Training in progress, step 4260, 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 sha256:074aa9aaccb98345eb52686ad76207bfee353f5ef7519f9424f732378fdcbe60
|
| 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:eb8920681d3919ca75d452cfafe70190c308a3d0741e273666640e694b56e26a
|
| 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:ff4bdf4d0831dd27700fbd52d872ba87c517320ec136e3bed18706b88fed80f6
|
| 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,
|
|
@@ -7658,6 +7658,24 @@
|
|
| 7658 |
"mean_token_accuracy": 0.6517602205276489,
|
| 7659 |
"num_tokens": 15502102.0,
|
| 7660 |
"step": 4250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7661 |
}
|
| 7662 |
],
|
| 7663 |
"logging_steps": 5,
|
|
@@ -7677,7 +7695,7 @@
|
|
| 7677 |
"attributes": {}
|
| 7678 |
}
|
| 7679 |
},
|
| 7680 |
-
"total_flos": 7.
|
| 7681 |
"train_batch_size": 4,
|
| 7682 |
"trial_name": null,
|
| 7683 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7658 |
"mean_token_accuracy": 0.6517602205276489,
|
| 7659 |
"num_tokens": 15502102.0,
|
| 7660 |
"step": 4250
|
| 7661 |
+
},
|
| 7662 |
+
{
|
| 7663 |
+
"epoch": 32.73076923076923,
|
| 7664 |
+
"grad_norm": 0.0,
|
| 7665 |
+
"learning_rate": 2.873e-05,
|
| 7666 |
+
"loss": 1.7375,
|
| 7667 |
+
"mean_token_accuracy": 0.6485500365495682,
|
| 7668 |
+
"num_tokens": 15520198.0,
|
| 7669 |
+
"step": 4255
|
| 7670 |
+
},
|
| 7671 |
+
{
|
| 7672 |
+
"epoch": 32.76923076923077,
|
| 7673 |
+
"grad_norm": 0.0,
|
| 7674 |
+
"learning_rate": 2.8705000000000004e-05,
|
| 7675 |
+
"loss": 1.7885,
|
| 7676 |
+
"mean_token_accuracy": 0.641147717833519,
|
| 7677 |
+
"num_tokens": 15538006.0,
|
| 7678 |
+
"step": 4260
|
| 7679 |
}
|
| 7680 |
],
|
| 7681 |
"logging_steps": 5,
|
|
|
|
| 7695 |
"attributes": {}
|
| 7696 |
}
|
| 7697 |
},
|
| 7698 |
+
"total_flos": 7.875351973807718e+17,
|
| 7699 |
"train_batch_size": 4,
|
| 7700 |
"trial_name": null,
|
| 7701 |
"trial_params": null
|