mistral_instruct_generation
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3338
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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.4954 | 0.0 | 20 | 1.3620 |
1.4476 | 0.01 | 40 | 1.3493 |
1.4787 | 0.01 | 60 | 1.3418 |
1.4646 | 0.02 | 80 | 1.3396 |
1.4857 | 0.02 | 100 | 1.3338 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.1
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 3
Model tree for joy2000/mistral_instruct_generation
Base model
mistralai/Mistral-7B-v0.1
Finetuned
mistralai/Mistral-7B-Instruct-v0.1
Adapter
this model