fia24's picture
Final One
906e0f6
|
raw
history blame
1.31 kB
metadata
base_model: csebuetnlp/banglat5
tags:
  - generated_from_trainer
model-index:
  - name: banel_with_pos_banglat5_v0.1.2.3.4
    results: []

banel_with_pos_banglat5_v0.1.2.3.4

This model is a fine-tuned version of csebuetnlp/banglat5 on an unknown dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.2303
  • eval_Val Accuracy: 0.911
  • eval_gen_len: 2.2765
  • eval_runtime: 24.2715
  • eval_samples_per_second: 92.083
  • eval_steps_per_second: 2.884
  • epoch: 27.0
  • step: 1620

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: 0.0001
  • train_batch_size: 300
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Framework versions

  • Transformers 4.34.1
  • Pytorch 1.13.1+cu117
  • Datasets 2.14.6
  • Tokenizers 0.14.1