roberta_twitterfin_padding0model

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8513
• Accuracy: 0.9125

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: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4832	1.0	597	0.3170	0.8848
0.2872	2.0	1194	0.2886	0.8974
0.232	3.0	1791	0.4198	0.8903
0.17	4.0	2388	0.4127	0.8982
0.1468	5.0	2985	0.4876	0.8899
0.0703	6.0	3582	0.5594	0.8991
0.0721	7.0	4179	0.6904	0.9012
0.0555	8.0	4776	0.7335	0.8907
0.0458	9.0	5373	0.7312	0.8978
0.0409	10.0	5970	0.7976	0.8982
0.0302	11.0	6567	0.7327	0.9012
0.0228	12.0	7164	0.7153	0.9058
0.021	13.0	7761	0.7794	0.9041
0.0156	14.0	8358	0.8214	0.9028
0.0198	15.0	8955	0.7953	0.9079
0.0096	16.0	9552	0.8087	0.9095
0.0112	17.0	10149	0.8202	0.9112
0.0083	18.0	10746	0.8334	0.9129
0.0071	19.0	11343	0.8517	0.9112
0.0019	20.0	11940	0.8513	0.9125

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.1
• Datasets 2.12.0
• Tokenizers 0.13.3