Training in progress, step 7570, 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 sha256:906b0f821cb3c7393013170289cf1c3bf9baf7f7ede4bdeff70f5d9be6a137b3
|
| 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 sha256:8f96f08c72a0d8cd9a78a322096bad15c6e8a36884f94909a4350722007feab4
|
| 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:ece93387c383c00163f081b9574ab679cd79584bcc493d9c15136ce445767585
|
| 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,
|
|
@@ -13616,6 +13616,24 @@
|
|
| 13616 |
"mean_token_accuracy": 0.6494860410690307,
|
| 13617 |
"num_tokens": 27569697.0,
|
| 13618 |
"step": 7560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13619 |
}
|
| 13620 |
],
|
| 13621 |
"logging_steps": 5,
|
|
@@ -13635,7 +13653,7 @@
|
|
| 13635 |
"attributes": {}
|
| 13636 |
}
|
| 13637 |
},
|
| 13638 |
-
"total_flos": 1.
|
| 13639 |
"train_batch_size": 4,
|
| 13640 |
"trial_name": null,
|
| 13641 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13616 |
"mean_token_accuracy": 0.6494860410690307,
|
| 13617 |
"num_tokens": 27569697.0,
|
| 13618 |
"step": 7560
|
| 13619 |
+
},
|
| 13620 |
+
{
|
| 13621 |
+
"epoch": 58.19230769230769,
|
| 13622 |
+
"grad_norm": 0.0,
|
| 13623 |
+
"learning_rate": 1.2180000000000002e-05,
|
| 13624 |
+
"loss": 1.7436,
|
| 13625 |
+
"mean_token_accuracy": 0.6535836279392242,
|
| 13626 |
+
"num_tokens": 27588049.0,
|
| 13627 |
+
"step": 7565
|
| 13628 |
+
},
|
| 13629 |
+
{
|
| 13630 |
+
"epoch": 58.23076923076923,
|
| 13631 |
+
"grad_norm": 0.0,
|
| 13632 |
+
"learning_rate": 1.2155000000000001e-05,
|
| 13633 |
+
"loss": 1.7814,
|
| 13634 |
+
"mean_token_accuracy": 0.6435631811618805,
|
| 13635 |
+
"num_tokens": 27605236.0,
|
| 13636 |
+
"step": 7570
|
| 13637 |
}
|
| 13638 |
],
|
| 13639 |
"logging_steps": 5,
|
|
|
|
| 13653 |
"attributes": {}
|
| 13654 |
}
|
| 13655 |
},
|
| 13656 |
+
"total_flos": 1.39951908974592e+18,
|
| 13657 |
"train_batch_size": 4,
|
| 13658 |
"trial_name": null,
|
| 13659 |
"trial_params": null
|