llama3_false_positives_0609_KTO_hp_screening

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

• Loss: 0.6200
• Eval/rewards/chosen: 0.1376
• Eval/logps/chosen: -196.7612
• Eval/rewards/rejected: 0.1472
• Eval/logps/rejected: -209.5413
• Eval/rewards/margins: -0.0096
• Eval/kl: 1.2612

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: 1
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 4.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4989	0.96	12	0.6223	0.2616
0.6212	2.0	25	0.6215	0.8164
0.4973	2.96	37	0.6192	1.2270
0.7188	3.84	48	0.6200	1.2612

Framework versions

• PEFT 0.11.1
• Transformers 4.44.0
• Pytorch 2.2.0
• Datasets 2.20.0
• Tokenizers 0.19.1