<!-- 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. -->
t5_number_v4
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0049
- Cer: 0.4112
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
- 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Cer |
---|---|---|---|---|
No log | 1.0 | 197 | 0.0116 | 0.6320 |
4.7961 | 2.0 | 394 | 0.0071 | 0.5152 |
0.0136 | 3.0 | 591 | 0.0063 | 0.5 |
0.0095 | 4.0 | 788 | 0.0058 | 0.4569 |
0.0074 | 5.0 | 985 | 0.0056 | 0.4518 |
0.0067 | 6.0 | 1182 | 0.0052 | 0.4365 |
0.0063 | 7.0 | 1379 | 0.0051 | 0.4315 |
0.006 | 8.0 | 1576 | 0.0050 | 0.4162 |
0.0056 | 9.0 | 1773 | 0.0049 | 0.4112 |
0.0053 | 10.0 | 1970 | 0.0049 | 0.4112 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3