# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Shularp/en2arCkptfromgendata")
model = AutoModelForSeq2SeqLM.from_pretrained("Shularp/en2arCkptfromgendata")Quick Links
en2arCkptfromgendata
This model is a fine-tuned version of Botnoi/ckpt_marian_mt_en_ar_health on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7945
- Bleu: 53.6921
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 0.841 | 1.0 | 37 | 0.8527 | 49.1712 |
| 0.4988 | 2.0 | 74 | 0.8091 | 51.9279 |
| 0.3991 | 3.0 | 111 | 0.8032 | 52.7260 |
| 0.3414 | 4.0 | 148 | 0.7959 | 53.4123 |
| 0.2818 | 5.0 | 185 | 0.7927 | 54.3209 |
| 0.2784 | 6.0 | 222 | 0.7920 | 53.4743 |
| 0.2309 | 7.0 | 259 | 0.7914 | 54.3270 |
| 0.2098 | 8.0 | 296 | 0.7894 | 53.5568 |
| 0.1714 | 9.0 | 333 | 0.7939 | 53.6273 |
| 0.2173 | 10.0 | 370 | 0.7945 | 53.6921 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
- 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="Shularp/en2arCkptfromgendata")