Training in progress, step 5380, 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 sha256:151389d351bd1a535e4e8d24c0804213bc4d65f743b8534a6b548965acf7d9ec
|
| 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 sha256:23a2a1da4e20edc6b7587cbaefab32d18b05ce93572842395b337ef5dd49d445
|
| 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 sha256:610f3e597517d7530b9348745367f567ec550748a5a787fa7cf4eb0fb1b1998e
|
| 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": 41.
|
| 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,
|
|
@@ -9674,6 +9674,24 @@
|
|
| 9674 |
"mean_token_accuracy": 0.6617189884185791,
|
| 9675 |
"num_tokens": 19584102.0,
|
| 9676 |
"step": 5370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9677 |
}
|
| 9678 |
],
|
| 9679 |
"logging_steps": 5,
|
|
@@ -9693,7 +9711,7 @@
|
|
| 9693 |
"attributes": {}
|
| 9694 |
}
|
| 9695 |
},
|
| 9696 |
-
"total_flos": 9.
|
| 9697 |
"train_batch_size": 4,
|
| 9698 |
"trial_name": null,
|
| 9699 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9674 |
"mean_token_accuracy": 0.6617189884185791,
|
| 9675 |
"num_tokens": 19584102.0,
|
| 9676 |
"step": 5370
|
| 9677 |
+
},
|
| 9678 |
+
{
|
| 9679 |
+
"epoch": 41.34615384615385,
|
| 9680 |
+
"grad_norm": 0.0,
|
| 9681 |
+
"learning_rate": 2.313e-05,
|
| 9682 |
+
"loss": 1.6773,
|
| 9683 |
+
"mean_token_accuracy": 0.6627373963594436,
|
| 9684 |
+
"num_tokens": 19602734.0,
|
| 9685 |
+
"step": 5375
|
| 9686 |
+
},
|
| 9687 |
+
{
|
| 9688 |
+
"epoch": 41.38461538461539,
|
| 9689 |
+
"grad_norm": 0.0,
|
| 9690 |
+
"learning_rate": 2.3105000000000003e-05,
|
| 9691 |
+
"loss": 1.7655,
|
| 9692 |
+
"mean_token_accuracy": 0.6403976768255234,
|
| 9693 |
+
"num_tokens": 19620846.0,
|
| 9694 |
+
"step": 5380
|
| 9695 |
}
|
| 9696 |
],
|
| 9697 |
"logging_steps": 5,
|
|
|
|
| 9711 |
"attributes": {}
|
| 9712 |
}
|
| 9713 |
},
|
| 9714 |
+
"total_flos": 9.941746653344563e+17,
|
| 9715 |
"train_batch_size": 4,
|
| 9716 |
"trial_name": null,
|
| 9717 |
"trial_params": null
|