|
--- |
|
base_model: NousResearch/Llama-2-7b-chat-hf |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: results |
|
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. --> |
|
|
|
# results |
|
|
|
This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5181 |
|
|
|
## 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: 8 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.02 |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 4.0113 | 0.08 | 5 | 4.2401 | |
|
| 3.9501 | 0.17 | 10 | 3.5159 | |
|
| 3.5429 | 0.25 | 15 | 2.8638 | |
|
| 2.4329 | 0.34 | 20 | 2.2028 | |
|
| 1.9968 | 0.42 | 25 | 1.4709 | |
|
| 1.3706 | 0.5 | 30 | 1.0854 | |
|
| 0.9502 | 0.59 | 35 | 0.8431 | |
|
| 0.7835 | 0.67 | 40 | 0.6751 | |
|
| 0.7254 | 0.76 | 45 | 0.6131 | |
|
| 0.5724 | 0.84 | 50 | 0.5480 | |
|
| 0.5966 | 0.92 | 55 | 0.5181 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
