<!-- 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. -->
transcriber-t5-v8-new
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0818
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: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.1008 | 0.72 | 500 | 0.1306 |
0.069 | 1.43 | 1000 | 0.1227 |
0.1052 | 2.15 | 1500 | 0.1209 |
0.1017 | 2.86 | 2000 | 0.0992 |
0.0828 | 3.58 | 2500 | 0.0919 |
0.0471 | 4.29 | 3000 | 0.0927 |
0.0769 | 5.01 | 3500 | 0.0849 |
0.0732 | 5.72 | 4000 | 0.0862 |
0.0801 | 6.44 | 4500 | 0.0857 |
0.0428 | 7.15 | 5000 | 0.0815 |
0.1119 | 7.87 | 5500 | 0.0790 |
0.0692 | 8.58 | 6000 | 0.0780 |
0.0684 | 9.3 | 6500 | 0.0818 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3