ntnu-smil/phi-4-mm-asr-dd-gec
08
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
phi-4-mm-asr-dd-gec
This model is a fine-tuned version of ntnu-smil/phi-4-mm-asr-dd on an unknown dataset.
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: 4e-05
- trainbatchsize: 4
- evalbatchsize: 8
- seed: 42
- gradientaccumulationsteps: 32
- totaltrainbatch_size: 128
- optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.95) and epsilon=1e-07 and optimizerargs=No additional optimizer arguments
- lrschedulertype: linear
- lrschedulerwarmup_steps: 50
- num_epochs: 1
Training results
Framework versions
- Transformers 4.50.3
- Pytorch 2.4.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1