flan-t5-small-whatsapp

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

• Loss: 1.5161
• Rouge1: 45.0756
• Rouge2: 21.3799
• Rougel: 37.9259
• Rougelsum: 41.4556
• Gen Len: 16.8473

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_FUSED 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
1.7382	1.0	1473	1.5392	44.1043	20.6892	37.1335	40.6217	16.7927
1.6917	2.0	2946	1.5248	44.9155	21.1499	37.6038	41.2823	16.9766
1.6439	3.0	4419	1.5239	44.5618	21.1748	37.6957	41.0448	16.6569
1.6201	4.0	5892	1.5161	45.0756	21.3799	37.9259	41.4556	16.8473
1.6141	5.0	7365	1.5190	44.6749	21.1746	37.6368	41.1283	16.8297

Framework versions

• Transformers 5.6.2
• Pytorch 2.10.0+cu128
• Datasets 4.8.4
• Tokenizers 0.22.2