README.md

metadata

library_name: transformers
license: mit
base_model: xlnet-large-cased
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: PRE-xlnet-large-cased-finetuned-augmentation
    results: []

PRE-xlnet-large-cased-finetuned-augmentation

This model is a fine-tuned version of xlnet-large-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3312
• F1: 0.7328
• Roc Auc: 0.8488
• Accuracy: 0.7773

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.34	1.0	389	0.3108	0.1424	0.5799	0.5386
0.2957	2.0	778	0.2733	0.3070	0.6420	0.5637
0.2697	3.0	1167	0.2241	0.4578	0.6995	0.6525
0.2248	4.0	1556	0.1944	0.5903	0.7595	0.7239
0.1689	5.0	1945	0.1793	0.6729	0.8127	0.7561
0.1052	6.0	2334	0.1961	0.6682	0.7962	0.7600
0.0964	7.0	2723	0.2035	0.6728	0.7989	0.7613
0.0885	8.0	3112	0.2315	0.7185	0.8404	0.7593
0.0497	9.0	3501	0.2608	0.7264	0.8476	0.7593
0.0411	10.0	3890	0.2688	0.7212	0.8363	0.7831
0.0182	11.0	4279	0.3081	0.7300	0.8558	0.7709
0.0186	12.0	4668	0.3179	0.7216	0.8452	0.7754
0.0131	13.0	5057	0.3312	0.7328	0.8488	0.7773
0.0069	14.0	5446	0.3464	0.7272	0.8472	0.7716
0.0069	15.0	5835	0.3522	0.7316	0.8481	0.7793
0.0027	16.0	6224	0.3555	0.7303	0.8500	0.7773

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0