nvl

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

• Loss: 1.7103
• Rouge1: 42.7355
• Rouge2: 19.1453
• Rougel: 35.3875
• Rougelsum: 39.3317
• Gen Len: 16.8694

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
2.0196	1.0	1842	1.7910	40.8317	17.2049	33.7121	37.4759	16.8388
1.8885	2.0	3684	1.7466	41.8713	18.2939	34.7126	38.3646	16.6862
1.8233	3.0	5526	1.7264	42.2002	18.8391	35.044	38.8975	17.1184
1.8024	4.0	7368	1.7131	42.5292	19.118	35.4246	39.2763	16.8339
1.7821	5.0	9210	1.7103	42.7355	19.1453	35.3875	39.3317	16.8694

Framework versions

• Transformers 4.36.1
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0