my_awesome_longformer_model

This model is a fine-tuned version of allenai/led-base-16384 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4077
• Rouge1: 0.0238
• Rouge2: 0.0067
• Rougel: 0.0222
• Rougelsum: 0.0239
• Gen Len: 20.0

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	1	2.8467	0.0088	0.0	0.0088	0.0086	20.0
No log	2.0	2	1.8386	0.0244	0.0032	0.0204	0.0219	20.0
No log	3.0	3	1.5336	0.0231	0.0048	0.0214	0.0228	20.0
No log	4.0	4	1.4077	0.0238	0.0067	0.0222	0.0239	20.0

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2