english-tamil-colloquial-translator

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

• Loss: 1.0137
• Model Preparation Time: 0.0065

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 100
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
No log	0.0025	2	1.0126	0.0065
No log	0.0050	4	1.0131	0.0065
No log	0.0075	6	1.0138	0.0065
No log	0.0100	8	1.0126	0.0065
0.4113	0.0125	10	1.0137	0.0065
0.4113	0.0150	12	1.0131	0.0065
0.4113	0.0175	14	1.0137	0.0065

Framework versions

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