metadata
library_name: transformers
license: apache-2.0
base_model: google/mt5-small
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: ADL_HW2_MT5_prefix
results: []
ADL_HW2_MT5_prefix
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2666
- Rouge1: 14.9351
- Rouge2: 5.1774
- Rougel: 14.8449
- Rougelsum: 14.8557
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: 5.6e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 5.5187 | 1.0 | 905 | 3.6796 | 10.8834 | 3.8911 | 10.7836 | 10.7678 |
| 4.1348 | 2.0 | 1810 | 3.5007 | 12.6862 | 4.7919 | 12.5718 | 12.6073 |
| 3.9168 | 3.0 | 2715 | 3.4039 | 13.4387 | 4.9163 | 13.3294 | 13.3195 |
| 3.7837 | 4.0 | 3620 | 3.3405 | 13.7297 | 4.8865 | 13.6301 | 13.6512 |
| 3.7018 | 5.0 | 4525 | 3.3057 | 14.034 | 5.1596 | 13.9229 | 13.9201 |
| 3.6474 | 6.0 | 5430 | 3.2837 | 14.7209 | 5.2105 | 14.6058 | 14.6093 |
| 3.6058 | 7.0 | 6335 | 3.2764 | 14.8731 | 5.0734 | 14.7598 | 14.7795 |
| 3.5881 | 8.0 | 7240 | 3.2666 | 14.9351 | 5.1774 | 14.8449 | 14.8557 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1