|
--- |
|
base_model: meta-llama/Meta-Llama-3.1-8B |
|
datasets: |
|
- scitldr |
|
library_name: peft |
|
license: llama3.1 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Llama-3.1-8B-Summarization-QLoRa |
|
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. --> |
|
|
|
# Llama-3.1-8B-Summarization-QLoRa |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the scitldr dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.3813 |
|
|
|
## 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: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- num_epochs: 2 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.1968 | 0.2008 | 200 | 2.2962 | |
|
| 2.2026 | 0.4016 | 400 | 2.3085 | |
|
| 2.205 | 0.6024 | 600 | 2.3048 | |
|
| 2.2028 | 0.8032 | 800 | 2.2968 | |
|
| 2.2001 | 1.0040 | 1000 | 2.2911 | |
|
| 1.7063 | 1.2048 | 1200 | 2.3696 | |
|
| 1.6856 | 1.4056 | 1400 | 2.3756 | |
|
| 1.6556 | 1.6064 | 1600 | 2.3823 | |
|
| 1.6331 | 1.8072 | 1800 | 2.3813 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
