bert_large_cnn_daily2

This model is a fine-tuned version of alexdg19/bert_large_cnn_daily on the cnn_dailymail dataset. It achieves the following results on the evaluation set:

• Loss: 1.3008
• Rouge1: 0.4504
• Rouge2: 0.2337
• Rougel: 0.3294
• Rougelsum: 0.424
• Gen Len: 60.2728

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: 3
• eval_batch_size: 3
• seed: 42
• gradient_accumulation_steps: 3
• total_train_batch_size: 9
• 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
1.1882	1.0	1021	1.1904	0.4379	0.223	0.318	0.41	61.3551
0.9513	2.0	2042	1.1891	0.4506	0.2353	0.3312	0.4239	59.6771
0.7581	3.0	3064	1.2440	0.4488	0.2317	0.3273	0.4214	59.9909
0.6364	4.0	4084	1.3008	0.4504	0.2337	0.3294	0.424	60.2728

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1