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: 1.4466
- Eval/rewards/chosen: -0.3663
- Eval/logps/chosen: -207.1990
- Eval/rewards/rejected: -0.4813
- Eval/logps/rejected: -220.0244
- Eval/rewards/margins: 0.1150
- Eval/kl: 0.0
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 | |
|---|---|---|---|---|
| 1.0617 | 0.96 | 12 | 1.6713 | 0.0691 |
| 1.5086 | 2.0 | 25 | 1.6025 | 0.0 |
| 0.9726 | 2.96 | 37 | 1.5329 | 0.0 |
| 1.2454 | 4.0 | 50 | 1.4632 | 0.0 |
| 0.919 | 4.96 | 62 | 1.4446 | 0.0 |
| 0.8342 | 5.76 | 72 | 1.4466 | 0.0 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.0
- Pytorch 2.2.0
- Datasets 2.20.0
- Tokenizers 0.19.1