Training in progress, step 3650, 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 sha256:8eec73b30e13ab97f26d12e86d864478fd64b7c7c18c5a472871f9ce2d7e484e
|
| 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 sha256:54a4982669449d1a65097b4ca10d08f587ab9668cfed2459c31ef57d7bf3ffd7
|
| 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 sha256:2550686ca12c289d016d5a3b807eea016a3ecb9a1f256fc96189b651d41409ec
|
| 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:c85aa0a64ea3b5e4cf74c3c3bddea266230518b8ebbe06f5c2504563745ab0d1
|
| 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,
|
|
@@ -3658,6 +3658,16 @@
|
|
| 3658 |
"mean_token_accuracy": 0.7644057601690293,
|
| 3659 |
"num_tokens": 16939640.0,
|
| 3660 |
"step": 3640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3661 |
}
|
| 3662 |
],
|
| 3663 |
"logging_steps": 10,
|
|
@@ -3677,7 +3687,7 @@
|
|
| 3677 |
"attributes": {}
|
| 3678 |
}
|
| 3679 |
},
|
| 3680 |
-
"total_flos": 8.
|
| 3681 |
"train_batch_size": 4,
|
| 3682 |
"trial_name": null,
|
| 3683 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7786666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3658 |
"mean_token_accuracy": 0.7644057601690293,
|
| 3659 |
"num_tokens": 16939640.0,
|
| 3660 |
"step": 3640
|
| 3661 |
+
},
|
| 3662 |
+
{
|
| 3663 |
+
"entropy": 1.0231108613312245,
|
| 3664 |
+
"epoch": 0.7786666666666666,
|
| 3665 |
+
"grad_norm": 0.23233352601528168,
|
| 3666 |
+
"learning_rate": 7.000215478924887e-05,
|
| 3667 |
+
"loss": 1.1309197425842286,
|
| 3668 |
+
"mean_token_accuracy": 0.744163216650486,
|
| 3669 |
+
"num_tokens": 16999652.0,
|
| 3670 |
+
"step": 3650
|
| 3671 |
}
|
| 3672 |
],
|
| 3673 |
"logging_steps": 10,
|
|
|
|
| 3687 |
"attributes": {}
|
| 3688 |
}
|
| 3689 |
},
|
| 3690 |
+
"total_flos": 8.052271378002432e+16,
|
| 3691 |
"train_batch_size": 4,
|
| 3692 |
"trial_name": null,
|
| 3693 |
"trial_params": null
|