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_1010_KTO_hp_screening_seeds
    results: []

llama3_false_positives_1010_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: 0.6955
Eval/rewards/chosen: 2.6328
Eval/logps/chosen: -171.1206
Eval/rewards/rejected: 3.7940
Eval/logps/rejected: -216.4652
Eval/rewards/margins: -1.1613
Eval/kl: 30.4319

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: 0.001
train_batch_size: 1
eval_batch_size: 2
seed: 1234
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
0.2388	0.96	12	0.7812	18.6117
0.2319	2.0	25	0.6955	30.4319

Framework versions

PEFT 0.11.1
Transformers 4.44.0
Pytorch 2.2.0
Datasets 2.20.0
Tokenizers 0.19.1