<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
tuna_t0_v1.6
This model is a fine-tuned version of anhdt-dsai-02/tuna_t0_v1.4 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2728
- Rouge1: 48.7673
- Rouge2: 21.6362
- Rougel: 33.1174
- Rougelsum: 36.77
- Bleu: 5.5664
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu |
|---|---|---|---|---|---|---|---|---|
| 0.3131 | 1.0 | 7455 | 0.2811 | 47.5613 | 21.2753 | 32.3442 | 35.7895 | 5.3805 |
| 0.3524 | 2.0 | 14910 | 0.2757 | 48.8703 | 21.5877 | 33.0113 | 36.6099 | 6.0464 |
| 0.2785 | 3.0 | 22365 | 0.2734 | 48.9094 | 21.7508 | 33.3675 | 36.9757 | 5.9984 |
| 0.3074 | 4.0 | 29820 | 0.2728 | 48.7673 | 21.6362 | 33.1174 | 36.77 | 5.5664 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
