metadata

library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: fine_tuned_main_raid
    results: []

fine_tuned_main_raid

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

Loss: 0.0407
Accuracy: 0.9922

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: 8
eval_batch_size: 8
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: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3543	0.0767	100	0.1765	0.9655
0.1516	0.1534	200	0.1955	0.9724
0.1415	0.2301	300	0.1323	0.9724
0.2002	0.3067	400	0.0993	0.9716
0.1057	0.3834	500	0.2031	0.9552
0.0734	0.4601	600	0.1010	0.9802
0.0725	0.5368	700	0.1511	0.9767
0.1326	0.6135	800	0.0607	0.9879
0.0667	0.6902	900	0.0734	0.9845
0.1132	0.7669	1000	0.0878	0.9819
0.0731	0.8436	1100	0.0694	0.9888
0.0678	0.9202	1200	0.0704	0.9853
0.0455	0.9969	1300	0.0522	0.9905
0.0656	1.0736	1400	0.0646	0.9871
0.0463	1.1503	1500	0.0407	0.9922
0.0432	1.2270	1600	0.0646	0.9897
0.0347	1.3037	1700	0.0421	0.9931
0.0361	1.3804	1800	0.0420	0.9931

Framework versions

Transformers 4.46.2
Pytorch 2.5.0+cu121
Datasets 3.1.0
Tokenizers 0.20.3