mistral_o1_25_full
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5698
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- 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
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7304 | 0.1649 | 100 | 0.7158 |
0.7094 | 0.3298 | 200 | 0.6878 |
0.6813 | 0.4946 | 300 | 0.6488 |
0.6352 | 0.6595 | 400 | 0.6073 |
0.5989 | 0.8244 | 500 | 0.5773 |
0.5727 | 0.9893 | 600 | 0.5698 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 16
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for CharlesLi/mistral_o1_25_full
Base model
mistralai/Mistral-7B-v0.1
Finetuned
mistralai/Mistral-7B-Instruct-v0.1