|
--- |
|
license: apache-2.0 |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral-Noromaid-7B |
|
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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
# Mistral-Noromaid-7B |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1514 |
|
|
|
## 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 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.2103 | 0.0 | 1 | 1.5604 | |
|
| 1.3191 | 0.1 | 192 | 1.2539 | |
|
| 1.1727 | 0.2 | 384 | 1.2346 | |
|
| 1.3466 | 0.3 | 576 | 1.2171 | |
|
| 0.9652 | 0.4 | 768 | 1.2073 | |
|
| 0.996 | 0.5 | 960 | 1.1920 | |
|
| 0.7863 | 0.6 | 1152 | 1.1804 | |
|
| 0.8883 | 0.7 | 1344 | 1.1700 | |
|
| 0.9351 | 0.8 | 1536 | 1.1590 | |
|
| 0.8361 | 0.9 | 1728 | 1.1511 | |
|
| 1.2718 | 1.0 | 1920 | 1.1438 | |
|
| 0.9613 | 1.09 | 2112 | 1.1585 | |
|
| 1.4066 | 1.19 | 2304 | 1.1550 | |
|
| 0.7388 | 1.29 | 2496 | 1.1538 | |
|
| 1.0686 | 1.39 | 2688 | 1.1531 | |
|
| 1.3536 | 1.49 | 2880 | 1.1533 | |
|
| 0.4994 | 1.59 | 3072 | 1.1517 | |
|
| 0.7574 | 1.69 | 3264 | 1.1519 | |
|
| 0.7574 | 1.79 | 3456 | 1.1516 | |
|
| 1.1436 | 1.89 | 3648 | 1.1514 | |
|
| 1.4085 | 1.99 | 3840 | 1.1514 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
