metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: spanish-spellchecker-t5-base-wikitest1000
results: []
spanish-spellchecker-t5-base-wikitest1000
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2943
- Bleu: 0.0
- 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
No log | 1.0 | 52 | 0.4171 | 0.0 | 19.0 |
No log | 2.0 | 104 | 0.3522 | 0.0 | 19.0 |
No log | 3.0 | 156 | 0.3275 | 0.0 | 19.0 |
No log | 4.0 | 208 | 0.3160 | 0.0 | 19.0 |
No log | 5.0 | 260 | 0.3064 | 0.0 | 19.0 |
No log | 6.0 | 312 | 0.3012 | 0.0 | 19.0 |
No log | 7.0 | 364 | 0.2987 | 0.0 | 19.0 |
No log | 8.0 | 416 | 0.2959 | 0.0 | 19.0 |
No log | 9.0 | 468 | 0.2947 | 0.0 | 19.0 |
0.5085 | 10.0 | 520 | 0.2943 | 0.0 | 19.0 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2