|
--- |
|
license: apache-2.0 |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral_Sparse_refined_web_70p_2024-03-12 |
|
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_70p_2024-03-12 |
|
|
|
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: 2.1626 |
|
|
|
## 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: 4 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- total_eval_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 1100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.7221 | 0.0 | 25 | 2.8218 | |
|
| 2.4266 | 0.01 | 50 | 2.6972 | |
|
| 2.4153 | 0.01 | 75 | 2.6181 | |
|
| 2.3588 | 0.02 | 100 | 2.5695 | |
|
| 2.3274 | 0.02 | 125 | 2.5427 | |
|
| 2.4054 | 0.02 | 150 | 2.5244 | |
|
| 2.3274 | 0.03 | 175 | 2.5144 | |
|
| 2.3042 | 0.03 | 200 | 2.4995 | |
|
| 2.3296 | 0.04 | 225 | 2.4898 | |
|
| 2.3621 | 0.04 | 250 | 2.4844 | |
|
| 2.2825 | 0.04 | 275 | 2.4756 | |
|
| 2.2932 | 0.05 | 300 | 2.4704 | |
|
| 2.3015 | 0.05 | 325 | 2.4693 | |
|
| 2.139 | 0.06 | 350 | 2.4612 | |
|
| 2.2953 | 0.06 | 375 | 2.4553 | |
|
| 2.3358 | 0.06 | 400 | 2.4546 | |
|
| 2.3302 | 0.07 | 425 | 2.4506 | |
|
| 2.2814 | 0.07 | 450 | 2.4506 | |
|
| 2.2014 | 0.08 | 475 | 2.4455 | |
|
| 2.266 | 0.08 | 500 | 2.4434 | |
|
| 2.3309 | 0.08 | 525 | 2.4430 | |
|
| 2.2278 | 0.09 | 550 | 2.4417 | |
|
| 2.3621 | 0.09 | 575 | 2.4384 | |
|
| 2.1614 | 0.1 | 600 | 2.4385 | |
|
| 2.2504 | 0.1 | 625 | 2.4370 | |
|
| 2.3301 | 0.1 | 650 | 2.4350 | |
|
| 2.3177 | 0.11 | 675 | 2.4331 | |
|
| 2.2784 | 0.11 | 700 | 2.4307 | |
|
| 2.2681 | 0.12 | 725 | 2.4305 | |
|
| 2.1777 | 0.12 | 750 | 2.4314 | |
|
| 2.2164 | 0.12 | 775 | 2.4321 | |
|
| 2.3068 | 0.13 | 800 | 2.4292 | |
|
| 2.3131 | 0.13 | 825 | 2.4267 | |
|
| 2.2971 | 0.14 | 850 | 2.4256 | |
|
| 2.1623 | 0.14 | 875 | 2.4231 | |
|
| 2.2308 | 0.14 | 900 | 2.4246 | |
|
| 2.1772 | 0.15 | 925 | 2.4259 | |
|
| 2.3114 | 0.15 | 950 | 2.4226 | |
|
| 2.2434 | 0.16 | 975 | 2.4268 | |
|
| 2.2852 | 0.16 | 1000 | 2.4259 | |
|
| 2.2924 | 0.16 | 1025 | 2.4262 | |
|
| 2.3095 | 0.17 | 1050 | 2.4231 | |
|
| 2.3378 | 0.17 | 1075 | 2.4225 | |
|
| 2.265 | 0.18 | 1100 | 2.4181 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
