Quick Links
mt5-base-encoding-correction-1k
This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0494
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 600
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3405 | 1.0 | 500 | 0.0660 |
| 0.0623 | 2.0 | 1000 | 0.0450 |
| 0.0523 | 3.0 | 1500 | 0.0467 |
| 0.0322 | 4.0 | 2000 | 0.0411 |
| 0.0282 | 5.0 | 2500 | 0.0435 |
| 0.0204 | 6.0 | 3000 | 0.0433 |
| 0.0150 | 7.0 | 3500 | 0.0494 |
Framework versions
- Transformers 5.10.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 27
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for sumanthbhargava/mt5-base-encoding-correction-1k
Base model
google/mt5-base
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("sumanthbhargava/mt5-base-encoding-correction-1k") model = AutoModelForSeq2SeqLM.from_pretrained("sumanthbhargava/mt5-base-encoding-correction-1k", device_map="auto")