baseline_3-seed_42

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: 3.7534
• Precision: 0.3541
• Recall: 0.3913
• F1: 0.3718

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: 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.7008	1.0	447	0.7467	0.4473	1.0	0.6181
0.6933	2.0	894	0.6963	0.45	0.9783	0.6164
0.6772	3.0	1341	0.6932	0.4820	0.8261	0.6088
0.6708	4.0	1788	0.7332	0.4637	0.7174	0.5633
0.6384	5.0	2235	0.8510	0.4468	0.6087	0.5153
0.6096	6.0	2682	0.9629	0.4371	0.4783	0.4567
0.5706	7.0	3129	1.4994	0.4115	0.5978	0.4874
0.5401	8.0	3576	1.6980	0.3933	0.5072	0.4430
0.4697	9.0	4023	2.2275	0.3797	0.4348	0.4054
0.4824	10.0	4470	2.5809	0.3933	0.4674	0.4272
0.4379	11.0	4917	2.6967	0.3742	0.4420	0.4053
0.4328	12.0	5364	2.9542	0.3683	0.4457	0.4033
0.4116	13.0	5811	3.2770	0.3705	0.4094	0.3890
0.3725	14.0	6258	3.3860	0.3543	0.3877	0.3702
0.3673	15.0	6705	3.7534	0.3541	0.3913	0.3718

Framework versions

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