Training in progress, step 5890, 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:dc0a370a3561d21cc4ad58cbf6b5303c436e248925642eb42b0b2ba96ae8c003
|
| 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 sha256:1c10b74d2c90445b9c79201d5f85a3f8709f52e3c5a6ebb463815e2b889fab10
|
| 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:f505188f6aaa1af940f15b83204a2f7f5d9fbac85c007515a20116f45f84a94d
|
| 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": 45.
|
| 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,
|
|
@@ -10592,6 +10592,24 @@
|
|
| 10592 |
"mean_token_accuracy": 0.6484750181436538,
|
| 10593 |
"num_tokens": 21446444.0,
|
| 10594 |
"step": 5880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10595 |
}
|
| 10596 |
],
|
| 10597 |
"logging_steps": 5,
|
|
@@ -10611,7 +10629,7 @@
|
|
| 10611 |
"attributes": {}
|
| 10612 |
}
|
| 10613 |
},
|
| 10614 |
-
"total_flos": 1.
|
| 10615 |
"train_batch_size": 4,
|
| 10616 |
"trial_name": null,
|
| 10617 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5890,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10592 |
"mean_token_accuracy": 0.6484750181436538,
|
| 10593 |
"num_tokens": 21446444.0,
|
| 10594 |
"step": 5880
|
| 10595 |
+
},
|
| 10596 |
+
{
|
| 10597 |
+
"epoch": 45.26923076923077,
|
| 10598 |
+
"grad_norm": 0.0,
|
| 10599 |
+
"learning_rate": 2.0580000000000003e-05,
|
| 10600 |
+
"loss": 1.7472,
|
| 10601 |
+
"mean_token_accuracy": 0.6514826148748398,
|
| 10602 |
+
"num_tokens": 21464094.0,
|
| 10603 |
+
"step": 5885
|
| 10604 |
+
},
|
| 10605 |
+
{
|
| 10606 |
+
"epoch": 45.30769230769231,
|
| 10607 |
+
"grad_norm": 0.0,
|
| 10608 |
+
"learning_rate": 2.0555000000000002e-05,
|
| 10609 |
+
"loss": 1.6722,
|
| 10610 |
+
"mean_token_accuracy": 0.6630917578935623,
|
| 10611 |
+
"num_tokens": 21482239.0,
|
| 10612 |
+
"step": 5890
|
| 10613 |
}
|
| 10614 |
],
|
| 10615 |
"logging_steps": 5,
|
|
|
|
| 10629 |
"attributes": {}
|
| 10630 |
}
|
| 10631 |
},
|
| 10632 |
+
"total_flos": 1.0886353962364109e+18,
|
| 10633 |
"train_batch_size": 4,
|
| 10634 |
"trial_name": null,
|
| 10635 |
"trial_params": null
|