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: 0.6833
- Eval/rewards/chosen: 0.1418
- Eval/logps/chosen: -202.1179
- Eval/rewards/rejected: 0.1134
- Eval/logps/rejected: -214.0775
- Eval/rewards/margins: 0.0284
- Eval/kl: 1.2457
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: 5678
- 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 | |
|---|---|---|---|---|
| 0.5892 | 0.96 | 12 | 0.6859 | 0.2642 |
| 0.6692 | 2.0 | 25 | 0.6839 | 0.8353 |
| 0.5716 | 2.96 | 37 | 0.6828 | 1.1690 |
| 0.6558 | 3.84 | 48 | 0.6833 | 1.2457 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.0
- Pytorch 2.2.0
- Datasets 2.20.0
- Tokenizers 0.19.1