metadata
library_name: transformers
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: my_awesome_billsum_model
results: []
my_awesome_billsum_model
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5565
- Rouge1: 0.1375
- Rouge2: 0.0452
- Rougel: 0.1156
- Rougelsum: 0.116
- Gen Len: 19.0
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 | 62 | 2.8458 | 0.1241 | 0.0319 | 0.1042 | 0.1045 | 19.0 |
| No log | 2.0 | 124 | 2.6353 | 0.1283 | 0.0385 | 0.1082 | 0.1084 | 19.0 |
| No log | 3.0 | 186 | 2.5731 | 0.135 | 0.0442 | 0.1136 | 0.1142 | 19.0 |
| No log | 4.0 | 248 | 2.5565 | 0.1375 | 0.0452 | 0.1156 | 0.116 | 19.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1