Training in progress, step 3550, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:426be9a43c12141fa5790c71f51d784566641c58c8c212414e4ef4bba36e8719
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5d0a7907b49dce936894818200b0755db855512004b105170a76710c57e2c0b
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f12378eadbf68114d99c85b8b3414a0aa5d00fdcd928f61ed245f1a29dab32f9
|
| 3 |
size 14645
|
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 sha256:672108c6f68a182db61db4c5d50cde93962aa7a8768280cbd14655c187d8e697
|
| 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": 0.
|
| 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,
|
|
@@ -3558,6 +3558,16 @@
|
|
| 3558 |
"mean_token_accuracy": 0.7466149963438511,
|
| 3559 |
"num_tokens": 16498069.0,
|
| 3560 |
"step": 3540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3561 |
}
|
| 3562 |
],
|
| 3563 |
"logging_steps": 10,
|
|
@@ -3577,7 +3587,7 @@
|
|
| 3577 |
"attributes": {}
|
| 3578 |
}
|
| 3579 |
},
|
| 3580 |
-
"total_flos": 7.
|
| 3581 |
"train_batch_size": 4,
|
| 3582 |
"trial_name": null,
|
| 3583 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7573333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3558 |
"mean_token_accuracy": 0.7466149963438511,
|
| 3559 |
"num_tokens": 16498069.0,
|
| 3560 |
"step": 3540
|
| 3561 |
+
},
|
| 3562 |
+
{
|
| 3563 |
+
"entropy": 0.932567299157381,
|
| 3564 |
+
"epoch": 0.7573333333333333,
|
| 3565 |
+
"grad_norm": 0.2745480239391327,
|
| 3566 |
+
"learning_rate": 7.157604980736962e-05,
|
| 3567 |
+
"loss": 1.02783260345459,
|
| 3568 |
+
"mean_token_accuracy": 0.7691405609250068,
|
| 3569 |
+
"num_tokens": 16546746.0,
|
| 3570 |
+
"step": 3550
|
| 3571 |
}
|
| 3572 |
],
|
| 3573 |
"logging_steps": 10,
|
|
|
|
| 3587 |
"attributes": {}
|
| 3588 |
}
|
| 3589 |
},
|
| 3590 |
+
"total_flos": 7.842238964359066e+16,
|
| 3591 |
"train_batch_size": 4,
|
| 3592 |
"trial_name": null,
|
| 3593 |
"trial_params": null
|