electra_small_layers_6_multi

This model is a fine-tuned version of toastynews/electra-hongkongese-small-discriminator on AlienKevin/hkcancor-multi and AlienKevin/wiki-yue-long-multi.

See https://github.com/AlienKevin/dips for details.

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.4.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
5
Safetensors
Model size
8.68M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for AlienKevin/electra-hongkongese-small-6-dropped-distilled-hkcancor-multi

Finetuned
(5)
this model
Finetunes
1 model

Datasets used to train AlienKevin/electra-hongkongese-small-6-dropped-distilled-hkcancor-multi

Collection including AlienKevin/electra-hongkongese-small-6-dropped-distilled-hkcancor-multi