metadata
library_name: transformers
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: billsum_model
results: []
billsum_model
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6491
- Rouge1: 0.1336
- Rouge2: 0.0434
- Rougel: 0.1104
- Rougelsum: 0.1103
- 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: 2.5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 62 | 2.8316 | 0.1231 | 0.0341 | 0.1019 | 0.1018 | 19.0 |
| No log | 2.0 | 124 | 2.6623 | 0.1327 | 0.0428 | 0.1097 | 0.1094 | 19.0 |
| No log | 2.5 | 155 | 2.6491 | 0.1336 | 0.0434 | 0.1104 | 0.1103 | 19.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1