metadata
base_model: meta-llama/Llama-3.1-8B-Instruct
library_name: peft
license: llama3.1
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: Llama-3.1-8B-Instruct-SFT-800
results: []
Llama-3.1-8B-Instruct-SFT-800
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the bct_non_cot_sft_800 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1235
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-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1189 | 1.1111 | 50 | 0.9741 |
| 0.1565 | 2.2222 | 100 | 0.1597 |
| 0.0611 | 3.3333 | 150 | 0.1300 |
| 0.0975 | 4.4444 | 200 | 0.1235 |
| 0.0664 | 5.5556 | 250 | 0.1240 |
| 0.0974 | 6.6667 | 300 | 0.1241 |
| 0.0677 | 7.7778 | 350 | 0.1239 |
| 0.0486 | 8.8889 | 400 | 0.1246 |
| 0.075 | 10.0 | 450 | 0.1243 |
Framework versions
- PEFT 0.12.0
- Transformers 4.45.2
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.20.0