gec-flan-t5-large-stage-2-v3

This model is a fine-tuned version of 512duncanl/gec-flan-t5-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2224
• F0.5: 0.6616
• Precision: 0.7074
• Recall: 0.5254

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: 1e-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: constant_with_warmup
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	F0.5	Precision	Recall
0.2945	1.0	561	0.2372	0.6601	0.7110	0.5133
0.2459	2.0	1122	0.2224	0.6616	0.7074	0.5254

Framework versions

• Transformers 4.54.0
• Pytorch 2.7.1+cu128
• Datasets 4.0.0
• Tokenizers 0.21.2