Training in progress, step 4860, 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:ff96cc785e4105da1869a915d6139a9c3c63d445cc972d07b58e53b1f527319a
|
| 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:b11202effd51df6416a25dfd9d4e27d41d1046a02ce20a0f1ec298db3d5d0d33
|
| 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 sha256:023d3f1a9c2fcb88862902869eed782ca29b8c691bdf720344abcb612eae0e9d
|
| 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": 37.
|
| 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,
|
|
@@ -8738,6 +8738,24 @@
|
|
| 8738 |
"mean_token_accuracy": 0.6470267534255981,
|
| 8739 |
"num_tokens": 17688130.0,
|
| 8740 |
"step": 4850
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8741 |
}
|
| 8742 |
],
|
| 8743 |
"logging_steps": 5,
|
|
@@ -8757,7 +8775,7 @@
|
|
| 8757 |
"attributes": {}
|
| 8758 |
}
|
| 8759 |
},
|
| 8760 |
-
"total_flos": 8.
|
| 8761 |
"train_batch_size": 4,
|
| 8762 |
"trial_name": null,
|
| 8763 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4860,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8738 |
"mean_token_accuracy": 0.6470267534255981,
|
| 8739 |
"num_tokens": 17688130.0,
|
| 8740 |
"step": 4850
|
| 8741 |
+
},
|
| 8742 |
+
{
|
| 8743 |
+
"epoch": 37.34615384615385,
|
| 8744 |
+
"grad_norm": 0.0,
|
| 8745 |
+
"learning_rate": 2.573e-05,
|
| 8746 |
+
"loss": 1.7409,
|
| 8747 |
+
"mean_token_accuracy": 0.6474620312452316,
|
| 8748 |
+
"num_tokens": 17706679.0,
|
| 8749 |
+
"step": 4855
|
| 8750 |
+
},
|
| 8751 |
+
{
|
| 8752 |
+
"epoch": 37.38461538461539,
|
| 8753 |
+
"grad_norm": 0.0,
|
| 8754 |
+
"learning_rate": 2.5705000000000002e-05,
|
| 8755 |
+
"loss": 1.7944,
|
| 8756 |
+
"mean_token_accuracy": 0.6404423266649246,
|
| 8757 |
+
"num_tokens": 17724627.0,
|
| 8758 |
+
"step": 4860
|
| 8759 |
}
|
| 8760 |
],
|
| 8761 |
"logging_steps": 5,
|
|
|
|
| 8775 |
"attributes": {}
|
| 8776 |
}
|
| 8777 |
},
|
| 8778 |
+
"total_flos": 8.982668212936704e+17,
|
| 8779 |
"train_batch_size": 4,
|
| 8780 |
"trial_name": null,
|
| 8781 |
"trial_params": null
|