slue_ted_finetuned

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

• Loss: 2.7886
• Rouge1: 0.328
• Rouge2: 0.099
• Rougel: 0.209
• Rougelsum: 0.209
• Gen Len: 92.7059

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.629	1.1820	500	2.5146	0.3005	0.0852	0.1856	0.1859	98.4
2.3239	2.3641	1000	2.5345	0.3123	0.0936	0.1952	0.1953	96.6
1.9514	3.5461	1500	2.5620	0.3183	0.0954	0.2009	0.2007	86.6824
1.6195	4.7281	2000	2.6603	0.3219	0.098	0.2027	0.2028	101.4047
1.3301	5.9102	2500	2.7886	0.328	0.099	0.209	0.209	92.7059

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1