Training in progress, step 5900, 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 sha256:6b206acb948043678d17a19909d7377b383fdcebb0b64208823ac5c7990bcfcf
|
| 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:c2997a252164dcdc6de0ba21fcc4eccb9d348fd2dfe8a2ca6a3480abc7a619d7
|
| 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 sha256:8c1dab610c4f94e117748fe05ae8e1aa9c47b9de7c75ea80edaf3326573ea980
|
| 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": 45.
|
| 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,
|
|
@@ -10610,6 +10610,24 @@
|
|
| 10610 |
"mean_token_accuracy": 0.6630917578935623,
|
| 10611 |
"num_tokens": 21482239.0,
|
| 10612 |
"step": 5890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10613 |
}
|
| 10614 |
],
|
| 10615 |
"logging_steps": 5,
|
|
@@ -10629,7 +10647,7 @@
|
|
| 10629 |
"attributes": {}
|
| 10630 |
}
|
| 10631 |
},
|
| 10632 |
-
"total_flos": 1.
|
| 10633 |
"train_batch_size": 4,
|
| 10634 |
"trial_name": null,
|
| 10635 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10610 |
"mean_token_accuracy": 0.6630917578935623,
|
| 10611 |
"num_tokens": 21482239.0,
|
| 10612 |
"step": 5890
|
| 10613 |
+
},
|
| 10614 |
+
{
|
| 10615 |
+
"epoch": 45.34615384615385,
|
| 10616 |
+
"grad_norm": 0.0,
|
| 10617 |
+
"learning_rate": 2.053e-05,
|
| 10618 |
+
"loss": 1.7819,
|
| 10619 |
+
"mean_token_accuracy": 0.6405300617218017,
|
| 10620 |
+
"num_tokens": 21499829.0,
|
| 10621 |
+
"step": 5895
|
| 10622 |
+
},
|
| 10623 |
+
{
|
| 10624 |
+
"epoch": 45.38461538461539,
|
| 10625 |
+
"grad_norm": 0.0,
|
| 10626 |
+
"learning_rate": 2.0505e-05,
|
| 10627 |
+
"loss": 1.7291,
|
| 10628 |
+
"mean_token_accuracy": 0.6537360846996307,
|
| 10629 |
+
"num_tokens": 21518451.0,
|
| 10630 |
+
"step": 5900
|
| 10631 |
}
|
| 10632 |
],
|
| 10633 |
"logging_steps": 5,
|
|
|
|
| 10647 |
"attributes": {}
|
| 10648 |
}
|
| 10649 |
},
|
| 10650 |
+
"total_flos": 1.0904297593680691e+18,
|
| 10651 |
"train_batch_size": 4,
|
| 10652 |
"trial_name": null,
|
| 10653 |
"trial_params": null
|