dialogue-pro-spanbert-samsum

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

• Loss: 0.3251
• Rouge1: 47.8977
• Rouge2: 24.7025
• Rougel: 40.4035
• Rougelsum: 40.4188
• Gen Len: 18.2482

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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
0.3887	1.0	1841	0.3397	46.5	23.7748	39.5841	39.5711	17.687
0.3484	2.0	3682	0.3263	48.0505	24.476	40.1212	40.1016	18.2005
0.3249	3.0	5523	0.3251	47.8977	24.7025	40.4035	40.4188	18.2482

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.1+cu102
• Datasets 2.10.1
• Tokenizers 0.12.1