mt-0-small-multilanguage-query-extraction
This model is a fine-tuned version of bigscience/mt0-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0037
- Rouge1: 90.139
- Rouge2: 88.3647
- Rougel: 90.1385
- Rougelsum: 90.1396
- 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.0046 | 1.0 | 17500 | 0.0040 | 90.1388 | 88.3642 | 90.1382 | 90.1395 | 19.0 |
| 0.0041 | 2.0 | 35000 | 0.0038 | 90.139 | 88.3647 | 90.1385 | 90.1396 | 19.0 |
| 0.0039 | 3.0 | 52500 | 0.0037 | 90.139 | 88.3647 | 90.1385 | 90.1396 | 19.0 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 40