qwen2.5_0.5b_500k_O3_16kcw_2ep_2
This model is a fine-tuned version of Qwen/Qwen2.5-Coder-0.5B-Instruct on the anghabench_o3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0060
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- total_eval_batch_size: 2
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0142 | 0.5151 | 61000 | 0.0123 |
| 0.0089 | 1.0302 | 122000 | 0.0082 |
| 0.0071 | 1.5452 | 183000 | 0.0064 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3