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: 1.1781
- Eval/rewards/chosen: -0.0396
- Eval/logps/chosen: -200.9254
- Eval/rewards/rejected: -0.0766
- Eval/logps/rejected: -241.0806
- Eval/rewards/margins: 0.0370
- Eval/kl: 0.0308
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: 6.0
Training results
Training Loss | Epoch | Step | Validation Loss | |
---|---|---|---|---|
0.7403 | 0.96 | 12 | 1.2009 | 0.1233 |
0.961 | 2.0 | 25 | 1.1781 | 0.0308 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.0
- Pytorch 2.2.0
- Datasets 2.20.0
- Tokenizers 0.19.1