mt5-small-finetuned-audio-text-cc
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 0.0364
- Rouge2: 0.0
- Rougel: 0.0182
- Rougelsum: 0.0182
- Gen Len: 4.5
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 5 | nan | 0.0364 | 0.0 | 0.0182 | 0.0182 | 4.5 |
| No log | 2.0 | 10 | nan | 0.0364 | 0.0 | 0.0182 | 0.0182 | 4.5 |
| No log | 3.0 | 15 | nan | 0.0364 | 0.0 | 0.0182 | 0.0182 | 4.5 |
| No log | 4.0 | 20 | nan | 0.0364 | 0.0 | 0.0182 | 0.0182 | 4.5 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2