results

This model is a fine-tuned version of gagan3012/k2t on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5481
• Rouge1: 65.0534
• Rouge2: 45.7092
• Rougel: 55.8222
• Rougelsum: 57.1866
• Gen Len: 17.8061

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.5049	1.0	1101	0.5527	65.0475	45.6298	55.8323	57.2102	17.7929
0.4994	2.0	2202	0.5490	65.0567	45.7082	55.8808	57.2343	17.8005
0.4969	3.0	3303	0.5481	65.0534	45.7092	55.8222	57.1866	17.8061

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1