Training in progress, step 3520, 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:eaabce9a37b2dc21c4ddcfe2cc5789904f2de3abd7f17c2f73a36bc76bc5dc5d
|
| 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 sha256:8cd72153623ce8b1d5da24cf3891fd3128eaf61447bf3ad3158a82ee0a361466
|
| 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 sha256:1795a6a4ac0dd6383625543080a09d385e140315b6e92298e0cedcdf486f7f99
|
| 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:b768181766a9a624e33d294d2855e294f5735388c4e8a9a87ae347064fbed161
|
| 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,
|
|
@@ -3528,6 +3528,16 @@
|
|
| 3528 |
"mean_token_accuracy": 0.7408729113638401,
|
| 3529 |
"num_tokens": 16355489.0,
|
| 3530 |
"step": 3510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3531 |
}
|
| 3532 |
],
|
| 3533 |
"logging_steps": 10,
|
|
@@ -3547,7 +3557,7 @@
|
|
| 3547 |
"attributes": {}
|
| 3548 |
}
|
| 3549 |
},
|
| 3550 |
-
"total_flos": 7.
|
| 3551 |
"train_batch_size": 4,
|
| 3552 |
"trial_name": null,
|
| 3553 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7509333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3528 |
"mean_token_accuracy": 0.7408729113638401,
|
| 3529 |
"num_tokens": 16355489.0,
|
| 3530 |
"step": 3510
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"entropy": 0.9718878209590912,
|
| 3534 |
+
"epoch": 0.7509333333333333,
|
| 3535 |
+
"grad_norm": 0.3055277168750763,
|
| 3536 |
+
"learning_rate": 7.20432628121669e-05,
|
| 3537 |
+
"loss": 1.1054911613464355,
|
| 3538 |
+
"mean_token_accuracy": 0.7583063259720803,
|
| 3539 |
+
"num_tokens": 16400826.0,
|
| 3540 |
+
"step": 3520
|
| 3541 |
}
|
| 3542 |
],
|
| 3543 |
"logging_steps": 10,
|
|
|
|
| 3557 |
"attributes": {}
|
| 3558 |
}
|
| 3559 |
},
|
| 3560 |
+
"total_flos": 7.770614434527744e+16,
|
| 3561 |
"train_batch_size": 4,
|
| 3562 |
"trial_name": null,
|
| 3563 |
"trial_params": null
|