Edit model card

HingFlow

It achieves the following results on the evaluation set:

  • Loss: 0.1887
  • Bleu: 72.3468
  • Gen Len: 5.9953

Model description

https://github.com/SRDdev/HingFlow

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: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
0.1505 1.0 1000 0.2053 71.6108 5.8418
0.1057 2.0 2000 0.1887 72.3468 5.9953

Framework versions

  • Transformers 4.29.0
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
26
Safetensors
Model size
75.9M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train SRDdev/HingFlow