cls_headline_llama3_v1

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.2617

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3038	0.2353	20	0.2961
0.2899	0.4706	40	0.2809
0.2707	0.7059	60	0.2714
0.2615	0.9412	80	0.2697
0.2357	1.1765	100	0.2707
0.2377	1.4118	120	0.2667
0.2346	1.6471	140	0.2662
0.2357	1.8824	160	0.2617

Framework versions

• PEFT 0.11.1
• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1