metadata
library_name: transformers
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: meetingbank_summary_model_finetuned_on_reduced_data
results: []
meetingbank_summary_model_finetuned_on_reduced_data
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3836
- Rouge1: 0.1699
- Rouge2: 0.0873
- Rougel: 0.1462
- Rougelsum: 0.1463
- Generated Length: 18.9954
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Generated Length |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 54 | 3.5593 | 0.165 | 0.0858 | 0.1408 | 0.1409 | 18.971 |
| No log | 2.0 | 108 | 3.4167 | 0.1678 | 0.0868 | 0.1442 | 0.1443 | 18.9954 |
| No log | 3.0 | 162 | 3.3836 | 0.1699 | 0.0873 | 0.1462 | 0.1463 | 18.9954 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1