Edit model card

Visualize in Weights & Biases Visualize in Weights & Biases

hubert-amharic

This model is a fine-tuned version of facebook/hubert-base-ls960 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1964
  • Accuracy: 0.9535

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: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • 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 Accuracy
0.5372 2.0202 500 0.3764 0.8929
0.2254 4.0404 1000 0.3798 0.9111
0.1699 6.0606 1500 0.1964 0.9535
0.1245 8.0808 2000 0.2290 0.9596
0.0597 10.1010 2500 0.2243 0.9636
0.0816 12.1212 3000 0.2717 0.9556

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.1.2
  • Datasets 2.19.1.dev0
  • Tokenizers 0.19.1
Downloads last month
6
Safetensors
Model size
95M params
Tensor type
F32
·
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for Gizachew/hubert-amharic

Finetuned
(67)
this model