flan-t5-base

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: 0.4831

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: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.4397	1.0	11	0.4739
0.4047	2.0	22	0.4714
0.3615	3.0	33	0.4707
0.3797	4.0	44	0.4498
0.3422	5.0	55	0.4552
0.3346	6.0	66	0.4707
0.3242	7.0	77	0.4753
0.2907	8.0	88	0.4676
0.2846	9.0	99	0.4705
0.2752	10.0	110	0.4766
0.2688	11.0	121	0.4681
0.2654	12.0	132	0.4879
0.2581	13.0	143	0.4866
0.2483	14.0	154	0.4824
0.2508	15.0	165	0.4948
0.2408	16.0	176	0.4868
0.251	17.0	187	0.4830
0.2368	18.0	198	0.4824
0.2465	19.0	209	0.4824
0.2422	20.0	220	0.4831

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0