distilbert-base-uncased-finetuned-adl_hw1

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: 0.2325
• Accuracy: 0.0003

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
4.2678	1.0	938	1.5396	0.0
0.9511	2.0	1876	0.3407	0.0
0.16	3.0	2814	0.2027	0.0
0.0492	4.0	3752	0.1910	0.0
0.0227	5.0	4690	0.1803	0.0
0.0142	6.0	5628	0.2025	0.0
0.014	7.0	6566	0.2010	0.0
0.0064	8.0	7504	0.2267	0.0
0.0076	9.0	8442	0.2312	0.0
0.0065	10.0	9380	0.2257	0.0
0.0051	11.0	10318	0.2285	0.0
0.003	12.0	11256	0.2325	0.0003
0.0031	13.0	12194	0.2582	0.0
0.0009	14.0	13132	0.2445	0.0
0.0012	15.0	14070	0.2511	0.0
0.0006	16.0	15008	0.2568	0.0
0.0002	17.0	15946	0.2586	0.0
0.0002	18.0	16884	0.2620	0.0
0.0001	19.0	17822	0.2606	0.0
0.0001	20.0	18760	0.2631	0.0

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1