Hugging Face's logo

sisi
/
bot_train_am_7

Text2Text Generation
Transformers
TensorBoard
Safetensors
marian
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
bot_train_am_7 / README.md
sisi's picture
sisi
End of training
7bd2a6c verified
preview code
|
raw
history blame contribute delete
No virus
2.02 kB
metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-ar-en
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: bot_train_am_7
    results: []

bot_train_am_7

This model is a fine-tuned version of Helsinki-NLP/opus-mt-ar-en on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5408
  • Bleu: 33.1944
  • Gen Len: 12.2599

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: 15
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
2.2203 1.0 984 1.7126 25.9506 12.0381
1.5778 2.0 1968 1.5978 28.5264 11.8927
1.3114 3.0 2952 1.5466 30.454 12.0183
1.1266 4.0 3936 1.5216 31.2974 12.1139
0.9856 5.0 4920 1.5155 31.7487 12.0509
0.8635 6.0 5904 1.5146 32.1394 12.1887
0.7871 7.0 6888 1.5223 32.7087 12.2431
0.7064 8.0 7872 1.5384 33.1917 12.1409
0.6409 9.0 8856 1.5408 33.1944 12.2599

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1