metadata

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

UIT-xlnet-large-cased-finetuned

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

Loss: 0.7374
F1: 0.7190
Roc Auc: 0.7861
Accuracy: 0.4368

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.6144	1.0	139	0.5899	0.0858	0.5045	0.1245
0.55	2.0	278	0.5547	0.2409	0.5430	0.1625
0.5049	3.0	417	0.4514	0.5298	0.6834	0.3574
0.4	4.0	556	0.4586	0.5030	0.6732	0.3538
0.3206	5.0	695	0.4345	0.6371	0.7279	0.3827
0.2969	6.0	834	0.4264	0.6807	0.7627	0.4170
0.2036	7.0	973	0.4564	0.6871	0.7633	0.4495
0.1986	8.0	1112	0.4918	0.6930	0.7632	0.4170
0.1437	9.0	1251	0.5499	0.7021	0.7861	0.3953
0.1066	10.0	1390	0.5774	0.7028	0.7725	0.4224
0.0674	11.0	1529	0.6038	0.7145	0.7824	0.4585
0.038	12.0	1668	0.6528	0.7020	0.7797	0.4458
0.0341	13.0	1807	0.6681	0.7092	0.7781	0.4477
0.0308	14.0	1946	0.6986	0.7085	0.7796	0.4260
0.0109	15.0	2085	0.7297	0.7087	0.7796	0.4332
0.0224	16.0	2224	0.7307	0.7156	0.7838	0.4440
0.0097	17.0	2363	0.7358	0.7155	0.7816	0.4440
0.0103	18.0	2502	0.7374	0.7190	0.7861	0.4368
0.0116	19.0	2641	0.7381	0.7150	0.7829	0.4368
0.0077	20.0	2780	0.7383	0.7130	0.7817	0.4350

Framework versions

Transformers 4.48.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.21.0