N_bert_twitterfin_padding70model

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: 1.0123
• Accuracy: 0.8874

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
0.6186	1.0	597	0.3664	0.8647
0.3355	2.0	1194	0.3325	0.8844
0.2398	3.0	1791	0.4079	0.8857
0.1511	4.0	2388	0.5350	0.8911
0.1077	5.0	2985	0.6086	0.8853
0.0367	6.0	3582	0.6945	0.8890
0.0368	7.0	4179	0.7918	0.8844
0.0283	8.0	4776	0.7927	0.8915
0.0236	9.0	5373	0.7818	0.8932
0.0204	10.0	5970	0.8325	0.8932
0.0168	11.0	6567	0.8979	0.8844
0.0101	12.0	7164	0.9055	0.8890
0.0088	13.0	7761	0.8781	0.8936
0.0054	14.0	8358	0.9046	0.8932
0.0062	15.0	8955	0.8997	0.8966
0.0037	16.0	9552	0.9535	0.8903
0.003	17.0	10149	0.9728	0.8915
0.0022	18.0	10746	1.0253	0.8869
0.0017	19.0	11343	1.0170	0.8890
0.0037	20.0	11940	1.0123	0.8874

Framework versions

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