|
--- |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: NousResearch/Llama-2-7b-hf |
|
model-index: |
|
- name: llama-2-7b-news-gen |
|
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-2-7b-news-gen |
|
|
|
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co./NousResearch/Llama-2-7b-hf) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3099 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.7847 | 0.41 | 25 | 1.7056 | |
|
| 1.6833 | 0.82 | 50 | 1.6216 | |
|
| 1.6116 | 1.23 | 75 | 1.5565 | |
|
| 1.5546 | 1.64 | 100 | 1.4979 | |
|
| 1.5453 | 2.05 | 125 | 1.4493 | |
|
| 1.433 | 2.46 | 150 | 1.3999 | |
|
| 1.4277 | 2.87 | 175 | 1.3624 | |
|
| 1.3405 | 3.28 | 200 | 1.3303 | |
|
| 1.3358 | 3.69 | 225 | 1.3099 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.1 |
