distilbert-base-uncased-text-classification-v6

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2704
• F1: 0.8474

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	F1
1.3969	1.0	569	0.6767	0.4906
0.6361	2.0	1138	0.4067	0.7038
0.3966	3.0	1707	0.3094	0.7988
0.2509	4.0	2276	0.2744	0.8339
0.1678	5.0	2845	0.2704	0.8474
0.126	6.0	3414	0.2810	0.8530
0.098	7.0	3983	0.3025	0.8582
0.0722	8.0	4552	0.2982	0.8556
0.0631	9.0	5121	0.3026	0.8597
0.0581	10.0	5690	0.3059	0.8614
0.0615	11.0	6259	0.3016	0.8623
0.0567	12.0	6828	0.3108	0.8608
0.0572	13.0	7397	0.3072	0.8577
0.0469	14.0	7966	0.3147	0.8563
0.0493	15.0	8535	0.3229	0.8637
0.0477	16.0	9104	0.3183	0.8705
0.0482	17.0	9673	0.3212	0.8676
0.0442	18.0	10242	0.3193	0.8667
0.0432	19.0	10811	0.3224	0.8665
0.0409	20.0	11380	0.3220	0.8663

Framework versions

• Transformers 4.28.1
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.13.3