Ministral-8B-Instruct-2410-sft-1000
This model is a fine-tuned version of mistralai/Ministral-8B-Instruct-2410 on the bct_non_cot_sft_1000 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0730
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- 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: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0691 | 1.7778 | 50 | 0.0730 |
| 0.0185 | 3.5556 | 100 | 0.0988 |
| 0.0054 | 5.3333 | 150 | 0.1454 |
| 0.0002 | 7.1111 | 200 | 0.1825 |
| 0.0005 | 8.8889 | 250 | 0.1897 |
Framework versions
- PEFT 0.12.0
- Transformers 4.45.2
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.20.0
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for chchen/Ministral-8B-Instruct-2410-sft-1000
Base model
mistralai/Ministral-8B-Instruct-2410