metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-small-finetuned-amazon-en-de
results: []
mt5-small-finetuned-amazon-en-de
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: 2.5844
- Rouge1: 18.6058
- Rouge2: 10.0803
- Rougel: 18.025
- Rougelsum: 18.2237
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|
| 2.6887 | 1.0 | 1301 | 2.7862 | 20.3987 | 12.8512 | 19.7713 | 19.7397 |
| 2.5315 | 2.0 | 2602 | 2.7636 | 19.7025 | 11.5086 | 19.2285 | 19.1621 |
| 2.9455 | 3.0 | 3903 | 2.6457 | 20.5245 | 12.445 | 19.9432 | 19.9865 |
| 2.9864 | 4.0 | 5204 | 2.5944 | 19.0345 | 10.3224 | 18.5022 | 18.5792 |
| 2.9746 | 5.0 | 6505 | 2.5910 | 19.5747 | 10.3954 | 18.9401 | 19.1369 |
| 2.9246 | 6.0 | 7806 | 2.5822 | 18.5846 | 9.8889 | 18.0374 | 18.2259 |
| 2.8968 | 7.0 | 9107 | 2.5757 | 18.8335 | 10.2201 | 18.2386 | 18.4522 |
| 2.8645 | 8.0 | 10408 | 2.5844 | 18.6058 | 10.0803 | 18.025 | 18.2237 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1