Edit model card

temp_assamese

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

  • Loss: 1.4149
  • Accuracy: 0.7014

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: 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: 2.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.2163 0.1409 2000 1.8646 0.6320
1.9456 0.2818 4000 1.7492 0.6495
1.8391 0.4227 6000 1.6770 0.6606
1.7704 0.5637 8000 1.6166 0.6707
1.7213 0.7046 10000 1.5818 0.6759
1.6802 0.8455 12000 1.5403 0.6820
1.6432 0.9864 14000 1.5153 0.6858
1.6074 1.1273 16000 1.4965 0.6885
1.5833 1.2682 18000 1.4678 0.6934
1.5649 1.4091 20000 1.4508 0.6950
1.553 1.5501 22000 1.4367 0.6985
1.5345 1.6910 24000 1.4231 0.7001
1.5261 1.8319 26000 1.4157 0.7013
1.5148 1.9728 28000 1.4098 0.7027

Framework versions

  • Transformers 4.43.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
238M 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.

Model tree for pritamdeka/muril-base-cased-assamese

Finetuned
(19)
this model