Training in progress, step 2010, 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 sha256:09a820e6298406d2cc3ebad07410e6837b09e7b54e569e6c2559197dd8509abc
|
| 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:a3f65ea763147f4c223ce6c75f02c449b77aa5f36ec8c84cb76fc14cfa3abc7e
|
| 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:fcbd06a7a48b116d782dcd22071a8b6e93acb70a04c69f3a12939fecb81beaa5
|
| 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": 15.
|
| 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,
|
|
@@ -3608,6 +3608,24 @@
|
|
| 3608 |
"mean_token_accuracy": 0.6513147324323654,
|
| 3609 |
"num_tokens": 7291754.0,
|
| 3610 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3611 |
}
|
| 3612 |
],
|
| 3613 |
"logging_steps": 5,
|
|
@@ -3627,7 +3645,7 @@
|
|
| 3627 |
"attributes": {}
|
| 3628 |
}
|
| 3629 |
},
|
| 3630 |
-
"total_flos": 3.
|
| 3631 |
"train_batch_size": 4,
|
| 3632 |
"trial_name": null,
|
| 3633 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2010,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3608 |
"mean_token_accuracy": 0.6513147324323654,
|
| 3609 |
"num_tokens": 7291754.0,
|
| 3610 |
"step": 2000
|
| 3611 |
+
},
|
| 3612 |
+
{
|
| 3613 |
+
"epoch": 15.423076923076923,
|
| 3614 |
+
"grad_norm": 0.0,
|
| 3615 |
+
"learning_rate": 3.998e-05,
|
| 3616 |
+
"loss": 1.7946,
|
| 3617 |
+
"mean_token_accuracy": 0.6427055537700653,
|
| 3618 |
+
"num_tokens": 7309133.0,
|
| 3619 |
+
"step": 2005
|
| 3620 |
+
},
|
| 3621 |
+
{
|
| 3622 |
+
"epoch": 15.461538461538462,
|
| 3623 |
+
"grad_norm": 0.0,
|
| 3624 |
+
"learning_rate": 3.9955000000000006e-05,
|
| 3625 |
+
"loss": 1.7461,
|
| 3626 |
+
"mean_token_accuracy": 0.6472333878278732,
|
| 3627 |
+
"num_tokens": 7328009.0,
|
| 3628 |
+
"step": 2010
|
| 3629 |
}
|
| 3630 |
],
|
| 3631 |
"logging_steps": 5,
|
|
|
|
| 3645 |
"attributes": {}
|
| 3646 |
}
|
| 3647 |
},
|
| 3648 |
+
"total_flos": 3.711721353368371e+17,
|
| 3649 |
"train_batch_size": 4,
|
| 3650 |
"trial_name": null,
|
| 3651 |
"trial_params": null
|