N_roberta_twitterfin_padding70model

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

• Loss: 0.9264
• Accuracy: 0.9037

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
0.524	1.0	597	0.2917	0.8890
0.3083	2.0	1194	0.2611	0.9041
0.253	3.0	1791	0.3960	0.8978
0.1889	4.0	2388	0.4370	0.8970
0.1575	5.0	2985	0.5243	0.8928
0.085	6.0	3582	0.5498	0.9037
0.0811	7.0	4179	0.6695	0.8961
0.0522	8.0	4776	0.6968	0.8924
0.0572	9.0	5373	0.7942	0.8886
0.0563	10.0	5970	0.7870	0.9028
0.0232	11.0	6567	0.7952	0.8991
0.0284	12.0	7164	0.8252	0.8995
0.0279	13.0	7761	0.8004	0.8957
0.0216	14.0	8358	0.8555	0.9020
0.0083	15.0	8955	0.8454	0.9016
0.0098	16.0	9552	0.9108	0.8945
0.0113	17.0	10149	0.9306	0.8991
0.0105	18.0	10746	0.8678	0.9070
0.0045	19.0	11343	0.9016	0.9070
0.0037	20.0	11940	0.9264	0.9037

Framework versions

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