N_roberta_twitterfin_padding80model

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

• Loss: 0.9104
• Accuracy: 0.9045

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
0.5492	1.0	597	0.3187	0.8848
0.3028	2.0	1194	0.2528	0.9054
0.2565	3.0	1791	0.3721	0.8907
0.1877	4.0	2388	0.4450	0.8991
0.1604	5.0	2985	0.5126	0.8953
0.0864	6.0	3582	0.6042	0.8987
0.068	7.0	4179	0.7240	0.8953
0.0497	8.0	4776	0.7586	0.8991
0.0459	9.0	5373	0.7846	0.9020
0.0483	10.0	5970	0.7701	0.9008
0.0319	11.0	6567	0.8474	0.8920
0.0244	12.0	7164	0.7441	0.9054
0.022	13.0	7761	0.7594	0.9079
0.0226	14.0	8358	0.8739	0.9037
0.0165	15.0	8955	0.8453	0.9020
0.0093	16.0	9552	0.8394	0.9020
0.0092	17.0	10149	0.8803	0.9054
0.0088	18.0	10746	0.9146	0.9045
0.0028	19.0	11343	0.9085	0.9020
0.0034	20.0	11940	0.9104	0.9045

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3