|
--- |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: meta-llama/Llama-2-7b-hf |
|
model-index: |
|
- name: mistral-stock-finetune |
|
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. --> |
|
|
|
# mistral-stock-finetune |
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6325 |
|
|
|
## 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: 2.5e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1 |
|
- training_steps: 500 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.2624 | 0.07 | 25 | 1.0074 | |
|
| 0.8582 | 0.13 | 50 | 0.7799 | |
|
| 0.7578 | 0.2 | 75 | 0.7358 | |
|
| 0.7276 | 0.26 | 100 | 0.7133 | |
|
| 0.7104 | 0.33 | 125 | 0.6944 | |
|
| 0.6791 | 0.4 | 150 | 0.6819 | |
|
| 0.6856 | 0.46 | 175 | 0.6734 | |
|
| 0.6723 | 0.53 | 200 | 0.6658 | |
|
| 0.6629 | 0.59 | 225 | 0.6601 | |
|
| 0.6526 | 0.66 | 250 | 0.6553 | |
|
| 0.6395 | 0.73 | 275 | 0.6505 | |
|
| 0.6537 | 0.79 | 300 | 0.6471 | |
|
| 0.6317 | 0.86 | 325 | 0.6445 | |
|
| 0.6401 | 0.92 | 350 | 0.6405 | |
|
| 0.6412 | 0.99 | 375 | 0.6375 | |
|
| 0.6303 | 1.06 | 400 | 0.6367 | |
|
| 0.6135 | 1.12 | 425 | 0.6347 | |
|
| 0.6107 | 1.19 | 450 | 0.6336 | |
|
| 0.605 | 1.25 | 475 | 0.6330 | |
|
| 0.6062 | 1.32 | 500 | 0.6325 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.40.0.dev0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |