Upload trainer_state.json
Browse files- trainer_state.json +139 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2500,
|
| 3 |
+
"best_metric": 0.9573901464713716,
|
| 4 |
+
"best_model_checkpoint": "C:\\Users\\Daniel\\Desktop\\GitHub\\NLPinitiative\\models\\dlsmallw\\NLPinitiative-Binary-Classification\\checkpoint-2500",
|
| 5 |
+
"epoch": 2.7203482045701852,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.544069640914037,
|
| 14 |
+
"grad_norm": 17.53396987915039,
|
| 15 |
+
"learning_rate": 1.637286906057309e-05,
|
| 16 |
+
"loss": 0.2811,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.544069640914037,
|
| 21 |
+
"eval_accuracy": 0.949238578680203,
|
| 22 |
+
"eval_auprc": 0.2945266340168414,
|
| 23 |
+
"eval_auroc": 0.015546624960699109,
|
| 24 |
+
"eval_f1": 0.946914399469144,
|
| 25 |
+
"eval_loss": 0.19298532605171204,
|
| 26 |
+
"eval_precision": 0.9564343163538874,
|
| 27 |
+
"eval_recall": 0.9375821287779238,
|
| 28 |
+
"eval_runtime": 102.1508,
|
| 29 |
+
"eval_samples_per_second": 30.856,
|
| 30 |
+
"eval_steps_per_second": 3.857,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.088139281828074,
|
| 35 |
+
"grad_norm": 1.0602138042449951,
|
| 36 |
+
"learning_rate": 1.2745738121146174e-05,
|
| 37 |
+
"loss": 0.1844,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.088139281828074,
|
| 42 |
+
"eval_accuracy": 0.9530456852791879,
|
| 43 |
+
"eval_auprc": 0.29439297154104793,
|
| 44 |
+
"eval_auroc": 0.013553767645090812,
|
| 45 |
+
"eval_f1": 0.9514435695538058,
|
| 46 |
+
"eval_loss": 0.19708991050720215,
|
| 47 |
+
"eval_precision": 0.9501965923984272,
|
| 48 |
+
"eval_recall": 0.9526938239159002,
|
| 49 |
+
"eval_runtime": 104.1259,
|
| 50 |
+
"eval_samples_per_second": 30.271,
|
| 51 |
+
"eval_steps_per_second": 3.784,
|
| 52 |
+
"step": 1000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.632208922742111,
|
| 56 |
+
"grad_norm": 0.019807865843176842,
|
| 57 |
+
"learning_rate": 9.11860718171926e-06,
|
| 58 |
+
"loss": 0.0806,
|
| 59 |
+
"step": 1500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.632208922742111,
|
| 63 |
+
"eval_accuracy": 0.9568527918781726,
|
| 64 |
+
"eval_auprc": 0.29427235149466713,
|
| 65 |
+
"eval_auroc": 0.011200752964697724,
|
| 66 |
+
"eval_f1": 0.9545758183032732,
|
| 67 |
+
"eval_loss": 0.23076476156711578,
|
| 68 |
+
"eval_precision": 0.9707880434782609,
|
| 69 |
+
"eval_recall": 0.9388961892247043,
|
| 70 |
+
"eval_runtime": 103.9447,
|
| 71 |
+
"eval_samples_per_second": 30.324,
|
| 72 |
+
"eval_steps_per_second": 3.79,
|
| 73 |
+
"step": 1500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.176278563656148,
|
| 77 |
+
"grad_norm": 0.047856587916612625,
|
| 78 |
+
"learning_rate": 5.491476242292347e-06,
|
| 79 |
+
"loss": 0.0743,
|
| 80 |
+
"step": 2000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.176278563656148,
|
| 84 |
+
"eval_accuracy": 0.9517766497461929,
|
| 85 |
+
"eval_auprc": 0.2942364000520487,
|
| 86 |
+
"eval_auroc": 0.010148496892206732,
|
| 87 |
+
"eval_f1": 0.9500984898227183,
|
| 88 |
+
"eval_loss": 0.2236114740371704,
|
| 89 |
+
"eval_precision": 0.949475065616798,
|
| 90 |
+
"eval_recall": 0.9507227332457293,
|
| 91 |
+
"eval_runtime": 100.9487,
|
| 92 |
+
"eval_samples_per_second": 31.224,
|
| 93 |
+
"eval_steps_per_second": 3.903,
|
| 94 |
+
"step": 2000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 2.7203482045701852,
|
| 98 |
+
"grad_norm": 0.010896860621869564,
|
| 99 |
+
"learning_rate": 1.8643453028654336e-06,
|
| 100 |
+
"loss": 0.0256,
|
| 101 |
+
"step": 2500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.7203482045701852,
|
| 105 |
+
"eval_accuracy": 0.9593908629441624,
|
| 106 |
+
"eval_auprc": 0.29418955133811675,
|
| 107 |
+
"eval_auroc": 0.009661165886023393,
|
| 108 |
+
"eval_f1": 0.9573901464713716,
|
| 109 |
+
"eval_loss": 0.21993429958820343,
|
| 110 |
+
"eval_precision": 0.970310391363023,
|
| 111 |
+
"eval_recall": 0.9448094612352168,
|
| 112 |
+
"eval_runtime": 100.9275,
|
| 113 |
+
"eval_samples_per_second": 31.23,
|
| 114 |
+
"eval_steps_per_second": 3.904,
|
| 115 |
+
"step": 2500
|
| 116 |
+
}
|
| 117 |
+
],
|
| 118 |
+
"logging_steps": 500,
|
| 119 |
+
"max_steps": 2757,
|
| 120 |
+
"num_input_tokens_seen": 0,
|
| 121 |
+
"num_train_epochs": 3,
|
| 122 |
+
"save_steps": 500,
|
| 123 |
+
"stateful_callbacks": {
|
| 124 |
+
"TrainerControl": {
|
| 125 |
+
"args": {
|
| 126 |
+
"should_epoch_stop": false,
|
| 127 |
+
"should_evaluate": false,
|
| 128 |
+
"should_log": false,
|
| 129 |
+
"should_save": true,
|
| 130 |
+
"should_training_stop": false
|
| 131 |
+
},
|
| 132 |
+
"attributes": {}
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
+
"total_flos": 1315555276800000.0,
|
| 136 |
+
"train_batch_size": 8,
|
| 137 |
+
"trial_name": null,
|
| 138 |
+
"trial_params": null
|
| 139 |
+
}
|