bert_twitterfin_padding20model

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: 1.0153
• Accuracy: 0.8865

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
0.6193	1.0	597	0.3863	0.8597
0.3289	2.0	1194	0.3259	0.8765
0.2266	3.0	1791	0.4277	0.8790
0.1408	4.0	2388	0.5860	0.8827
0.0999	5.0	2985	0.6335	0.8823
0.0371	6.0	3582	0.7146	0.8882
0.0368	7.0	4179	0.7644	0.8794
0.0326	8.0	4776	0.7843	0.8840
0.0211	9.0	5373	0.8496	0.8794
0.0246	10.0	5970	0.8321	0.8865
0.0146	11.0	6567	0.8637	0.8786
0.0094	12.0	7164	0.9359	0.8844
0.0149	13.0	7761	0.8658	0.8857
0.0077	14.0	8358	0.9680	0.8840
0.0065	15.0	8955	0.9877	0.8903
0.0038	16.0	9552	0.9742	0.8827
0.0031	17.0	10149	0.9920	0.8861
0.0017	18.0	10746	1.0075	0.8903
0.0037	19.0	11343	1.0174	0.8857
0.0008	20.0	11940	1.0153	0.8865

Framework versions

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