Training in progress, step 3710, 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 sha256:8c19cebfd097c52d8252201564a90baf66afce410053d4622b9f9203cd5b323a
|
| 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:ad92e45bed68c79521d82d462764b3510cfe038d13ab9c3f853804df03fff512
|
| 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:bb26e6ee02aadc7d8c0b2d9ff753d338ee61b3002b03febd1669b67b4ac88115
|
| 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 sha256:112424dfe1d0ba6b6bb7340e2d1c9d55d7aa639fe09b2e797e34b9a13e889a5f
|
| 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,
|
|
@@ -3718,6 +3718,16 @@
|
|
| 3718 |
"mean_token_accuracy": 0.7787635132670403,
|
| 3719 |
"num_tokens": 17235554.0,
|
| 3720 |
"step": 3700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3721 |
}
|
| 3722 |
],
|
| 3723 |
"logging_steps": 10,
|
|
@@ -3737,7 +3747,7 @@
|
|
| 3737 |
"attributes": {}
|
| 3738 |
}
|
| 3739 |
},
|
| 3740 |
-
"total_flos": 8.
|
| 3741 |
"train_batch_size": 4,
|
| 3742 |
"trial_name": null,
|
| 3743 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7914666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3718 |
"mean_token_accuracy": 0.7787635132670403,
|
| 3719 |
"num_tokens": 17235554.0,
|
| 3720 |
"step": 3700
|
| 3721 |
+
},
|
| 3722 |
+
{
|
| 3723 |
+
"entropy": 0.8578987941145897,
|
| 3724 |
+
"epoch": 0.7914666666666667,
|
| 3725 |
+
"grad_norm": 0.2751041352748871,
|
| 3726 |
+
"learning_rate": 6.904619356135484e-05,
|
| 3727 |
+
"loss": 0.9659609794616699,
|
| 3728 |
+
"mean_token_accuracy": 0.7794149458408356,
|
| 3729 |
+
"num_tokens": 17280617.0,
|
| 3730 |
+
"step": 3710
|
| 3731 |
}
|
| 3732 |
],
|
| 3733 |
"logging_steps": 10,
|
|
|
|
| 3747 |
"attributes": {}
|
| 3748 |
}
|
| 3749 |
},
|
| 3750 |
+
"total_flos": 8.182288310893978e+16,
|
| 3751 |
"train_batch_size": 4,
|
| 3752 |
"trial_name": null,
|
| 3753 |
"trial_params": null
|