Training in progress, step 8750, 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 sha256:236f9969aac401f057f399a1e48494aa7e022e05fe9e0be7368d84d2bb561fc6
|
| 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:d93ddbb591da538ff69386caf86ceff595c7391c92066543e5b594efe74c7fcf
|
| 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:a6c0b8bd764ed24ec19fae1c554f5502d0f773eede2c8924b1e8ea21a51326b1
|
| 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": 67.
|
| 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,
|
|
@@ -15740,6 +15740,24 @@
|
|
| 15740 |
"mean_token_accuracy": 0.6533631831407547,
|
| 15741 |
"num_tokens": 31874474.0,
|
| 15742 |
"step": 8740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15743 |
}
|
| 15744 |
],
|
| 15745 |
"logging_steps": 5,
|
|
@@ -15759,7 +15777,7 @@
|
|
| 15759 |
"attributes": {}
|
| 15760 |
}
|
| 15761 |
},
|
| 15762 |
-
"total_flos": 1.
|
| 15763 |
"train_batch_size": 4,
|
| 15764 |
"trial_name": null,
|
| 15765 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15740 |
"mean_token_accuracy": 0.6533631831407547,
|
| 15741 |
"num_tokens": 31874474.0,
|
| 15742 |
"step": 8740
|
| 15743 |
+
},
|
| 15744 |
+
{
|
| 15745 |
+
"epoch": 67.26923076923077,
|
| 15746 |
+
"grad_norm": 0.0,
|
| 15747 |
+
"learning_rate": 6.28e-06,
|
| 15748 |
+
"loss": 1.6755,
|
| 15749 |
+
"mean_token_accuracy": 0.6652740865945816,
|
| 15750 |
+
"num_tokens": 31893418.0,
|
| 15751 |
+
"step": 8745
|
| 15752 |
+
},
|
| 15753 |
+
{
|
| 15754 |
+
"epoch": 67.3076923076923,
|
| 15755 |
+
"grad_norm": 0.0,
|
| 15756 |
+
"learning_rate": 6.254999999999999e-06,
|
| 15757 |
+
"loss": 1.7896,
|
| 15758 |
+
"mean_token_accuracy": 0.639714989066124,
|
| 15759 |
+
"num_tokens": 31911351.0,
|
| 15760 |
+
"step": 8750
|
| 15761 |
}
|
| 15762 |
],
|
| 15763 |
"logging_steps": 5,
|
|
|
|
| 15777 |
"attributes": {}
|
| 15778 |
}
|
| 15779 |
},
|
| 15780 |
+
"total_flos": 1.6181031953129472e+18,
|
| 15781 |
"train_batch_size": 4,
|
| 15782 |
"trial_name": null,
|
| 15783 |
"trial_params": null
|