gec-flan-t5-large-stage-2-v2

This model is a fine-tuned version of 512duncanl/gec-flan-t5-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1958
• F0.5: 0.6534
• Precision: 0.6913
• Recall: 0.5357

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: 2e-05
• train_batch_size: 22
• eval_batch_size: 22
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 3
• total_train_batch_size: 66
• 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_ratio: 0.05
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	F0.5	Precision	Recall
0.2382	1.0	561	0.2082	0.6463	0.6877	0.5208
0.2283	2.0	1122	0.1958	0.6534	0.6913	0.5357

Framework versions

• Transformers 4.53.2
• Pytorch 2.7.1+cu128
• Datasets 4.0.0
• Tokenizers 0.21.2