metadata
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: NousResearch/Meta-Llama-3-8B-Instruct
datasets:
- generator
model-index:
- name: clearpolicy-llama-3-8binstruct-v4
results: []
clearpolicy-llama-3-8binstruct-v4
This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.7051
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 7 | 1.2237 |
| No log | 2.0 | 14 | 0.8634 |
| No log | 3.0 | 21 | 0.7050 |
| No log | 4.0 | 28 | 0.7051 |
Framework versions
- PEFT 0.11.0
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1