|
---
|
|
license: apache-2.0
|
|
base_model: t5-small
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- bleu
|
|
- wer
|
|
model-index:
|
|
- name: randomization_model_new
|
|
results: []
|
|
---
|
|
|
|
<!-- 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. -->
|
|
|
|
# randomization_model_new
|
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 2.5559
|
|
- Bleu: 0.0
|
|
- Wer: 0.9616
|
|
- Rougel: 0.1052
|
|
- Gen Len: 19.0
|
|
|
|
## 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: 20
|
|
- eval_batch_size: 20
|
|
- seed: 42
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
- lr_scheduler_type: linear
|
|
- num_epochs: 3
|
|
- mixed_precision_training: Native AMP
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Wer | Rougel | Gen Len |
|
|
|:-------------:|:-----:|:----:|:---------------:|:----:|:------:|:------:|:-------:|
|
|
| 3.4449 | 0.4 | 100 | 2.9554 | 0.0 | 0.9649 | 0.0961 | 18.99 |
|
|
| 3.2957 | 0.8 | 200 | 2.7974 | 0.0 | 0.964 | 0.0989 | 18.984 |
|
|
| 3.1923 | 1.2 | 300 | 2.6976 | 0.0 | 0.9629 | 0.1013 | 18.9945 |
|
|
| 3.1268 | 1.6 | 400 | 2.6331 | 0.0 | 0.9626 | 0.1025 | 18.9985 |
|
|
| 3.0741 | 2.0 | 500 | 2.5914 | 0.0 | 0.962 | 0.104 | 18.997 |
|
|
| 3.0514 | 2.4 | 600 | 2.5671 | 0.0 | 0.9616 | 0.105 | 18.997 |
|
|
| 3.0312 | 2.8 | 700 | 2.5559 | 0.0 | 0.9616 | 0.1052 | 19.0 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.41.0
|
|
- Pytorch 2.3.0
|
|
- Datasets 2.19.1
|
|
- Tokenizers 0.19.1
|
|
|
