Training in progress, step 3670, 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 sha256:77dd33d15ee1608e4a5d147de3871a9866f8aa8a166d045974da6f84f60efed7
|
| 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 sha256:0d6dd7374734ad7f66c91cd50e6b708c0c972ff900882a7beba0e0da0fcfe0c4
|
| 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 sha256:1bd3568fe11d8bbd83db97bd2d933c20fb36cb00dbf6e65d2005ff6b18675421
|
| 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 sha256:15a622b62caf72c6314589492b96800f0c8c29744716f35a900e0f0317b58e2d
|
| 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,
|
|
@@ -3678,6 +3678,16 @@
|
|
| 3678 |
"mean_token_accuracy": 0.7736709147691727,
|
| 3679 |
"num_tokens": 17046141.0,
|
| 3680 |
"step": 3660
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3681 |
}
|
| 3682 |
],
|
| 3683 |
"logging_steps": 10,
|
|
@@ -3697,7 +3707,7 @@
|
|
| 3697 |
"attributes": {}
|
| 3698 |
}
|
| 3699 |
},
|
| 3700 |
-
"total_flos": 8.
|
| 3701 |
"train_batch_size": 4,
|
| 3702 |
"trial_name": null,
|
| 3703 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7829333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3670,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3678 |
"mean_token_accuracy": 0.7736709147691727,
|
| 3679 |
"num_tokens": 17046141.0,
|
| 3680 |
"step": 3660
|
| 3681 |
+
},
|
| 3682 |
+
{
|
| 3683 |
+
"entropy": 1.0374766498804093,
|
| 3684 |
+
"epoch": 0.7829333333333334,
|
| 3685 |
+
"grad_norm": 0.2597425878047943,
|
| 3686 |
+
"learning_rate": 6.968443934771933e-05,
|
| 3687 |
+
"loss": 1.1429466247558593,
|
| 3688 |
+
"mean_token_accuracy": 0.7515291333198547,
|
| 3689 |
+
"num_tokens": 17096136.0,
|
| 3690 |
+
"step": 3670
|
| 3691 |
}
|
| 3692 |
],
|
| 3693 |
"logging_steps": 10,
|
|
|
|
| 3707 |
"attributes": {}
|
| 3708 |
}
|
| 3709 |
},
|
| 3710 |
+
"total_flos": 8.09674224633815e+16,
|
| 3711 |
"train_batch_size": 4,
|
| 3712 |
"trial_name": null,
|
| 3713 |
"trial_params": null
|