distilbert_twitterfin_padding40model

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: 1.1281
• Accuracy: 0.8744

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
0.6696	1.0	597	0.5204	0.8049
0.3995	2.0	1194	0.3527	0.8723
0.2854	3.0	1791	0.3942	0.8756
0.1921	4.0	2388	0.5487	0.8773
0.1519	5.0	2985	0.6299	0.8735
0.0632	6.0	3582	0.6852	0.8735
0.0498	7.0	4179	0.7728	0.8702
0.0446	8.0	4776	0.8638	0.8681
0.0321	9.0	5373	0.8343	0.8765
0.0339	10.0	5970	0.8881	0.8790
0.0194	11.0	6567	0.9281	0.8752
0.0106	12.0	7164	0.9799	0.8723
0.0145	13.0	7761	1.0008	0.8752
0.0121	14.0	8358	1.0437	0.8756
0.009	15.0	8955	1.0609	0.8748
0.0062	16.0	9552	1.0912	0.8719
0.0068	17.0	10149	1.1045	0.8731
0.0046	18.0	10746	1.1086	0.8735
0.0056	19.0	11343	1.1271	0.8723
0.0029	20.0	11940	1.1281	0.8744

Framework versions

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