flan-t5-base-max

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

• Loss: 1.3767
• Rouge1: 47.658
• Rouge2: 23.8342
• Rougel: 39.8959
• Rougelsum: 43.9372
• Gen Len: 18.0037

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 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
1.4528	1.0	1842	1.3867	47.1561	23.0232	39.2965	43.2173	18.0794
1.3385	2.0	3684	1.3751	47.261	23.4468	39.3675	43.388	18.0098
1.2791	3.0	5526	1.3695	47.6429	23.7409	39.7882	43.6692	17.6654
1.2262	4.0	7368	1.3761	47.8213	24.0947	40.0904	44.0943	18.0256
1.2035	5.0	9210	1.3767	47.658	23.8342	39.8959	43.9372	18.0037

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0