ZeroShot-3.3.33-Mistral-7b-Multilanguage-3.2.0
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3823
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.4732 | 0.12 | 100 | 0.4529 |
0.4174 | 0.25 | 200 | 0.4165 |
0.4009 | 0.37 | 300 | 0.4039 |
0.4036 | 0.5 | 400 | 0.3962 |
0.3917 | 0.62 | 500 | 0.3895 |
0.3908 | 0.74 | 600 | 0.3851 |
0.3879 | 0.87 | 700 | 0.3828 |
0.3782 | 0.99 | 800 | 0.3823 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Model tree for Weni/ZeroShot-3.3.33-Mistral-7b-Multilanguage-3.2.0
Base model
mistralai/Mistral-7B-Instruct-v0.2