Training in progress, step 4730, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57fc42b485786f7e5efa3c035528ddbc5f760cbfa0c11a1e0b6a6effde0551fb
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9721f8078468f63a635558c01f1f0899ac635617a27c3d62a2cbe24adbabdb9d
|
| 3 |
size 14709
|
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:e120f77f030edd1bdde7ae6c2bd4df71322af66fcf0dd84dec07f900e161f361
|
| 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": 36.
|
| 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,
|
|
@@ -8504,6 +8504,24 @@
|
|
| 8504 |
"mean_token_accuracy": 0.6590126276016235,
|
| 8505 |
"num_tokens": 17213782.0,
|
| 8506 |
"step": 4720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8507 |
}
|
| 8508 |
],
|
| 8509 |
"logging_steps": 5,
|
|
@@ -8523,7 +8541,7 @@
|
|
| 8523 |
"attributes": {}
|
| 8524 |
}
|
| 8525 |
},
|
| 8526 |
-
"total_flos": 8.
|
| 8527 |
"train_batch_size": 4,
|
| 8528 |
"trial_name": null,
|
| 8529 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4730,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8504 |
"mean_token_accuracy": 0.6590126276016235,
|
| 8505 |
"num_tokens": 17213782.0,
|
| 8506 |
"step": 4720
|
| 8507 |
+
},
|
| 8508 |
+
{
|
| 8509 |
+
"epoch": 36.34615384615385,
|
| 8510 |
+
"grad_norm": 0.0,
|
| 8511 |
+
"learning_rate": 2.6379999999999998e-05,
|
| 8512 |
+
"loss": 1.7659,
|
| 8513 |
+
"mean_token_accuracy": 0.6419188559055329,
|
| 8514 |
+
"num_tokens": 17231953.0,
|
| 8515 |
+
"step": 4725
|
| 8516 |
+
},
|
| 8517 |
+
{
|
| 8518 |
+
"epoch": 36.38461538461539,
|
| 8519 |
+
"grad_norm": 0.0,
|
| 8520 |
+
"learning_rate": 2.6355e-05,
|
| 8521 |
+
"loss": 1.7443,
|
| 8522 |
+
"mean_token_accuracy": 0.6517761409282684,
|
| 8523 |
+
"num_tokens": 17250069.0,
|
| 8524 |
+
"step": 4730
|
| 8525 |
}
|
| 8526 |
],
|
| 8527 |
"logging_steps": 5,
|
|
|
|
| 8541 |
"attributes": {}
|
| 8542 |
}
|
| 8543 |
},
|
| 8544 |
+
"total_flos": 8.742308341358592e+17,
|
| 8545 |
"train_batch_size": 4,
|
| 8546 |
"trial_name": null,
|
| 8547 |
"trial_params": null
|