc305eb9d5d602d9f5c5d2e0221
|
| 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,
|
|
@@ -13688,6 +13688,24 @@
|
|
| 13688 |
"mean_token_accuracy": 0.6482616752386093,
|
| 13689 |
"num_tokens": 27713869.0,
|
| 13690 |
"step": 7600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13691 |
}
|
| 13692 |
],
|
| 13693 |
"logging_steps": 5,
|
|
@@ -13707,7 +13725,7 @@
|
|
| 13707 |
"attributes": {}
|
| 13708 |
}
|
| 13709 |
},
|
| 13710 |
-
"total_flos": 1.
|
| 13711 |
"train_batch_size": 4,
|
| 13712 |
"trial_name": null,
|
| 13713 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13688 |
"mean_token_accuracy": 0.6482616752386093,
|
| 13689 |
"num_tokens": 27713869.0,
|
| 13690 |
"step": 7600
|
| 13691 |
+
},
|
| 13692 |
+
{
|
| 13693 |
+
"epoch": 58.5,
|
| 13694 |
+
"grad_norm": 0.0,
|
| 13695 |
+
"learning_rate": 1.198e-05,
|
| 13696 |
+
"loss": 1.7355,
|
| 13697 |
+
"mean_token_accuracy": 0.6519585400819778,
|
| 13698 |
+
"num_tokens": 27731955.0,
|
| 13699 |
+
"step": 7605
|
| 13700 |
+
},
|
| 13701 |
+
{
|
| 13702 |
+
"epoch": 58.53846153846154,
|
| 13703 |
+
"grad_norm": 0.0,
|
| 13704 |
+
"learning_rate": 1.1955000000000002e-05,
|
| 13705 |
+
"loss": 1.7163,
|
| 13706 |
+
"mean_token_accuracy": 0.6518133997917175,
|
| 13707 |
+
"num_tokens": 27750713.0,
|
| 13708 |
+
"step": 7610
|
| 13709 |
}
|
| 13710 |
],
|
| 13711 |
"logging_steps": 5,
|
|
|
|
| 13725 |
"attributes": {}
|
| 13726 |
}
|
| 13727 |
},
|
| 13728 |
+
"total_flos": 1.406991553926267e+18,
|
| 13729 |
"train_batch_size": 4,
|
| 13730 |
"trial_name": null,
|
| 13731 |
"trial_params": null
|