# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("rebego/mt5-small")
model = AutoModelForSeq2SeqLM.from_pretrained("rebego/mt5-small")Quick Links
mt5-small
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 13.1971
- Bleu: 0.0279
- Gen Len: 3.0
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: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 10 | 17.3800 | 0.0254 | 2.95 |
| No log | 2.0 | 20 | 14.8955 | 0.0309 | 3.0 |
| No log | 3.0 | 30 | 13.6927 | 0.0274 | 2.9 |
| No log | 4.0 | 40 | 13.1837 | 0.0279 | 3.0 |
| No log | 5.0 | 50 | 13.1971 | 0.0279 | 3.0 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1
- Downloads last month
- 4
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="rebego/mt5-small")