Training in progress, step 1970, 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 sha256:07916d5a8d30e1f2e52e5b10bb92604f39fd3e774702a32779c580a76c5494a1
|
| 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:db3e22887db76d3b7a0cdea7e3a1b54cb368f9c88f6936bb2013215dff66ff29
|
| 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 sha256:972f71b5a9c68e6400a63574d05027c51ba2f64906c86fc03d5705f537dde005
|
| 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": 15.
|
| 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,
|
|
@@ -3536,6 +3536,24 @@
|
|
| 3536 |
"mean_token_accuracy": 0.6474148839712143,
|
| 3537 |
"num_tokens": 7147764.0,
|
| 3538 |
"step": 1960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3539 |
}
|
| 3540 |
],
|
| 3541 |
"logging_steps": 5,
|
|
@@ -3555,7 +3573,7 @@
|
|
| 3555 |
"attributes": {}
|
| 3556 |
}
|
| 3557 |
},
|
| 3558 |
-
"total_flos": 3.
|
| 3559 |
"train_batch_size": 4,
|
| 3560 |
"trial_name": null,
|
| 3561 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1970,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3536 |
"mean_token_accuracy": 0.6474148839712143,
|
| 3537 |
"num_tokens": 7147764.0,
|
| 3538 |
"step": 1960
|
| 3539 |
+
},
|
| 3540 |
+
{
|
| 3541 |
+
"epoch": 15.115384615384615,
|
| 3542 |
+
"grad_norm": 0.0,
|
| 3543 |
+
"learning_rate": 4.018e-05,
|
| 3544 |
+
"loss": 1.7608,
|
| 3545 |
+
"mean_token_accuracy": 0.6430147528648377,
|
| 3546 |
+
"num_tokens": 7165688.0,
|
| 3547 |
+
"step": 1965
|
| 3548 |
+
},
|
| 3549 |
+
{
|
| 3550 |
+
"epoch": 15.153846153846153,
|
| 3551 |
+
"grad_norm": 0.0,
|
| 3552 |
+
"learning_rate": 4.0155000000000004e-05,
|
| 3553 |
+
"loss": 1.768,
|
| 3554 |
+
"mean_token_accuracy": 0.6483392864465714,
|
| 3555 |
+
"num_tokens": 7183723.0,
|
| 3556 |
+
"step": 1970
|
| 3557 |
}
|
| 3558 |
],
|
| 3559 |
"logging_steps": 5,
|
|
|
|
| 3573 |
"attributes": {}
|
| 3574 |
}
|
| 3575 |
},
|
| 3576 |
+
"total_flos": 3.639183100408627e+17,
|
| 3577 |
"train_batch_size": 4,
|
| 3578 |
"trial_name": null,
|
| 3579 |
"trial_params": null
|