colloquial-tamil-finetuned

This model is a fine-tuned version of aishu15/colloquial-tamil on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0443

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.1624 1.0 4124 0.1008
0.1027 2.0 8248 0.0577
0.0786 3.0 12372 0.0443

Framework versions

  • Transformers 4.48.3
  • Pytorch 2.5.1+cu124
  • Tokenizers 0.21.0
Downloads last month
46
Safetensors
Model size
484M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for aishu15/colloquial-tamil-finetuned

Finetuned
(1)
this model