N_distilbert_twitterfin_padding0model

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

• Loss: 1.0496
• Accuracy: 0.8844

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
0.5625	1.0	597	0.3936	0.8526
0.3236	2.0	1194	0.3517	0.8748
0.231	3.0	1791	0.4241	0.8794
0.1474	4.0	2388	0.5579	0.8807
0.1004	5.0	2985	0.6444	0.8848
0.0419	6.0	3582	0.7431	0.8765
0.0394	7.0	4179	0.7534	0.8790
0.0287	8.0	4776	0.7662	0.8819
0.0262	9.0	5373	0.8529	0.8819
0.0168	10.0	5970	0.8335	0.8844
0.0115	11.0	6567	0.8641	0.8823
0.0141	12.0	7164	0.9629	0.8760
0.0097	13.0	7761	0.9226	0.8844
0.0066	14.0	8358	0.9800	0.8798
0.0033	15.0	8955	0.9822	0.8844
0.0036	16.0	9552	0.9928	0.8827
0.0029	17.0	10149	1.0094	0.8857
0.0009	18.0	10746	1.0535	0.8857
0.0011	19.0	11343	1.0431	0.8815
0.0034	20.0	11940	1.0496	0.8844

Framework versions

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