README.md

metadata

library_name: transformers
license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: test_model
    results: []

test_model

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

• Loss: 0.1449
• F1: 0.0
• Roc Auc: 0.5
• Accuracy: 0.8976

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: 0.001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.1509	1.0	3491	0.1449	0.0	0.5	0.8976
0.1472	2.0	6982	0.1478	0.0	0.5	0.8976
0.1454	3.0	10473	0.1532	0.0	0.5	0.8976
0.144	4.0	13964	0.1457	0.0	0.5	0.8976
0.1463	5.0	17455	0.1441	0.0	0.5	0.8976
0.1427	6.0	20946	0.1463	0.0	0.5	0.8976
0.1423	7.0	24437	0.1419	0.0	0.5	0.8976
0.143	8.0	27928	0.1428	0.0	0.5	0.8976
0.1417	9.0	31419	0.1434	0.0	0.5	0.8976
0.1485	10.0	34910	0.1443	0.0	0.5	0.8976
0.142	11.0	38401	0.1455	0.0	0.5	0.8976
0.1402	12.0	41892	0.1464	0.0	0.5	0.8976
0.1417	13.0	45383	0.1423	0.0	0.5	0.8976
0.1452	14.0	48874	0.1450	0.0	0.5	0.8976
0.1455	15.0	52365	0.1423	0.0	0.5	0.8976
0.1355	16.0	55856	0.1422	0.0	0.5	0.8976
0.1369	17.0	59347	0.1431	0.0	0.5	0.8976
0.1416	18.0	62838	0.1436	0.0	0.5	0.8976
0.1387	19.0	66329	0.1418	0.0	0.5	0.8976
0.143	20.0	69820	0.1416	0.0	0.5	0.8976

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3