t5gemma-math-corrector

This model is a fine-tuned version of google/t5gemma-s-s-ul2-it on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.8249

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.0085	0.6415	200	0.6018
0.0029	1.2823	400	1.9704
0.001	1.9238	600	3.8351
0.0005	2.5646	800	3.8249

Framework versions

• PEFT 0.17.1
• Transformers 4.55.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4