metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
- wer
base_model: google/mt5-small
model-index:
- name: nep-spell-mt5-small-0
results: []
nep-spell-mt5-small-0
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6065
- Accuracy: 0.0
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Wer: 7.0137
- Cer: 13.4164
- Chrf: 1.5380
- Exact Match: 0.0
- Bertscore:precision: 0.4936
- Bertscore:recall: 0.5422
- Bertscore:f1: 0.5139
- Ter: 701.3722
- Blerurt: -0.5287
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Wer | Cer | Chrf | Exact Match | Bertscore:precision | Bertscore:recall | Bertscore:f1 | Ter | Blerurt |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 39.0737 | 0.39 | 500 | 14.0796 | 0.0 | 0.0 | 0.0 | 0.0 | 28.9335 | 58.5317 | 0.3292 | 0.0 | 0.3772 | 0.5413 | 0.4436 | 2893.3486 | -0.9012 |
| 4.5775 | 0.79 | 1000 | 1.6065 | 0.0 | 0.0 | 0.0 | 0.0 | 7.0137 | 13.4164 | 1.5380 | 0.0 | 0.4936 | 0.5422 | 0.5139 | 701.3722 | -0.5287 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2