🏜️MIRAGE-Bench [NAACL'25]
Collection
Dataset Collection from the MIRAGE-Bench paper • 12 items • Updated • 2
nthakur/Mistral-7B-Instruct-v0.2-mirage-bench-sft
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the nthakur/mirage-gpt-4o-sft-instruct-mistral dataset. It achieves the following results on the evaluation set:
- Loss: 0.2294
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3189 | 0.2535 | 200 | 0.2828 |
| 0.2906 | 0.5070 | 400 | 0.2465 |
| 0.2525 | 0.7605 | 600 | 0.2326 |
Framework versions
- PEFT 0.7.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for nthakur/Mistral-7B-Instruct-v0.2-mirage-bench-sft
Base model
mistralai/Mistral-7B-Instruct-v0.2