Output_llama2_70-15-15_new

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6310
• Accuracy: 0.6474
• Precision: 0.6760
• Recall: 0.6474
• F1: 0.6376

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: 1e-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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	46	0.7791	0.4808	0.2311	0.4808	0.3122
No log	2.0	92	0.7556	0.4872	0.7519	0.4872	0.3262
No log	3.0	138	0.7071	0.5064	0.5708	0.5064	0.4086
No log	4.0	184	0.7045	0.5	0.5549	0.5	0.3971
No log	5.0	230	0.6714	0.5705	0.6227	0.5705	0.5340
No log	6.0	276	0.6976	0.4936	0.5303	0.4936	0.3932
No log	7.0	322	0.6453	0.6603	0.6906	0.6603	0.6507
No log	8.0	368	0.6640	0.5769	0.6429	0.5769	0.5354
No log	9.0	414	0.6460	0.6154	0.6643	0.6154	0.5928
No log	10.0	460	0.6310	0.6474	0.6760	0.6474	0.6376

Framework versions

• PEFT 0.10.0
• Transformers 4.41.2
• Pytorch 2.3.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1