metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- xlsum
metrics:
- rouge
model-index:
- name: mt5-swatf
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: xlsum
type: xlsum
config: swahili
split: validation
args: swahili
metrics:
- name: Rouge1
type: rouge
value: 9.7053
mt5-swatf
This model is a fine-tuned version of google/mt5-small on the xlsum dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 9.7053
- Rouge2: 1.3021
- Rougel: 8.4306
- Rougelsum: 8.4159
- Gen Len: 683.08
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: 4e-05
- train_batch_size: 4
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.0 | 0.8 | 500 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 1.6 | 1000 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 2.4 | 1500 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 3.2 | 2000 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 4.0 | 2500 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 4.8 | 3000 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 5.6 | 3500 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 6.4 | 4000 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 7.2 | 4500 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 8.0 | 5000 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 8.8 | 5500 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
| 0.0 | 9.6 | 6000 | nan | 9.7053 | 1.3021 | 8.4306 | 8.4159 | 683.08 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3