bert_twitterfin_padding100model

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: 1.0383
• Accuracy: 0.8869

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
0.6101	1.0	597	0.3786	0.8618
0.3341	2.0	1194	0.3280	0.8781
0.23	3.0	1791	0.4172	0.8781
0.138	4.0	2388	0.5795	0.8844
0.1119	5.0	2985	0.6322	0.8807
0.0504	6.0	3582	0.7185	0.8798
0.0374	7.0	4179	0.7900	0.8786
0.0371	8.0	4776	0.7836	0.8790
0.0256	9.0	5373	0.7867	0.8832
0.0232	10.0	5970	0.8910	0.8861
0.0228	11.0	6567	0.8978	0.8832
0.0134	12.0	7164	0.8992	0.8840
0.0086	13.0	7761	0.9213	0.8903
0.0123	14.0	8358	0.9328	0.8899
0.0055	15.0	8955	0.9661	0.8869
0.0028	16.0	9552	0.9949	0.8899
0.0029	17.0	10149	1.0184	0.8857
0.0046	18.0	10746	1.0291	0.8890
0.0014	19.0	11343	1.0393	0.8878
0.0015	20.0	11940	1.0383	0.8869

Framework versions

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