metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: random-all-q
results: []
random-all-q
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3793
- Rouge1: 0.1605
- Rouge2: 0.0487
- Rougel: 0.1314
- Rougelsum: 0.1314
- Gen Len: 17.3704
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.0528 | 1.0 | 11248 | 2.5314 | 0.1402 | 0.0407 | 0.1159 | 0.1159 | 15.8872 |
| 2.951 | 2.0 | 22496 | 2.4406 | 0.1554 | 0.0462 | 0.1276 | 0.1276 | 17.0291 |
| 2.847 | 3.0 | 33744 | 2.4066 | 0.1592 | 0.0485 | 0.1307 | 0.1307 | 17.2227 |
| 2.7959 | 4.0 | 44992 | 2.3870 | 0.1597 | 0.0489 | 0.1309 | 0.131 | 17.3245 |
| 2.8236 | 5.0 | 56240 | 2.3793 | 0.1605 | 0.0487 | 0.1314 | 0.1314 | 17.3704 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3