Training in progress, step 3790, 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 sha256:38de148b42235201b6f25e82304ce8313ab40648d17c6d2773a002faf625cfb2
|
| 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 sha256:17e147d862df4e75cb4a34bfc407d6115443fcf13052e77ce4269ec3ecb3a800
|
| 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 sha256:4b08ed07c30748809e170fd825eca3191e635e294121c3c9b7fbbf0d0e06fd62
|
| 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 sha256:8bd6961a16775d2dfd539e613859a399e48d4390d84444f6f9175e36534a47b5
|
| 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,
|
|
@@ -3798,6 +3798,16 @@
|
|
| 3798 |
"mean_token_accuracy": 0.774232342839241,
|
| 3799 |
"num_tokens": 17611723.0,
|
| 3800 |
"step": 3780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3801 |
}
|
| 3802 |
],
|
| 3803 |
"logging_steps": 10,
|
|
@@ -3817,7 +3827,7 @@
|
|
| 3817 |
"attributes": {}
|
| 3818 |
}
|
| 3819 |
},
|
| 3820 |
-
"total_flos": 8.
|
| 3821 |
"train_batch_size": 4,
|
| 3822 |
"trial_name": null,
|
| 3823 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8085333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3798 |
"mean_token_accuracy": 0.774232342839241,
|
| 3799 |
"num_tokens": 17611723.0,
|
| 3800 |
"step": 3780
|
| 3801 |
+
},
|
| 3802 |
+
{
|
| 3803 |
+
"entropy": 0.9692328073084354,
|
| 3804 |
+
"epoch": 0.8085333333333333,
|
| 3805 |
+
"grad_norm": 0.24602019786834717,
|
| 3806 |
+
"learning_rate": 6.775887153189233e-05,
|
| 3807 |
+
"loss": 1.06738224029541,
|
| 3808 |
+
"mean_token_accuracy": 0.7612074792385102,
|
| 3809 |
+
"num_tokens": 17657838.0,
|
| 3810 |
+
"step": 3790
|
| 3811 |
}
|
| 3812 |
],
|
| 3813 |
"logging_steps": 10,
|
|
|
|
| 3827 |
"attributes": {}
|
| 3828 |
}
|
| 3829 |
},
|
| 3830 |
+
"total_flos": 8.36086750049833e+16,
|
| 3831 |
"train_batch_size": 4,
|
| 3832 |
"trial_name": null,
|
| 3833 |
"trial_params": null
|