english-to-hindi-colloquial

This model is a fine-tuned version of unsloth/tinyllama-chat-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:

• Loss: 9.2932

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: 0.0003
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
14.8489	0.8	2	9.2917
14.8337	1.4	4	9.2917
14.802	2.0	6	9.2917
14.8105	2.8	8	9.2917
14.8631	3.4	10	9.2917
14.7616	4.0	12	9.2917
14.8257	4.8	14	9.2917
14.7342	5.4	16	9.2917
13.0498	6.0	18	9.2930
9.3032	6.8	20	9.2932

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0