Training in progress, step 7580, 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:c1a28dd94b089f0e3bdc54ddf13fafd41058b5e694c112dc3574900ae1db1cc9
|
| 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 sha256:1cdd938ada356e1d00ef2559e2ef99e65448c724156c1430e0198b63fe7ad709
|
| 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 sha256:1a6ca2da1aa64d463501da0fcad79b37fa867b372dd10af0c5a1fb390b1c9a4f
|
| 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": 58.
|
| 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,
|
|
@@ -13634,6 +13634,24 @@
|
|
| 13634 |
"mean_token_accuracy": 0.6435631811618805,
|
| 13635 |
"num_tokens": 27605236.0,
|
| 13636 |
"step": 7570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13637 |
}
|
| 13638 |
],
|
| 13639 |
"logging_steps": 5,
|
|
@@ -13653,7 +13671,7 @@
|
|
| 13653 |
"attributes": {}
|
| 13654 |
}
|
| 13655 |
},
|
| 13656 |
-
"total_flos": 1.
|
| 13657 |
"train_batch_size": 4,
|
| 13658 |
"trial_name": null,
|
| 13659 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13634 |
"mean_token_accuracy": 0.6435631811618805,
|
| 13635 |
"num_tokens": 27605236.0,
|
| 13636 |
"step": 7570
|
| 13637 |
+
},
|
| 13638 |
+
{
|
| 13639 |
+
"epoch": 58.26923076923077,
|
| 13640 |
+
"grad_norm": 0.0,
|
| 13641 |
+
"learning_rate": 1.213e-05,
|
| 13642 |
+
"loss": 1.7401,
|
| 13643 |
+
"mean_token_accuracy": 0.6488517135381698,
|
| 13644 |
+
"num_tokens": 27623605.0,
|
| 13645 |
+
"step": 7575
|
| 13646 |
+
},
|
| 13647 |
+
{
|
| 13648 |
+
"epoch": 58.30769230769231,
|
| 13649 |
+
"grad_norm": 0.0,
|
| 13650 |
+
"learning_rate": 1.2105000000000002e-05,
|
| 13651 |
+
"loss": 1.7388,
|
| 13652 |
+
"mean_token_accuracy": 0.6520835846662522,
|
| 13653 |
+
"num_tokens": 27641906.0,
|
| 13654 |
+
"step": 7580
|
| 13655 |
}
|
| 13656 |
],
|
| 13657 |
"logging_steps": 5,
|
|
|
|
| 13671 |
"attributes": {}
|
| 13672 |
}
|
| 13673 |
},
|
| 13674 |
+
"total_flos": 1.4014479388144435e+18,
|
| 13675 |
"train_batch_size": 4,
|
| 13676 |
"trial_name": null,
|
| 13677 |
"trial_params": null
|