ja
This model is a fine-tuned version of Qwen/Qwen3-8B on the mmlu_prox_ja_train dataset. It achieves the following results on the evaluation set:
- Loss: 0.3479
- Accuracy: 0.8980
- Mcq Accuracy: 0.4904
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mcq Accuracy |
|---|---|---|---|---|---|
| 0.1335 | 2.5367 | 200 | 0.3460 | 0.8975 | 0.4881 |
Framework versions
- PEFT 0.18.1
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 12