Training in progress, step 700, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:572394f94a94bd935b57ee0625ccc1a5fe3bda7aad1df0ff6599546d461f3900
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ab61d8fdf2a3657ac71d2ade5eb62ff2b78d04e9b46f1b9e5168c5e9e047150
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccd7a7a24476cb81cd83daa9c750585ba557219d9c597aeb4cb42b9a29821e85
|
| 3 |
size 14645
|
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:eede5a83e89d96d694f8778553ecce393ab8b4ffab386dcf3ab06d145ebf21fb
|
| 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": 0.
|
| 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,
|
|
@@ -708,6 +708,16 @@
|
|
| 708 |
"mean_token_accuracy": 0.7591987878084183,
|
| 709 |
"num_tokens": 3193515.0,
|
| 710 |
"step": 690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 711 |
}
|
| 712 |
],
|
| 713 |
"logging_steps": 10,
|
|
@@ -727,7 +737,7 @@
|
|
| 727 |
"attributes": {}
|
| 728 |
}
|
| 729 |
},
|
| 730 |
-
"total_flos": 1.
|
| 731 |
"train_batch_size": 4,
|
| 732 |
"trial_name": null,
|
| 733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.14933333333333335,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 708 |
"mean_token_accuracy": 0.7591987878084183,
|
| 709 |
"num_tokens": 3193515.0,
|
| 710 |
"step": 690
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"entropy": 0.9688289143145085,
|
| 714 |
+
"epoch": 0.14933333333333335,
|
| 715 |
+
"grad_norm": 0.28721460700035095,
|
| 716 |
+
"learning_rate": 9.952389128992113e-05,
|
| 717 |
+
"loss": 1.0814785957336426,
|
| 718 |
+
"mean_token_accuracy": 0.759615159034729,
|
| 719 |
+
"num_tokens": 3242439.0,
|
| 720 |
+
"step": 700
|
| 721 |
}
|
| 722 |
],
|
| 723 |
"logging_steps": 10,
|
|
|
|
| 737 |
"attributes": {}
|
| 738 |
}
|
| 739 |
},
|
| 740 |
+
"total_flos": 1.535563844562432e+16,
|
| 741 |
"train_batch_size": 4,
|
| 742 |
"trial_name": null,
|
| 743 |
"trial_params": null
|