|
--- |
|
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_1609_KTO_optimised_model |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# llama3_false_positives_1609_KTO_optimised_model |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5846 |
|
- Eval/rewards/chosen: 2.6874 |
|
- Eval/logps/chosen: -171.2629 |
|
- Eval/rewards/rejected: 2.4373 |
|
- Eval/logps/rejected: -186.6407 |
|
- Eval/rewards/margins: 0.2501 |
|
- Eval/kl: 24.3196 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- 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 | | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 0.4821 | 0.96 | 12 | 0.6001 | 13.3805 | |
|
| 0.1368 | 2.0 | 25 | 0.5846 | 24.3196 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.2.0 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
