Training in progress, step 3680, 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:c110a31da32ffd213cc59e0053a9afa56351942d16adcf5eaddb709a747bdb50
|
| 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 sha256:58e5e0230eff9b5e794d7b8d1cd83bcbb85fa38445afd970234bb68dcef10fb4
|
| 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 sha256:31e58fd132b14730d384ea8fd82ae553fa932d349d08d387f8d2630fd9bd431c
|
| 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 sha256:47c397115142eeea4d4000613982af98eada11892d251ef48622f892e5a6db62
|
| 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,
|
|
@@ -3688,6 +3688,16 @@
|
|
| 3688 |
"mean_token_accuracy": 0.7515291333198547,
|
| 3689 |
"num_tokens": 17096136.0,
|
| 3690 |
"step": 3670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3691 |
}
|
| 3692 |
],
|
| 3693 |
"logging_steps": 10,
|
|
@@ -3707,7 +3717,7 @@
|
|
| 3707 |
"attributes": {}
|
| 3708 |
}
|
| 3709 |
},
|
| 3710 |
-
"total_flos": 8.
|
| 3711 |
"train_batch_size": 4,
|
| 3712 |
"trial_name": null,
|
| 3713 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7850666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3688 |
"mean_token_accuracy": 0.7515291333198547,
|
| 3689 |
"num_tokens": 17096136.0,
|
| 3690 |
"step": 3670
|
| 3691 |
+
},
|
| 3692 |
+
{
|
| 3693 |
+
"entropy": 0.974248643219471,
|
| 3694 |
+
"epoch": 0.7850666666666667,
|
| 3695 |
+
"grad_norm": 0.22508691251277924,
|
| 3696 |
+
"learning_rate": 6.952522690159861e-05,
|
| 3697 |
+
"loss": 1.0584315299987792,
|
| 3698 |
+
"mean_token_accuracy": 0.7587296038866043,
|
| 3699 |
+
"num_tokens": 17144177.0,
|
| 3700 |
+
"step": 3680
|
| 3701 |
}
|
| 3702 |
],
|
| 3703 |
"logging_steps": 10,
|
|
|
|
| 3717 |
"attributes": {}
|
| 3718 |
}
|
| 3719 |
},
|
| 3720 |
+
"total_flos": 8.119511633724826e+16,
|
| 3721 |
"train_batch_size": 4,
|
| 3722 |
"trial_name": null,
|
| 3723 |
"trial_params": null
|