Training in progress, step 5440, 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:c4c12c836441b9716fd56d56d2793dca388a9b7266d8a5c734ef09272be02156
|
| 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 sha256:5fee675778afc38085430f750eb36b24497b5619387db7886f2f6209f1ad5e7c
|
| 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 sha256:853ddd3303a2fe87549b13121a46995adb6e70805b7865c1c5b29c53f995813e
|
| 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": 41.
|
| 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,
|
|
@@ -9782,6 +9782,24 @@
|
|
| 9782 |
"mean_token_accuracy": 0.6542178004980087,
|
| 9783 |
"num_tokens": 19803873.0,
|
| 9784 |
"step": 5430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9785 |
}
|
| 9786 |
],
|
| 9787 |
"logging_steps": 5,
|
|
@@ -9801,7 +9819,7 @@
|
|
| 9801 |
"attributes": {}
|
| 9802 |
}
|
| 9803 |
},
|
| 9804 |
-
"total_flos": 1.
|
| 9805 |
"train_batch_size": 4,
|
| 9806 |
"trial_name": null,
|
| 9807 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9782 |
"mean_token_accuracy": 0.6542178004980087,
|
| 9783 |
"num_tokens": 19803873.0,
|
| 9784 |
"step": 5430
|
| 9785 |
+
},
|
| 9786 |
+
{
|
| 9787 |
+
"epoch": 41.80769230769231,
|
| 9788 |
+
"grad_norm": 0.0,
|
| 9789 |
+
"learning_rate": 2.283e-05,
|
| 9790 |
+
"loss": 1.7208,
|
| 9791 |
+
"mean_token_accuracy": 0.6572512924671173,
|
| 9792 |
+
"num_tokens": 19822419.0,
|
| 9793 |
+
"step": 5435
|
| 9794 |
+
},
|
| 9795 |
+
{
|
| 9796 |
+
"epoch": 41.84615384615385,
|
| 9797 |
+
"grad_norm": 0.0,
|
| 9798 |
+
"learning_rate": 2.2805000000000003e-05,
|
| 9799 |
+
"loss": 1.7922,
|
| 9800 |
+
"mean_token_accuracy": 0.6356712460517884,
|
| 9801 |
+
"num_tokens": 19840582.0,
|
| 9802 |
+
"step": 5440
|
| 9803 |
}
|
| 9804 |
],
|
| 9805 |
"logging_steps": 5,
|
|
|
|
| 9819 |
"attributes": {}
|
| 9820 |
}
|
| 9821 |
},
|
| 9822 |
+
"total_flos": 1.0054035265565491e+18,
|
| 9823 |
"train_batch_size": 4,
|
| 9824 |
"trial_name": null,
|
| 9825 |
"trial_params": null
|