Training in progress, step 3170, 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 sha256:5e69b946fcc816a502922a82af0d5417931d95f66d0482c96e3f80a0ac99783f
|
| 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 sha256:494866439cf7766269d8bd6c99c007fdfaf032282bdc8a1775256ed2c07c12fa
|
| 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 sha256:9060818511b08c4add8d1a0dab06442924789f96a374279a2a821aa58eec16c5
|
| 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": 24.
|
| 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,
|
|
@@ -5696,6 +5696,24 @@
|
|
| 5696 |
"mean_token_accuracy": 0.6544101685285568,
|
| 5697 |
"num_tokens": 11524471.0,
|
| 5698 |
"step": 3160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5699 |
}
|
| 5700 |
],
|
| 5701 |
"logging_steps": 5,
|
|
@@ -5715,7 +5733,7 @@
|
|
| 5715 |
"attributes": {}
|
| 5716 |
}
|
| 5717 |
},
|
| 5718 |
-
"total_flos": 5.
|
| 5719 |
"train_batch_size": 4,
|
| 5720 |
"trial_name": null,
|
| 5721 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5696 |
"mean_token_accuracy": 0.6544101685285568,
|
| 5697 |
"num_tokens": 11524471.0,
|
| 5698 |
"step": 3160
|
| 5699 |
+
},
|
| 5700 |
+
{
|
| 5701 |
+
"epoch": 24.346153846153847,
|
| 5702 |
+
"grad_norm": 0.0,
|
| 5703 |
+
"learning_rate": 3.418e-05,
|
| 5704 |
+
"loss": 1.7619,
|
| 5705 |
+
"mean_token_accuracy": 0.6497153013944625,
|
| 5706 |
+
"num_tokens": 11542302.0,
|
| 5707 |
+
"step": 3165
|
| 5708 |
+
},
|
| 5709 |
+
{
|
| 5710 |
+
"epoch": 24.384615384615383,
|
| 5711 |
+
"grad_norm": 0.0,
|
| 5712 |
+
"learning_rate": 3.4155e-05,
|
| 5713 |
+
"loss": 1.7937,
|
| 5714 |
+
"mean_token_accuracy": 0.6424742221832276,
|
| 5715 |
+
"num_tokens": 11560367.0,
|
| 5716 |
+
"step": 3170
|
| 5717 |
}
|
| 5718 |
],
|
| 5719 |
"logging_steps": 5,
|
|
|
|
| 5733 |
"attributes": {}
|
| 5734 |
}
|
| 5735 |
},
|
| 5736 |
+
"total_flos": 5.857421453077709e+17,
|
| 5737 |
"train_batch_size": 4,
|
| 5738 |
"trial_name": null,
|
| 5739 |
"trial_params": null
|