Training in progress, step 3490, 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 sha256:3bd1c2796af225b309342c30e1fe88ce20acf1ea8c17085019547e61ed3b7888
|
| 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 sha256:0cf83851e9ada496e11f83a7e5e2470c4d3d7501e1f25354f1a586d5f1daf30f
|
| 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 sha256:6c122a839680352a5055552264c2f47561abcf640ae7bebf224d2b87fca0f3b5
|
| 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:cae3618318e0d321c4e4483d48a9cd1b451ed748eab089557b5fdf8d8a97533f
|
| 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,
|
|
@@ -3498,6 +3498,16 @@
|
|
| 3498 |
"mean_token_accuracy": 0.7344872549176216,
|
| 3499 |
"num_tokens": 16218140.0,
|
| 3500 |
"step": 3480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3501 |
}
|
| 3502 |
],
|
| 3503 |
"logging_steps": 10,
|
|
@@ -3517,7 +3527,7 @@
|
|
| 3517 |
"attributes": {}
|
| 3518 |
}
|
| 3519 |
},
|
| 3520 |
-
"total_flos": 7.
|
| 3521 |
"train_batch_size": 4,
|
| 3522 |
"trial_name": null,
|
| 3523 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7445333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3498 |
"mean_token_accuracy": 0.7344872549176216,
|
| 3499 |
"num_tokens": 16218140.0,
|
| 3500 |
"step": 3480
|
| 3501 |
+
},
|
| 3502 |
+
{
|
| 3503 |
+
"entropy": 0.9035327732563019,
|
| 3504 |
+
"epoch": 0.7445333333333334,
|
| 3505 |
+
"grad_norm": 0.35477346181869507,
|
| 3506 |
+
"learning_rate": 7.250809883844855e-05,
|
| 3507 |
+
"loss": 1.0146682739257813,
|
| 3508 |
+
"mean_token_accuracy": 0.7716259181499481,
|
| 3509 |
+
"num_tokens": 16261629.0,
|
| 3510 |
+
"step": 3490
|
| 3511 |
}
|
| 3512 |
],
|
| 3513 |
"logging_steps": 10,
|
|
|
|
| 3527 |
"attributes": {}
|
| 3528 |
}
|
| 3529 |
},
|
| 3530 |
+
"total_flos": 7.70265683405906e+16,
|
| 3531 |
"train_batch_size": 4,
|
| 3532 |
"trial_name": null,
|
| 3533 |
"trial_params": null
|