|
--- |
|
license: apache-2.0 |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: sparse_mistral_7b_refined_web_50p_2024-05-11 |
|
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. --> |
|
|
|
# sparse_mistral_7b_refined_web_50p_2024-05-11 |
|
|
|
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: 2.2258 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 4 |
|
- seed: 0 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 275 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.3307 | 0.0 | 25 | 2.4048 | |
|
| 2.2364 | 0.0 | 50 | 2.3533 | |
|
| 2.2723 | 0.01 | 75 | 2.3099 | |
|
| 2.1585 | 0.01 | 100 | 2.2884 | |
|
| 2.2562 | 0.01 | 125 | 2.2787 | |
|
| 2.4057 | 0.01 | 150 | 2.2709 | |
|
| 2.3147 | 0.01 | 175 | 2.2635 | |
|
| 2.2796 | 0.02 | 200 | 2.2600 | |
|
| 2.2157 | 0.02 | 225 | 2.2557 | |
|
| 2.303 | 0.02 | 250 | 2.2542 | |
|
| 2.0701 | 0.02 | 275 | 2.2511 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.2 |
|
|
