metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2-Audio-7B-Instruct
tags:
- generated_from_trainer
model-index:
- name: Qwen2-RUNY-Intent
results: []
Qwen2-RUNY-Intent
This model is a fine-tuned version of Qwen/Qwen2-Audio-7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0143
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1086 | 0.2 | 281 | 0.0233 |
| 0.0283 | 0.4 | 562 | 0.0265 |
| 0.0317 | 0.6 | 843 | 0.0176 |
| 0.0333 | 0.8 | 1124 | 0.0184 |
| 0.0186 | 1.0 | 1405 | 0.0143 |
Framework versions
- PEFT 0.15.2
- Transformers 4.53.0.dev0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1