Training in progress, step 6540, 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 sha256:7a86c1390ce736748bfebf1e8c91a1ea3128f5b5a660f6fafdbe3e79ec3fd62c
|
| 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 sha256:223881f33bc27bac40d898a61846d6adba5e9217bc4c26e5feea71319c8e7637
|
| 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 sha256:68b89882a2939131c2d676f3d4889231406ac76b8938dd3eab03cf8ec21b8b81
|
| 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": 50.
|
| 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,
|
|
@@ -11762,6 +11762,24 @@
|
|
| 11762 |
"mean_token_accuracy": 0.6565469861030578,
|
| 11763 |
"num_tokens": 23814122.0,
|
| 11764 |
"step": 6530
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11765 |
}
|
| 11766 |
],
|
| 11767 |
"logging_steps": 5,
|
|
@@ -11781,7 +11799,7 @@
|
|
| 11781 |
"attributes": {}
|
| 11782 |
}
|
| 11783 |
},
|
| 11784 |
-
"total_flos": 1.
|
| 11785 |
"train_batch_size": 4,
|
| 11786 |
"trial_name": null,
|
| 11787 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6540,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11762 |
"mean_token_accuracy": 0.6565469861030578,
|
| 11763 |
"num_tokens": 23814122.0,
|
| 11764 |
"step": 6530
|
| 11765 |
+
},
|
| 11766 |
+
{
|
| 11767 |
+
"epoch": 50.26923076923077,
|
| 11768 |
+
"grad_norm": 0.0,
|
| 11769 |
+
"learning_rate": 1.7330000000000002e-05,
|
| 11770 |
+
"loss": 1.6964,
|
| 11771 |
+
"mean_token_accuracy": 0.6581017464399338,
|
| 11772 |
+
"num_tokens": 23832733.0,
|
| 11773 |
+
"step": 6535
|
| 11774 |
+
},
|
| 11775 |
+
{
|
| 11776 |
+
"epoch": 50.30769230769231,
|
| 11777 |
+
"grad_norm": 0.0,
|
| 11778 |
+
"learning_rate": 1.7305e-05,
|
| 11779 |
+
"loss": 1.7557,
|
| 11780 |
+
"mean_token_accuracy": 0.6457631707191467,
|
| 11781 |
+
"num_tokens": 23851205.0,
|
| 11782 |
+
"step": 6540
|
| 11783 |
}
|
| 11784 |
],
|
| 11785 |
"logging_steps": 5,
|
|
|
|
| 11799 |
"attributes": {}
|
| 11800 |
}
|
| 11801 |
},
|
| 11802 |
+
"total_flos": 1.2092022768048538e+18,
|
| 11803 |
"train_batch_size": 4,
|
| 11804 |
"trial_name": null,
|
| 11805 |
"trial_params": null
|