Training in progress, step 5970, 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 sha256:11a53e5b1598ba62f3b40247c471ce62c169a02e1778d2387859001ad7729c7a
|
| 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:f054284defb407cb4c04d48753632573883d222afa0038a6f1d5508b13621381
|
| 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 sha256:35908209560c175138f626a0c60f4dbca7d39c3c7724815c597cf3b06200f4ff
|
| 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": 45.
|
| 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,
|
|
@@ -10736,6 +10736,24 @@
|
|
| 10736 |
"mean_token_accuracy": 0.6459046006202698,
|
| 10737 |
"num_tokens": 21734632.0,
|
| 10738 |
"step": 5960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10739 |
}
|
| 10740 |
],
|
| 10741 |
"logging_steps": 5,
|
|
@@ -10755,7 +10773,7 @@
|
|
| 10755 |
"attributes": {}
|
| 10756 |
}
|
| 10757 |
},
|
| 10758 |
-
"total_flos": 1.
|
| 10759 |
"train_batch_size": 4,
|
| 10760 |
"trial_name": null,
|
| 10761 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5970,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10736 |
"mean_token_accuracy": 0.6459046006202698,
|
| 10737 |
"num_tokens": 21734632.0,
|
| 10738 |
"step": 5960
|
| 10739 |
+
},
|
| 10740 |
+
{
|
| 10741 |
+
"epoch": 45.88461538461539,
|
| 10742 |
+
"grad_norm": 0.0,
|
| 10743 |
+
"learning_rate": 2.0180000000000003e-05,
|
| 10744 |
+
"loss": 1.7534,
|
| 10745 |
+
"mean_token_accuracy": 0.6509894400835037,
|
| 10746 |
+
"num_tokens": 21753024.0,
|
| 10747 |
+
"step": 5965
|
| 10748 |
+
},
|
| 10749 |
+
{
|
| 10750 |
+
"epoch": 45.92307692307692,
|
| 10751 |
+
"grad_norm": 0.0,
|
| 10752 |
+
"learning_rate": 2.0155000000000003e-05,
|
| 10753 |
+
"loss": 1.6896,
|
| 10754 |
+
"mean_token_accuracy": 0.663582494854927,
|
| 10755 |
+
"num_tokens": 21771809.0,
|
| 10756 |
+
"step": 5970
|
| 10757 |
}
|
| 10758 |
],
|
| 10759 |
"logging_steps": 5,
|
|
|
|
| 10773 |
"attributes": {}
|
| 10774 |
}
|
| 10775 |
},
|
| 10776 |
+
"total_flos": 1.1033189741223936e+18,
|
| 10777 |
"train_batch_size": 4,
|
| 10778 |
"trial_name": null,
|
| 10779 |
"trial_params": null
|