wiki_asp-animal_7340_bart-base

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

• Loss: 2.5325
• Rouge1: 0.1399
• Rouge2: 0.0606
• Rougel: 0.1236
• Rougelsum: 0.1238
• Gen Len: 15.5516

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.93	500	2.7950	0.1206	0.0456	0.1042	0.1044	15.4938
No log	3.87	1000	2.6359	0.1188	0.0475	0.1037	0.104	14.4579
No log	5.8	1500	2.5695	0.137	0.0571	0.1205	0.1207	15.7157
2.9693	7.74	2000	2.5406	0.1433	0.0611	0.1263	0.1268	15.7796
2.9693	9.67	2500	2.5325	0.1399	0.0606	0.1236	0.1238	15.5516

Framework versions

• Transformers 4.38.2
• Pytorch 2.0.0+cu117
• Datasets 2.18.0
• Tokenizers 0.15.2