MNLP_M2_mcqa_model2
This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5787
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: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6677 | 1.0 | 4380 | 1.5840 |
| 1.6558 | 2.0 | 8760 | 1.5796 |
| 1.6602 | 3.0 | 13140 | 1.5785 |
| 1.6553 | 4.0 | 17520 | 1.5787 |
| 1.6479 | 5.0 | 21900 | 1.5787 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 976
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for sophiargh/MNLP_M2_mcqa_model
Base model
Qwen/Qwen3-0.6B-Base