Dataset Used

• Dataset Name: BanusreeM/sawit-swn
• Description: Tamil colloquial dataset for translation tasks.
• Total Entries: 50
• Example Query-Answer Pairs:
  • English: "What is the eligibility criteria for JEE MAINS"
  • Tamil Colloquial: "JEE MAINS thervil servatharku yenna thaguthi thevai"

sawit-tamil-chatbot

This model is a fine-tuned version of unsloth/tinyllama-chat-bnb-4bit on BanusreeM/sawit-swn dataset. It achieves the following results on the evaluation set:

• Loss: 10.4634

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: 4
• eval_batch_size: 4
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	10	10.4631
No log	2.0	20	10.4632
No log	3.0	30	10.4633
No log	4.0	40	10.4634
No log	5.0	50	10.4634

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0