metadata

base_model: meta-llama/Meta-Llama-3-8B-Instruct
library_name: peft
license: llama3
tags:
  - trl
  - kto
  - generated_from_trainer
model-index:
  - name: llama3_false_positives_0609_KTO_hp_screening_seeds
    results: []

llama3_false_positives_0609_KTO_hp_screening_seeds

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: 0.7043
Eval/rewards/chosen: 2.7139
Eval/logps/chosen: -180.4410
Eval/rewards/rejected: 2.5251
Eval/logps/rejected: -196.3258
Eval/rewards/margins: 0.1888
Eval/kl: 22.1345

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: 9012
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
0.5502	0.9412	12	0.6760	8.5385
0.3996	1.9608	25	0.6791	17.9477
0.2636	2.9804	38	0.7076	21.9801
0.34	3.7647	48	0.7043	22.1345

Framework versions

PEFT 0.11.1
Transformers 4.44.0
Pytorch 2.2.0
Datasets 2.20.0
Tokenizers 0.19.1