|
--- |
|
license: apache-2.0 |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral_Sparse_refined_web_90p_2024-02-16 |
|
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_Sparse_refined_web_90p_2024-02-16 |
|
|
|
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: 2.3570 |
|
|
|
## 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: 1 |
|
- seed: 0 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 16 |
|
- total_eval_batch_size: 2 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 1000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 8.7348 | 0.0 | 25 | 8.3850 | |
|
| 5.9261 | 0.01 | 50 | 5.5212 | |
|
| 3.6159 | 0.01 | 75 | 3.6689 | |
|
| 3.0291 | 0.02 | 100 | 3.1644 | |
|
| 2.786 | 0.02 | 125 | 2.9872 | |
|
| 2.7951 | 0.02 | 150 | 2.9148 | |
|
| 2.6959 | 0.03 | 175 | 2.8528 | |
|
| 2.6134 | 0.03 | 200 | 2.8111 | |
|
| 2.6439 | 0.04 | 225 | 2.7811 | |
|
| 2.6326 | 0.04 | 250 | 2.7534 | |
|
| 2.5528 | 0.04 | 275 | 2.7384 | |
|
| 2.5601 | 0.05 | 300 | 2.7239 | |
|
| 2.5693 | 0.05 | 325 | 2.7181 | |
|
| 2.3934 | 0.06 | 350 | 2.7019 | |
|
| 2.5466 | 0.06 | 375 | 2.6918 | |
|
| 2.5872 | 0.06 | 400 | 2.6840 | |
|
| 2.5638 | 0.07 | 425 | 2.6768 | |
|
| 2.5235 | 0.07 | 450 | 2.6671 | |
|
| 2.4179 | 0.08 | 475 | 2.6622 | |
|
| 2.4862 | 0.08 | 500 | 2.6619 | |
|
| 2.5594 | 0.08 | 525 | 2.6584 | |
|
| 2.4604 | 0.09 | 550 | 2.6564 | |
|
| 2.5887 | 0.09 | 575 | 2.6493 | |
|
| 2.3974 | 0.1 | 600 | 2.6447 | |
|
| 2.4769 | 0.1 | 625 | 2.6457 | |
|
| 2.53 | 0.1 | 650 | 2.6317 | |
|
| 2.5403 | 0.11 | 675 | 2.6341 | |
|
| 2.4764 | 0.11 | 700 | 2.6296 | |
|
| 2.489 | 0.12 | 725 | 2.6268 | |
|
| 2.3969 | 0.12 | 750 | 2.6288 | |
|
| 2.4164 | 0.12 | 775 | 2.6264 | |
|
| 2.5208 | 0.13 | 800 | 2.6227 | |
|
| 2.4997 | 0.13 | 825 | 2.6190 | |
|
| 2.4853 | 0.14 | 850 | 2.6200 | |
|
| 2.3447 | 0.14 | 875 | 2.6091 | |
|
| 2.4384 | 0.14 | 900 | 2.6132 | |
|
| 2.3863 | 0.15 | 925 | 2.6152 | |
|
| 2.5076 | 0.15 | 950 | 2.6114 | |
|
| 2.4299 | 0.16 | 975 | 2.6144 | |
|
| 2.478 | 0.16 | 1000 | 2.6109 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
