metadata
base_model: google/mt5-base
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: mt5-base_Nepali_News_Summarization_0
results: []
mt5-base_Nepali_News_Summarization_0
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3685
- Rouge-1 R: 0.3321
- Rouge-1 P: 0.3218
- Rouge-1 F: 0.3186
- Rouge-2 R: 0.1761
- Rouge-2 P: 0.1703
- Rouge-2 F: 0.1677
- Rouge-l R: 0.3234
- Rouge-l P: 0.3133
- Rouge-l F: 0.3102
- Gen Len: 15.7133
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: 0.0005
- train_batch_size: 5
- eval_batch_size: 5
- 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 | Rouge-1 R | Rouge-1 P | Rouge-1 F | Rouge-2 R | Rouge-2 P | Rouge-2 F | Rouge-l R | Rouge-l P | Rouge-l F | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.8844 | 1.0 | 10191 | 1.4867 | 0.31 | 0.3133 | 0.3024 | 0.1576 | 0.1605 | 0.1531 | 0.3015 | 0.3048 | 0.2942 | 15.2667 |
| 1.7381 | 2.0 | 20382 | 1.4401 | 0.3203 | 0.3104 | 0.3068 | 0.1675 | 0.162 | 0.1592 | 0.3121 | 0.3026 | 0.299 | 15.699 |
| 1.6401 | 3.0 | 30573 | 1.3685 | 0.3321 | 0.3218 | 0.3186 | 0.1761 | 0.1703 | 0.1677 | 0.3234 | 0.3133 | 0.3102 | 15.7133 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1