metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: Mistral_Sparse_refined_web_70p_2024-03-22
results: []
Mistral_Sparse_refined_web_70p_2024-03-22
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: 2.2982
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: 3
- gradient_accumulation_steps: 4
- total_train_batch_size: 12
- total_eval_batch_size: 3
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 251
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.9435 | 0.0 | 25 | 3.1292 |
2.8593 | 0.01 | 50 | 2.9094 |
2.6292 | 0.01 | 75 | 2.7553 |
2.4816 | 0.01 | 100 | 2.6809 |
2.3645 | 0.01 | 125 | 2.6480 |
2.4033 | 0.02 | 150 | 2.6153 |
2.3721 | 0.02 | 175 | 2.5967 |
2.4718 | 0.02 | 200 | 2.5749 |
2.4336 | 0.03 | 225 | 2.5629 |
2.3863 | 0.03 | 250 | 2.5455 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0