metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: sparse_mistral_refined_web_90p_2024-03-23
results: []
sparse_mistral_refined_web_90p_2024-03-23
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: 2.5513
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: 8
- total_train_batch_size: 32
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.6179 | 0.01 | 25 | 8.1852 |
| 5.5288 | 0.02 | 50 | 5.1072 |
| 3.412 | 0.02 | 75 | 3.4986 |
| 2.9282 | 0.03 | 100 | 3.0918 |
| 2.8311 | 0.04 | 125 | 2.9413 |
| 2.6787 | 0.05 | 150 | 2.8614 |
| 2.5768 | 0.06 | 175 | 2.8043 |
| 2.6834 | 0.06 | 200 | 2.7735 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0