opus-mt-en-zh-ft3 – AI Model by momentum99 | AlphaNeural AI

You can deploy this model and start earning money today!

momentum99/
opus-mt-en-zh-ft3

like

0

text2text-generation

generated_from_trainer

Helsinki-NLP/opus-mt-en-zh

endpoints_compatible

Views

No views yet

opus-mt-en-zh-ft3

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-zh on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.1164
Model Preparation Time: 0.0088
Bleu: 31.3321

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: 3e-05
train_batch_size: 64
eval_batch_size: 128
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 9
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Bleu
2.475	1.0	79841	2.3263	0.0088	29.1702
2.325	2.0	159682	2.2498	0.0088	29.7419
2.2698	3.0	239523	2.2085	0.0088	30.3255
2.2197	4.0	319364	2.1812	0.0088	30.5081
2.1927	5.0	399205	2.1579	0.0088	30.8275
2.1656	6.0	479046	2.1431	0.0088	30.9670
2.1162	7.0	558887	2.1299	0.0088	31.0997
2.1208	8.0	638728	2.1215	0.0088	31.2667
2.0838	9.0	718569	2.1164	0.0088	31.3330

Framework versions

Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 2.18.0
Tokenizers 0.22.2