Training in progress, step 7540, 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:fd0856f174d0b19ae5924b72ce58181339bbec87a771166f8acd5310faf0c104
|
| 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 sha256:3ede4140a6d99828ffeeac15410313033980d1c8bc0191c2b690829d1cf64b99
|
| 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 sha256:1f7c1eeb1d733e0e1191c3914ec7eb1879e1a3d054e0e2fe0396539c19336a2f
|
| 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":
|
| 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,
|
|
@@ -13562,6 +13562,24 @@
|
|
| 13562 |
"mean_token_accuracy": 0.653878676891327,
|
| 13563 |
"num_tokens": 27463877.0,
|
| 13564 |
"step": 7530
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13565 |
}
|
| 13566 |
],
|
| 13567 |
"logging_steps": 5,
|
|
@@ -13581,7 +13599,7 @@
|
|
| 13581 |
"attributes": {}
|
| 13582 |
}
|
| 13583 |
},
|
| 13584 |
-
"total_flos": 1.
|
| 13585 |
"train_batch_size": 4,
|
| 13586 |
"trial_name": null,
|
| 13587 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7540,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13562 |
"mean_token_accuracy": 0.653878676891327,
|
| 13563 |
"num_tokens": 27463877.0,
|
| 13564 |
"step": 7530
|
| 13565 |
+
},
|
| 13566 |
+
{
|
| 13567 |
+
"epoch": 57.96153846153846,
|
| 13568 |
+
"grad_norm": 0.0,
|
| 13569 |
+
"learning_rate": 1.233e-05,
|
| 13570 |
+
"loss": 1.836,
|
| 13571 |
+
"mean_token_accuracy": 0.6318351715803147,
|
| 13572 |
+
"num_tokens": 27480728.0,
|
| 13573 |
+
"step": 7535
|
| 13574 |
+
},
|
| 13575 |
+
{
|
| 13576 |
+
"epoch": 58.0,
|
| 13577 |
+
"grad_norm": 0.0,
|
| 13578 |
+
"learning_rate": 1.2305000000000002e-05,
|
| 13579 |
+
"loss": 1.8048,
|
| 13580 |
+
"mean_token_accuracy": 0.6375920951366425,
|
| 13581 |
+
"num_tokens": 27498090.0,
|
| 13582 |
+
"step": 7540
|
| 13583 |
}
|
| 13584 |
],
|
| 13585 |
"logging_steps": 5,
|
|
|
|
| 13599 |
"attributes": {}
|
| 13600 |
}
|
| 13601 |
},
|
| 13602 |
+
"total_flos": 1.394166168388731e+18,
|
| 13603 |
"train_batch_size": 4,
|
| 13604 |
"trial_name": null,
|
| 13605 |
"trial_params": null
|