flan-t5-base-samsum-tiny

This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5151
• Rouge1: 47.0628
• Rouge2: 22.7811
• Rougel: 38.9719
• Rougelsum: 42.8569
• Gen Len: 17.68

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: 5e-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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	13	1.5191	46.3183	22.8147	39.5293	42.4343	16.76
No log	2.0	26	1.5157	46.7913	22.5395	39.2556	42.831	17.26
No log	3.0	39	1.5151	47.0628	22.7811	38.9719	42.8569	17.68
No log	4.0	52	1.5185	46.5019	22.5028	38.142	42.2845	17.57
No log	5.0	65	1.5198	46.6278	22.5381	38.2493	42.505	17.59

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1