distilbert-base-uncased-lora-text-classification

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: 2.1159
• Accuracy: 0.8148
• F1: 0.8147
• Precision: 0.8148
• Recall: 0.8148

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: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	81	1.3621	0.8148	0.8137	0.8189	0.8148
No log	2.0	162	0.9435	0.8272	0.8272	0.8283	0.8272
No log	3.0	243	1.3333	0.7778	0.7778	0.7789	0.7778
No log	4.0	324	1.4928	0.8395	0.8388	0.8509	0.8395
No log	5.0	405	1.7831	0.8025	0.8022	0.8028	0.8025
No log	6.0	486	2.2104	0.8148	0.8137	0.8189	0.8148
0.1214	7.0	567	1.9896	0.8025	0.8022	0.8028	0.8025
0.1214	8.0	648	2.0504	0.8148	0.8147	0.8148	0.8148
0.1214	9.0	729	2.1091	0.8148	0.8147	0.8148	0.8148
0.1214	10.0	810	2.1159	0.8148	0.8147	0.8148	0.8148

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0