metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: postocr
results: []
postocr
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5782
- Rouge1: 0.286
- Rouge2: 0.1937
- Rougel: 0.2773
- Rougelsum: 0.2763
- Gen Len: 14.375
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: 16
- eval_batch_size: 16
- 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 | 14 | 4.0745 | 0.2388 | 0.1532 | 0.2294 | 0.2289 | 13.9464 |
| No log | 2.0 | 28 | 3.7913 | 0.2612 | 0.1749 | 0.2506 | 0.2489 | 14.25 |
| No log | 3.0 | 42 | 3.6383 | 0.2833 | 0.192 | 0.2738 | 0.2735 | 14.4107 |
| No log | 4.0 | 56 | 3.5782 | 0.286 | 0.1937 | 0.2773 | 0.2763 | 14.375 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2