cat_2_classifier

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

• Loss: 1.4909
• Accuracy: 0.8231

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
0.8619	1.0	1489	0.6702	0.7819
0.6055	2.0	2978	0.5732	0.8031
0.4928	3.0	4467	0.5505	0.8209
0.397	4.0	5956	0.5604	0.8125
0.3121	5.0	7445	0.6099	0.8262
0.2427	6.0	8934	0.6541	0.8152
0.1971	7.0	10423	0.7778	0.8193
0.1408	8.0	11912	0.8617	0.8246
0.1259	9.0	13401	0.9893	0.8141
0.0889	10.0	14890	1.0761	0.8201
0.0619	11.0	16379	1.1579	0.8171
0.0615	12.0	17868	1.2634	0.8243
0.0443	13.0	19357	1.2942	0.8197
0.042	14.0	20846	1.4132	0.8175
0.0259	15.0	22335	1.3641	0.8205
0.0228	16.0	23824	1.4526	0.8186
0.0208	17.0	25313	1.4841	0.8280
0.0123	18.0	26802	1.4679	0.8239
0.0101	19.0	28291	1.5019	0.8269
0.0099	20.0	29780	1.4909	0.8231

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1