# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("kabelomalapane/Zu-En_update")
model = AutoModelForSeq2SeqLM.from_pretrained("kabelomalapane/Zu-En_update", device_map="auto")Quick Links
Zu-En_update
This model is a fine-tuned version of kabelomalapane/model_zu-en_updated on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9399
- Bleu: 27.9608
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: 16
- eval_batch_size: 32
- seed: 42
- 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 |
|---|---|---|---|---|
| 2.1017 | 1.0 | 1173 | 1.8404 | 29.1031 |
| 1.7497 | 2.0 | 2346 | 1.8318 | 28.9036 |
| 1.523 | 3.0 | 3519 | 1.8250 | 28.8415 |
| 1.364 | 4.0 | 4692 | 1.8551 | 28.6215 |
| 1.2462 | 5.0 | 5865 | 1.8684 | 28.3783 |
| 1.1515 | 6.0 | 7038 | 1.8948 | 28.3372 |
| 1.0796 | 7.0 | 8211 | 1.9109 | 28.1603 |
| 1.0215 | 8.0 | 9384 | 1.9274 | 28.0309 |
| 0.9916 | 9.0 | 10557 | 1.9323 | 27.9472 |
| 0.9583 | 10.0 | 11730 | 1.9399 | 27.9260 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 13
# 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="kabelomalapane/Zu-En_update")