flan-t5-base-samsum

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: 1.3692
• Rouge1: 47.2141
• Rouge2: 23.4837
• Rougel: 39.7822
• Rougelsum: 43.2157
• Gen Len: 17.1612

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.4566	1.0	1842	1.3834	46.9151	22.8925	39.1161	43.0414	17.4493
1.3394	2.0	3684	1.3741	47.2947	23.5658	39.8063	43.487	17.1819
1.2786	3.0	5526	1.3692	47.2141	23.4837	39.7822	43.2157	17.1612
1.2274	4.0	7368	1.3776	47.6914	24.1243	40.1764	43.9611	17.4042
1.2028	5.0	9210	1.3771	47.3328	23.5144	39.6487	43.4161	17.2357

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0+cu118
• Datasets 2.19.0
• Tokenizers 0.19.1