Training in progress, step 8100, 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 sha256:302622f80a52d410e91a97e9a7ae7c6ba1fbaf0f478304f5519c31f7d402d210
|
| 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 sha256:22fdffac3ea0f421be59bf5427617b235017152573fca74cbf693130b33e6103
|
| 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:ea11e8669dcf93123614373867f8b7da4cd5e706fa62688f2f6e9e1314747d37
|
| 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": 62.
|
| 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,
|
|
@@ -14570,6 +14570,24 @@
|
|
| 14570 |
"mean_token_accuracy": 0.6603300988674163,
|
| 14571 |
"num_tokens": 29503619.0,
|
| 14572 |
"step": 8090
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14573 |
}
|
| 14574 |
],
|
| 14575 |
"logging_steps": 5,
|
|
@@ -14589,7 +14607,7 @@
|
|
| 14589 |
"attributes": {}
|
| 14590 |
}
|
| 14591 |
},
|
| 14592 |
-
"total_flos": 1.
|
| 14593 |
"train_batch_size": 4,
|
| 14594 |
"trial_name": null,
|
| 14595 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14570 |
"mean_token_accuracy": 0.6603300988674163,
|
| 14571 |
"num_tokens": 29503619.0,
|
| 14572 |
"step": 8090
|
| 14573 |
+
},
|
| 14574 |
+
{
|
| 14575 |
+
"epoch": 62.26923076923077,
|
| 14576 |
+
"grad_norm": 0.0,
|
| 14577 |
+
"learning_rate": 9.53e-06,
|
| 14578 |
+
"loss": 1.7563,
|
| 14579 |
+
"mean_token_accuracy": 0.6429074674844741,
|
| 14580 |
+
"num_tokens": 29521125.0,
|
| 14581 |
+
"step": 8095
|
| 14582 |
+
},
|
| 14583 |
+
{
|
| 14584 |
+
"epoch": 62.30769230769231,
|
| 14585 |
+
"grad_norm": 0.0,
|
| 14586 |
+
"learning_rate": 9.505e-06,
|
| 14587 |
+
"loss": 1.7227,
|
| 14588 |
+
"mean_token_accuracy": 0.6537641167640686,
|
| 14589 |
+
"num_tokens": 29539856.0,
|
| 14590 |
+
"step": 8100
|
| 14591 |
}
|
| 14592 |
],
|
| 14593 |
"logging_steps": 5,
|
|
|
|
| 14607 |
"attributes": {}
|
| 14608 |
}
|
| 14609 |
},
|
| 14610 |
+
"total_flos": 1.49776241624875e+18,
|
| 14611 |
"train_batch_size": 4,
|
| 14612 |
"trial_name": null,
|
| 14613 |
"trial_params": null
|