N_bert_twitterfin_padding90model

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: 1.0260
• Accuracy: 0.8890

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
0.635	1.0	597	0.4070	0.8539
0.3588	2.0	1194	0.3219	0.8907
0.2478	3.0	1791	0.4226	0.8865
0.1539	4.0	2388	0.5291	0.8811
0.1226	5.0	2985	0.6593	0.8639
0.0441	6.0	3582	0.6809	0.8861
0.0364	7.0	4179	0.7800	0.8882
0.0343	8.0	4776	0.7629	0.8840
0.0255	9.0	5373	0.7855	0.8811
0.0191	10.0	5970	0.8804	0.8790
0.0101	11.0	6567	0.8909	0.8865
0.0083	12.0	7164	0.8889	0.8853
0.0108	13.0	7761	0.8784	0.8936
0.0122	14.0	8358	0.9470	0.8907
0.0071	15.0	8955	0.9631	0.8865
0.0044	16.0	9552	1.0000	0.8915
0.0039	17.0	10149	1.0128	0.8911
0.002	18.0	10746	1.0107	0.8903
0.0032	19.0	11343	1.0090	0.8911
0.0022	20.0	11940	1.0260	0.8890

Framework versions

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