metadata
base_model: alayaran/bodo-t5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bodo-t5-base-news-headline-ft
results: []
bodo-t5-base-news-headline-ft
This model is a fine-tuned version of alayaran/bodo-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2069
- Rouge1: 0.004
- Rouge2: 0.0
- Rougel: 0.004
- Rougelsum: 0.004
- Gen Len: 18.86
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: 12
- eval_batch_size: 12
- seed: 0
- 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 |
|---|---|---|---|---|---|---|---|---|
| 2.7919 | 2.33 | 500 | 3.2179 | 0.004 | 0.0 | 0.004 | 0.004 | 18.86 |
| 2.7924 | 4.65 | 1000 | 3.2069 | 0.004 | 0.0 | 0.004 | 0.004 | 18.86 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3