Training in progress, step 3560, 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:ebde3d7e559a48848dc709360ddf4d64cdda954d1cb3fe794d942bded79f95d8
|
| 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:c17c3bc26250a812166f29e379657082877dc2905caa7b3ca79bd0e054588564
|
| 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:d702f00a2f08d2b738793fd7a29f217448a5a6e44a611e821d40d99816cd86d9
|
| 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 sha256:6dd90a7b3ffd42e7d697a64c9b723494d4e821060ee3fea49f312e5184c1a7a0
|
| 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,
|
|
@@ -3568,6 +3568,16 @@
|
|
| 3568 |
"mean_token_accuracy": 0.7691405609250068,
|
| 3569 |
"num_tokens": 16546746.0,
|
| 3570 |
"step": 3550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3571 |
}
|
| 3572 |
],
|
| 3573 |
"logging_steps": 10,
|
|
@@ -3587,7 +3597,7 @@
|
|
| 3587 |
"attributes": {}
|
| 3588 |
}
|
| 3589 |
},
|
| 3590 |
-
"total_flos": 7.
|
| 3591 |
"train_batch_size": 4,
|
| 3592 |
"trial_name": null,
|
| 3593 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7594666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3560,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3568 |
"mean_token_accuracy": 0.7691405609250068,
|
| 3569 |
"num_tokens": 16546746.0,
|
| 3570 |
"step": 3550
|
| 3571 |
+
},
|
| 3572 |
+
{
|
| 3573 |
+
"entropy": 0.9001861125230789,
|
| 3574 |
+
"epoch": 0.7594666666666666,
|
| 3575 |
+
"grad_norm": 0.29825839400291443,
|
| 3576 |
+
"learning_rate": 7.141979262215396e-05,
|
| 3577 |
+
"loss": 1.0350588798522948,
|
| 3578 |
+
"mean_token_accuracy": 0.7682245895266533,
|
| 3579 |
+
"num_tokens": 16586157.0,
|
| 3580 |
+
"step": 3560
|
| 3581 |
}
|
| 3582 |
],
|
| 3583 |
"logging_steps": 10,
|
|
|
|
| 3597 |
"attributes": {}
|
| 3598 |
}
|
| 3599 |
},
|
| 3600 |
+
"total_flos": 7.860559192182374e+16,
|
| 3601 |
"train_batch_size": 4,
|
| 3602 |
"trial_name": null,
|
| 3603 |
"trial_params": null
|