T5-JSON-OM-IMP

This model is a fine-tuned version of T5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0946
• Micro Precision: 0.3295
• Micro Recall: 0.3853
• Micro F1: 0.3552
• Macro Precision: 0.3295
• Macro Recall: 0.3853
• Macro F1: 0.3552
• Bleu: 77.6645
• Rouge1: 0.7910
• Rouge2: 0.5470

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: 8
• eval_batch_size: 8
• seed: 42
• 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
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Micro Precision	Micro Recall	Micro F1	Macro Precision	Macro Recall	Macro F1	Bleu	Rouge1	Rouge2
0.1167	1.0	468	0.0975	0.2817	0.4680	0.3517	0.2817	0.4680	0.3517	75.2453	0.7657	0.5238
0.1103	2.0	936	0.0953	0.2956	0.4421	0.3543	0.2956	0.4421	0.3543	75.8760	0.7700	0.5180
0.1022	3.0	1404	0.0941	0.2897	0.4452	0.3510	0.2897	0.4452	0.3510	75.7205	0.7651	0.5213
0.1072	4.0	1872	0.0946	0.3295	0.3853	0.3552	0.3295	0.3853	0.3552	77.6645	0.7910	0.5470

Framework versions

• Transformers 4.51.1
• Pytorch 2.8.0.dev20250409+cu128
• Datasets 3.5.0
• Tokenizers 0.21.1