bert_twitterfin_padding80model

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

• Loss: 1.0344
• Accuracy: 0.8840

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
0.6173	1.0	597	0.3644	0.8723
0.3317	2.0	1194	0.3204	0.8815
0.235	3.0	1791	0.4381	0.8882
0.1385	4.0	2388	0.5672	0.8777
0.108	5.0	2985	0.6875	0.8748
0.0466	6.0	3582	0.7728	0.8823
0.0414	7.0	4179	0.7724	0.8869
0.0306	8.0	4776	0.7541	0.8840
0.0336	9.0	5373	0.7872	0.8907
0.0221	10.0	5970	0.8676	0.8832
0.0195	11.0	6567	0.9031	0.8811
0.01	12.0	7164	0.8561	0.8823
0.0148	13.0	7761	0.9173	0.8890
0.0093	14.0	8358	0.9178	0.8874
0.0052	15.0	8955	0.9563	0.8865
0.0046	16.0	9552	0.9723	0.8857
0.0051	17.0	10149	0.9839	0.8882
0.0029	18.0	10746	1.0261	0.8844
0.0041	19.0	11343	1.0228	0.8869
0.0023	20.0	11940	1.0344	0.8840

Framework versions

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