metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- sacrebleu
model-index:
- name: final_tcc_model
results: []
final_tcc_model
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7783
- Sacrebleu: 7.6467
- Gen Len: 17.9035
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: 16
- eval_batch_size: 16
- seed: 42
- 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 | Sacrebleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 275 | 0.8201 | 7.1607 | 17.8917 |
| 0.9564 | 2.0 | 550 | 0.7971 | 7.3848 | 17.9008 |
| 0.9564 | 3.0 | 825 | 0.7862 | 7.5097 | 17.909 |
| 0.8977 | 4.0 | 1100 | 0.7803 | 7.5882 | 17.9035 |
| 0.8977 | 5.0 | 1375 | 0.7783 | 7.6467 | 17.9035 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cpu
- Datasets 2.13.0
- Tokenizers 0.13.3