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: 0.6329
- Eval/rewards/chosen: 0.4406
- Eval/logps/chosen: -199.1299
- Eval/rewards/rejected: 0.4160
- Eval/logps/rejected: -211.0515
- Eval/rewards/margins: 0.0246
- Eval/kl: 4.1837
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 | |
|---|---|---|---|---|
| 0.5565 | 0.96 | 12 | 0.6326 | 0.3559 |
| 0.6102 | 2.0 | 25 | 0.6329 | 1.4255 |
| 0.5449 | 2.96 | 37 | 0.6345 | 2.7750 |
| 0.6022 | 4.0 | 50 | 0.6340 | 3.7858 |
| 0.5433 | 4.96 | 62 | 0.6299 | 4.1605 |
| 0.5345 | 5.76 | 72 | 0.6329 | 4.1837 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.0
- Pytorch 2.2.0
- Datasets 2.20.0
- Tokenizers 0.19.1