Training in progress, step 8660, 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 sha256:10432662ffb3fe4e360028abe2479d00659b2b7f35ba62dada6fcf2de8ec113d
|
| 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:e014dc309e4e976a73fc40c9603e67e1f05b2f51488da6aa1fd7195c755d1649
|
| 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 sha256:3656f6e48aa7808dc0d30ce19947a758f543c8658f4e26a136b97f21e1554ba5
|
| 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": 66.
|
| 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,
|
|
@@ -15578,6 +15578,24 @@
|
|
| 15578 |
"mean_token_accuracy": 0.6471589595079422,
|
| 15579 |
"num_tokens": 31546956.0,
|
| 15580 |
"step": 8650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15581 |
}
|
| 15582 |
],
|
| 15583 |
"logging_steps": 5,
|
|
@@ -15597,7 +15615,7 @@
|
|
| 15597 |
"attributes": {}
|
| 15598 |
}
|
| 15599 |
},
|
| 15600 |
-
"total_flos": 1.
|
| 15601 |
"train_batch_size": 4,
|
| 15602 |
"trial_name": null,
|
| 15603 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 66.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8660,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15578 |
"mean_token_accuracy": 0.6471589595079422,
|
| 15579 |
"num_tokens": 31546956.0,
|
| 15580 |
"step": 8650
|
| 15581 |
+
},
|
| 15582 |
+
{
|
| 15583 |
+
"epoch": 66.57692307692308,
|
| 15584 |
+
"grad_norm": 0.0,
|
| 15585 |
+
"learning_rate": 6.73e-06,
|
| 15586 |
+
"loss": 1.7086,
|
| 15587 |
+
"mean_token_accuracy": 0.6558182656764984,
|
| 15588 |
+
"num_tokens": 31565836.0,
|
| 15589 |
+
"step": 8655
|
| 15590 |
+
},
|
| 15591 |
+
{
|
| 15592 |
+
"epoch": 66.61538461538461,
|
| 15593 |
+
"grad_norm": 0.0,
|
| 15594 |
+
"learning_rate": 6.705e-06,
|
| 15595 |
+
"loss": 1.7636,
|
| 15596 |
+
"mean_token_accuracy": 0.6479879409074784,
|
| 15597 |
+
"num_tokens": 31583762.0,
|
| 15598 |
+
"step": 8660
|
| 15599 |
}
|
| 15600 |
],
|
| 15601 |
"logging_steps": 5,
|
|
|
|
| 15615 |
"attributes": {}
|
| 15616 |
}
|
| 15617 |
},
|
| 15618 |
+
"total_flos": 1.6014780660267418e+18,
|
| 15619 |
"train_batch_size": 4,
|
| 15620 |
"trial_name": null,
|
| 15621 |
"trial_params": null
|