th_cl_18epochs_lora_pos_neg

This model is a fine-tuned version of gradientai/Llama-3-8B-Instruct-262k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0601
• Balanced Accuracy: 0.515
• Accuracy: 0.5111

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Balanced Accuracy	Accuracy
No log	1.0	32	1.0156	0.4939	0.4889
No log	2.0	64	0.9877	0.4939	0.4889
No log	3.0	96	0.9764	0.5504	0.5556
No log	4.0	128	1.0566	0.5741	0.5778
No log	5.0	160	1.0601	0.515	0.5111

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1