baseline_1-seed_2025

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

• Loss: 3.0203
• Precision: 0.6238
• Recall: 0.7029
• F1: 0.6610

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 2025
• 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.1713	1.0	447	1.5784	0.6209	0.6884	0.6529
0.1871	2.0	894	1.6753	0.6399	0.6630	0.6512
0.1613	3.0	1341	1.8808	0.6084	0.6304	0.6192
0.1367	4.0	1788	2.2017	0.6164	0.7101	0.6599
0.1101	5.0	2235	2.2647	0.6245	0.5725	0.5974
0.0603	6.0	2682	2.1269	0.6280	0.6667	0.6467
0.0642	7.0	3129	2.4185	0.5971	0.7355	0.6591
0.0757	8.0	3576	2.3896	0.6167	0.6703	0.6424
0.042	9.0	4023	2.1657	0.6295	0.6341	0.6318
0.0506	10.0	4470	2.5379	0.6254	0.7138	0.6667
0.0184	11.0	4917	2.7895	0.6171	0.7065	0.6588
0.0257	12.0	5364	2.9373	0.6246	0.6993	0.6598
0.003	13.0	5811	3.1143	0.6213	0.6775	0.6482
0.0248	14.0	6258	3.0020	0.6287	0.6993	0.6621
0.0002	15.0	6705	3.0203	0.6238	0.7029	0.6610

Framework versions

• Transformers 4.52.0.dev0
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1