mistral-journal-finetune
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.3357
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: 2.5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.3125 | 1.0 | 197 | 0.3488 |
0.3121 | 2.0 | 394 | 0.3382 |
0.3016 | 3.0 | 591 | 0.3332 |
0.2936 | 4.0 | 788 | 0.3334 |
0.2825 | 5.0 | 985 | 0.3357 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.38.2
- Pytorch 2.1.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for Ai-Marshal/mistral-journal-finetune
Base model
mistralai/Mistral-7B-Instruct-v0.2
Adapter
this model