insightSumm_t5_finetuned_model_final-insightSumm__2025-05-06_02.19.20

This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3468
• Rouge1: 89.1089
• Rouge2: 86.5989
• Rougel: 88.8703
• Rougelsum: 88.8963

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: 16
• eval_batch_size: 16
• seed: 42
• 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
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.2422	1.0	3168	0.3808	88.8866	86.4314	88.6547	88.6723
0.2168	2.0	6336	0.3629	88.9098	86.4533	88.6846	88.7028
0.6073	3.0	9504	0.3476	89.0326	86.5194	88.786	88.8062
0.3439	4.0	12672	0.3468	89.1089	86.5989	88.8703	88.8963
0.4147	5.0	15840	0.3453	89.0482	86.5523	88.8104	88.8276

Framework versions

• Transformers 4.49.0
• Pytorch 2.7.0+cu126
• Datasets 3.5.1
• Tokenizers 0.21.1