Training in progress, step 4220, 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 sha256:3cf116a73664a304c0100f71483e8435f90e8a171b08ef736e206693248cde47
|
| 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:ed51210223ef3e564f63c789d67c42e95720f16ad0b188fb3f966f333703add7
|
| 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 sha256:4cfcd7a210a8ad0f29b8f2bcf5f90defcb3ccd6f7743fa97e52198541b8238ac
|
| 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": 32.
|
| 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,
|
|
@@ -7586,6 +7586,24 @@
|
|
| 7586 |
"mean_token_accuracy": 0.6678825885057449,
|
| 7587 |
"num_tokens": 15355227.0,
|
| 7588 |
"step": 4210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7589 |
}
|
| 7590 |
],
|
| 7591 |
"logging_steps": 5,
|
|
@@ -7605,7 +7623,7 @@
|
|
| 7605 |
"attributes": {}
|
| 7606 |
}
|
| 7607 |
},
|
| 7608 |
-
"total_flos": 7.
|
| 7609 |
"train_batch_size": 4,
|
| 7610 |
"trial_name": null,
|
| 7611 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7586 |
"mean_token_accuracy": 0.6678825885057449,
|
| 7587 |
"num_tokens": 15355227.0,
|
| 7588 |
"step": 4210
|
| 7589 |
+
},
|
| 7590 |
+
{
|
| 7591 |
+
"epoch": 32.42307692307692,
|
| 7592 |
+
"grad_norm": 0.0,
|
| 7593 |
+
"learning_rate": 2.8930000000000003e-05,
|
| 7594 |
+
"loss": 1.7637,
|
| 7595 |
+
"mean_token_accuracy": 0.6434868663549423,
|
| 7596 |
+
"num_tokens": 15373422.0,
|
| 7597 |
+
"step": 4215
|
| 7598 |
+
},
|
| 7599 |
+
{
|
| 7600 |
+
"epoch": 32.46153846153846,
|
| 7601 |
+
"grad_norm": 0.0,
|
| 7602 |
+
"learning_rate": 2.8905e-05,
|
| 7603 |
+
"loss": 1.7577,
|
| 7604 |
+
"mean_token_accuracy": 0.6474568367004394,
|
| 7605 |
+
"num_tokens": 15391589.0,
|
| 7606 |
+
"step": 4220
|
| 7607 |
}
|
| 7608 |
],
|
| 7609 |
"logging_steps": 5,
|
|
|
|
| 7623 |
"attributes": {}
|
| 7624 |
}
|
| 7625 |
},
|
| 7626 |
+
"total_flos": 7.800854386183373e+17,
|
| 7627 |
"train_batch_size": 4,
|
| 7628 |
"trial_name": null,
|
| 7629 |
"trial_params": null
|