Training in progress, step 3430, 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:d128cfbbe4255f122fe7c526ce6ca739e2b217c6cf15ad3c79deeadcb33c510f
|
| 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 sha256:32bb3852a8edfc12e841ab5978910b8067a4a72659c719650d412b08f664ef41
|
| 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 sha256:939e063776f1e83a51fd19519c1f2a4ed27d183e4f95ee1c9e9ccd6d1d29f270
|
| 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 sha256:5caf0bd93d4bf4a19e7af16eadd5ba4a6cd498b76c005df88e42e0bd31fd3760
|
| 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,
|
|
@@ -3438,6 +3438,16 @@
|
|
| 3438 |
"mean_token_accuracy": 0.738009649515152,
|
| 3439 |
"num_tokens": 15937698.0,
|
| 3440 |
"step": 3420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3441 |
}
|
| 3442 |
],
|
| 3443 |
"logging_steps": 10,
|
|
@@ -3457,7 +3467,7 @@
|
|
| 3457 |
"attributes": {}
|
| 3458 |
}
|
| 3459 |
},
|
| 3460 |
-
"total_flos": 7.
|
| 3461 |
"train_batch_size": 4,
|
| 3462 |
"trial_name": null,
|
| 3463 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7317333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3438 |
"mean_token_accuracy": 0.738009649515152,
|
| 3439 |
"num_tokens": 15937698.0,
|
| 3440 |
"step": 3420
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"entropy": 0.9974006466567517,
|
| 3444 |
+
"epoch": 0.7317333333333333,
|
| 3445 |
+
"grad_norm": 0.23932306468486786,
|
| 3446 |
+
"learning_rate": 7.343043971959902e-05,
|
| 3447 |
+
"loss": 1.0580031394958496,
|
| 3448 |
+
"mean_token_accuracy": 0.7584069922566414,
|
| 3449 |
+
"num_tokens": 15984086.0,
|
| 3450 |
+
"step": 3430
|
| 3451 |
}
|
| 3452 |
],
|
| 3453 |
"logging_steps": 10,
|
|
|
|
| 3467 |
"attributes": {}
|
| 3468 |
}
|
| 3469 |
},
|
| 3470 |
+
"total_flos": 7.572279426420634e+16,
|
| 3471 |
"train_batch_size": 4,
|
| 3472 |
"trial_name": null,
|
| 3473 |
"trial_params": null
|