Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +87 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 1780,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.6671270718232044,
|
| 13 |
+
"eval_auc": 0.8569681026713354,
|
| 14 |
+
"eval_f1": 0.6135910212256817,
|
| 15 |
+
"eval_loss": 0.801713228225708,
|
| 16 |
+
"eval_runtime": 2.2511,
|
| 17 |
+
"eval_samples_per_second": 643.232,
|
| 18 |
+
"eval_steps_per_second": 40.424,
|
| 19 |
+
"step": 445
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 1.12,
|
| 23 |
+
"learning_rate": 8.203410220458389e-06,
|
| 24 |
+
"loss": 0.9006,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"eval_accuracy": 0.6740331491712708,
|
| 30 |
+
"eval_auc": 0.8628486862082239,
|
| 31 |
+
"eval_f1": 0.6196832877481853,
|
| 32 |
+
"eval_loss": 0.8145365715026855,
|
| 33 |
+
"eval_runtime": 2.3359,
|
| 34 |
+
"eval_samples_per_second": 619.899,
|
| 35 |
+
"eval_steps_per_second": 38.958,
|
| 36 |
+
"step": 890
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.25,
|
| 40 |
+
"learning_rate": 4.0787012285802695e-06,
|
| 41 |
+
"loss": 0.6203,
|
| 42 |
+
"step": 1000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_accuracy": 0.6678176795580111,
|
| 47 |
+
"eval_auc": 0.8647304774970923,
|
| 48 |
+
"eval_f1": 0.6165706484778348,
|
| 49 |
+
"eval_loss": 0.9743533730506897,
|
| 50 |
+
"eval_runtime": 2.2727,
|
| 51 |
+
"eval_samples_per_second": 637.138,
|
| 52 |
+
"eval_steps_per_second": 40.041,
|
| 53 |
+
"step": 1335
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.37,
|
| 57 |
+
"learning_rate": 6.193171389152996e-07,
|
| 58 |
+
"loss": 0.4125,
|
| 59 |
+
"step": 1500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_accuracy": 0.664364640883978,
|
| 64 |
+
"eval_auc": 0.8620308629559635,
|
| 65 |
+
"eval_f1": 0.6208186150187146,
|
| 66 |
+
"eval_loss": 1.013535976409912,
|
| 67 |
+
"eval_runtime": 2.2778,
|
| 68 |
+
"eval_samples_per_second": 635.708,
|
| 69 |
+
"eval_steps_per_second": 39.951,
|
| 70 |
+
"step": 1780
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 4.0,
|
| 74 |
+
"step": 1780,
|
| 75 |
+
"total_flos": 5624274750874848.0,
|
| 76 |
+
"train_loss": 0.5952618631084313,
|
| 77 |
+
"train_runtime": 315.5628,
|
| 78 |
+
"train_samples_per_second": 90.226,
|
| 79 |
+
"train_steps_per_second": 5.641
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"max_steps": 1780,
|
| 83 |
+
"num_train_epochs": 4,
|
| 84 |
+
"total_flos": 5624274750874848.0,
|
| 85 |
+
"trial_name": null,
|
| 86 |
+
"trial_params": null
|
| 87 |
+
}
|