qwen3-32b-stage2
This model is a fine-tuned version of /workspace/llama-factory/saves/Qwen3-32B-Instruct/full/qwen3-32b-stage1 on the private_roleplay dataset. It achieves the following results on the evaluation set:
- Loss: 2.0873
- Num Input Tokens Seen: 3480000
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.LION_8BIT and the args are: No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.52.1
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- -
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support