Training in progress, step 1990, 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 sha256:0b35a3553254b3a8fba61bc5704b9468d6f50ffff023b2be2be9bfc69a5b811e
|
| 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:c3f2fb8a9bfa1448f0af9cf1a42dd371ca6f433697d5bf07c0818b3bb40429b9
|
| 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:a1cd64aaac3e815d2c827214e63a947a15b901cd60a8eaa89be968b7deac4263
|
| 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,
|
|
@@ -3572,6 +3572,24 @@
|
|
| 3572 |
"mean_token_accuracy": 0.6437583029270172,
|
| 3573 |
"num_tokens": 7218897.0,
|
| 3574 |
"step": 1980
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3575 |
}
|
| 3576 |
],
|
| 3577 |
"logging_steps": 5,
|
|
@@ -3591,7 +3609,7 @@
|
|
| 3591 |
"attributes": {}
|
| 3592 |
}
|
| 3593 |
},
|
| 3594 |
-
"total_flos": 3.
|
| 3595 |
"train_batch_size": 4,
|
| 3596 |
"trial_name": null,
|
| 3597 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.307692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1990,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3572 |
"mean_token_accuracy": 0.6437583029270172,
|
| 3573 |
"num_tokens": 7218897.0,
|
| 3574 |
"step": 1980
|
| 3575 |
+
},
|
| 3576 |
+
{
|
| 3577 |
+
"epoch": 15.26923076923077,
|
| 3578 |
+
"grad_norm": 0.0,
|
| 3579 |
+
"learning_rate": 4.008e-05,
|
| 3580 |
+
"loss": 1.7186,
|
| 3581 |
+
"mean_token_accuracy": 0.6547761648893357,
|
| 3582 |
+
"num_tokens": 7236557.0,
|
| 3583 |
+
"step": 1985
|
| 3584 |
+
},
|
| 3585 |
+
{
|
| 3586 |
+
"epoch": 15.307692307692308,
|
| 3587 |
+
"grad_norm": 0.0,
|
| 3588 |
+
"learning_rate": 4.0055e-05,
|
| 3589 |
+
"loss": 1.7277,
|
| 3590 |
+
"mean_token_accuracy": 0.6466970533132553,
|
| 3591 |
+
"num_tokens": 7255192.0,
|
| 3592 |
+
"step": 1990
|
| 3593 |
}
|
| 3594 |
],
|
| 3595 |
"logging_steps": 5,
|
|
|
|
| 3609 |
"attributes": {}
|
| 3610 |
}
|
| 3611 |
},
|
| 3612 |
+
"total_flos": 3.675737235456e+17,
|
| 3613 |
"train_batch_size": 4,
|
| 3614 |
"trial_name": null,
|
| 3615 |
"trial_params": null
|