llama-3.1-8b-sst2-lora

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5812
• Accuracy: 0.9725
• Precision: 0.9779
• Recall: 0.9693
• F1: 0.9736

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0367	1.0000	33674	0.1889	0.9794	0.9955	0.9649	0.9800
0.0075	2.0	67349	0.1711	0.9908	0.9956	0.9868	0.9912
0.1737	3.0000	101023	0.2529	0.9633	0.9953	0.9342	0.9638
0.0006	4.0	134698	0.3349	0.9725	0.9737	0.9737	0.9737
0.0325	5.0000	168372	0.2762	0.9702	0.9778	0.9649	0.9713
0.0005	6.0	202047	0.3221	0.9748	0.9738	0.9781	0.9759
0.0	7.0000	235721	0.3101	0.9748	0.9822	0.9693	0.9757
0.0	8.0	269396	0.3646	0.9771	0.9823	0.9737	0.9780
0.0	9.0000	303070	0.4815	0.9725	0.9821	0.9649	0.9735
0.0	9.9999	336740	0.5812	0.9725	0.9779	0.9693	0.9736

Framework versions

• PEFT 0.15.0
• Transformers 4.44.2
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1