metadata
license: other
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: Kquant03/NeuralTrix-7B-dpo-laser
model-index:
- name: train_2024-02-15-20-15-48
results: []
train_2024-02-15-20-15-48
This model is a fine-tuned version of Kquant03/NeuralTrix-7B-dpo-laser on the alpaca_en dataset.
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.2
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 66.57 |
| AI2 Reasoning Challenge (25-Shot) | 62.80 |
| HellaSwag (10-Shot) | 83.01 |
| MMLU (5-Shot) | 63.02 |
| TruthfulQA (0-shot) | 48.32 |
| Winogrande (5-shot) | 81.69 |
| GSM8k (5-shot) | 60.58 |