distilBERT_without_preprocessing_grid_search

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: 0.6731
• Precision: 0.8400
• Recall: 0.8427
• F1: 0.8407
• Accuracy: 0.8779

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	257	0.6542	0.7446	0.8052	0.7657	0.8350
0.8635	2.0	514	0.5548	0.7961	0.8277	0.8056	0.8540
0.8635	3.0	771	0.4839	0.7912	0.8427	0.8115	0.8589
0.3097	4.0	1028	0.5256	0.8148	0.8544	0.8315	0.8667
0.3097	5.0	1285	0.5657	0.8346	0.8494	0.8413	0.8764
0.1839	6.0	1542	0.6005	0.8208	0.8430	0.8304	0.8710
0.1839	7.0	1799	0.6580	0.8319	0.8349	0.8314	0.8706
0.1254	8.0	2056	0.6348	0.8342	0.8515	0.8423	0.8774
0.1254	9.0	2313	0.6601	0.8314	0.8394	0.8348	0.8745
0.0935	10.0	2570	0.6731	0.8400	0.8427	0.8407	0.8779

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3