t5_lora_finetuned

This model is a fine-tuned version of t5-small on MS MARCO dataset.

Model description

This model is a fine-tuned version of T5 small text to text generation model.

Intended uses & limitations

Model is fine tuned for the context based query answering task.

Training and evaluation data

• Training data ~ 35,000
• evaluation data ~ 2,000
• input data format - "Answer the question {question} based on the context {context}"

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use 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: 500
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

• training loss at 1% : 15
• training loss at 50% : 0.17
• training loss 100% : 0.17

Framework versions

• PEFT 0.14.0
• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0