metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: Mistral_Sparse_refined_web_50p_2024-03-10
results: []
Mistral_Sparse_refined_web_50p_2024-03-10
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1110
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 |
|---|---|---|---|
| 2.4139 | 0.0 | 25 | 2.5658 |
| 2.226 | 0.01 | 50 | 2.5201 |
| 2.2555 | 0.01 | 75 | 2.4799 |
| 2.2174 | 0.02 | 100 | 2.4604 |
| 2.2232 | 0.02 | 125 | 2.4481 |
| 2.2955 | 0.02 | 150 | 2.4355 |
| 2.2275 | 0.03 | 175 | 2.4291 |
| 2.2219 | 0.03 | 200 | 2.4206 |
| 2.2521 | 0.04 | 225 | 2.4176 |
| 2.2937 | 0.04 | 250 | 2.4077 |
| 2.2073 | 0.04 | 275 | 2.4069 |
| 2.2157 | 0.05 | 300 | 2.4061 |
| 2.2274 | 0.05 | 325 | 2.4085 |
| 2.0697 | 0.06 | 350 | 2.4033 |
| 2.2338 | 0.06 | 375 | 2.4037 |
| 2.2722 | 0.06 | 400 | 2.4003 |
| 2.2638 | 0.07 | 425 | 2.4003 |
| 2.2215 | 0.07 | 450 | 2.4011 |
| 2.1437 | 0.08 | 475 | 2.3962 |
| 2.2073 | 0.08 | 500 | 2.3951 |
| 2.2696 | 0.08 | 525 | 2.3923 |
| 2.1624 | 0.09 | 550 | 2.3899 |
| 2.3006 | 0.09 | 575 | 2.3930 |
| 2.0869 | 0.1 | 600 | 2.3915 |
| 2.1871 | 0.1 | 625 | 2.3906 |
| 2.2712 | 0.1 | 650 | 2.3895 |
| 2.2596 | 0.11 | 675 | 2.3898 |
| 2.2297 | 0.11 | 700 | 2.3878 |
| 2.2126 | 0.12 | 725 | 2.3860 |
| 2.119 | 0.12 | 750 | 2.3869 |
| 2.1637 | 0.12 | 775 | 2.3848 |
| 2.2537 | 0.13 | 800 | 2.3853 |
| 2.2641 | 0.13 | 825 | 2.3872 |
| 2.2422 | 0.14 | 850 | 2.3874 |
| 2.11 | 0.14 | 875 | 2.3847 |
| 2.1745 | 0.14 | 900 | 2.3831 |
| 2.1222 | 0.15 | 925 | 2.3834 |
| 2.2604 | 0.15 | 950 | 2.3858 |
| 2.1929 | 0.16 | 975 | 2.3847 |
| 2.2353 | 0.16 | 1000 | 2.3841 |
| 2.2409 | 0.16 | 1025 | 2.3825 |
| 2.237 | 0.17 | 1050 | 2.3805 |
| 2.28 | 0.17 | 1075 | 2.3806 |
| 2.209 | 0.18 | 1100 | 2.3802 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0