metadata
license: mit
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: results
results: []
results
This model is a fine-tuned version of gagan3012/k2t on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5481
- Rouge1: 65.0534
- Rouge2: 45.7092
- Rougel: 55.8222
- Rougelsum: 57.1866
- Gen Len: 17.8061
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: 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 |
|---|---|---|---|---|---|---|---|---|
| 0.5049 | 1.0 | 1101 | 0.5527 | 65.0475 | 45.6298 | 55.8323 | 57.2102 | 17.7929 |
| 0.4994 | 2.0 | 2202 | 0.5490 | 65.0567 | 45.7082 | 55.8808 | 57.2343 | 17.8005 |
| 0.4969 | 3.0 | 3303 | 0.5481 | 65.0534 | 45.7092 | 55.8222 | 57.1866 | 17.8061 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1