llama3_false_positives_1609_KTO_optimised_model

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: 0.5894
• Eval/rewards/chosen: 2.7219
• Eval/logps/chosen: -170.9184
• Eval/rewards/rejected: 2.5085
• Eval/logps/rejected: -185.9287
• Eval/rewards/margins: 0.2134
• Eval/kl: 25.1066

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: 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: 6.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4841	0.96	12	0.6000	13.4542
0.1395	2.0	25	0.5894	25.1066

Framework versions

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