Training in progress, step 3120, 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 sha256:1f8de4882b4a98d90ee591fc92dcc1d6f95c13ebe666481e16d3d6706d15a26b
|
| 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 sha256:0afe1e2e0673eb1b65e7a5972f306baea70395983dd66764e4c239a2328e0699
|
| 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 sha256:3d1cfbdd4f8dbf85f04a710281d992ecb6f3785816958c7d98872e0bc59886d6
|
| 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,
|
|
@@ -5606,6 +5606,24 @@
|
|
| 5606 |
"mean_token_accuracy": 0.6531584694981575,
|
| 5607 |
"num_tokens": 11343111.0,
|
| 5608 |
"step": 3110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5609 |
}
|
| 5610 |
],
|
| 5611 |
"logging_steps": 5,
|
|
@@ -5625,7 +5643,7 @@
|
|
| 5625 |
"attributes": {}
|
| 5626 |
}
|
| 5627 |
},
|
| 5628 |
-
"total_flos": 5.
|
| 5629 |
"train_batch_size": 4,
|
| 5630 |
"trial_name": null,
|
| 5631 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5606 |
"mean_token_accuracy": 0.6531584694981575,
|
| 5607 |
"num_tokens": 11343111.0,
|
| 5608 |
"step": 3110
|
| 5609 |
+
},
|
| 5610 |
+
{
|
| 5611 |
+
"epoch": 23.96153846153846,
|
| 5612 |
+
"grad_norm": 0.0,
|
| 5613 |
+
"learning_rate": 3.443e-05,
|
| 5614 |
+
"loss": 1.7569,
|
| 5615 |
+
"mean_token_accuracy": 0.6495847851037979,
|
| 5616 |
+
"num_tokens": 11361415.0,
|
| 5617 |
+
"step": 3115
|
| 5618 |
+
},
|
| 5619 |
+
{
|
| 5620 |
+
"epoch": 24.0,
|
| 5621 |
+
"grad_norm": 0.0,
|
| 5622 |
+
"learning_rate": 3.440500000000001e-05,
|
| 5623 |
+
"loss": 1.8106,
|
| 5624 |
+
"mean_token_accuracy": 0.6377548843622207,
|
| 5625 |
+
"num_tokens": 11378520.0,
|
| 5626 |
+
"step": 3120
|
| 5627 |
}
|
| 5628 |
],
|
| 5629 |
"logging_steps": 5,
|
|
|
|
| 5643 |
"attributes": {}
|
| 5644 |
}
|
| 5645 |
},
|
| 5646 |
+
"total_flos": 5.765755076370432e+17,
|
| 5647 |
"train_batch_size": 4,
|
| 5648 |
"trial_name": null,
|
| 5649 |
"trial_params": null
|