Pstman/Text_summarization

my_text_sum_model

This model is a fine-tuned version of facebook/bart-large-cnn on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1211
• Rouge1: 0.3212
• Rouge2: 0.1225
• Rougel: 0.2329
• Rougelsum: 0.2327
• Gen Len: 65.4998

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: 8
• eval_batch_size: 8
• 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
1.8113	1.0	1134	1.7859	0.3221	0.1245	0.2348	0.2348	64.0653
1.3327	2.0	2268	1.8142	0.3248	0.1255	0.2368	0.2368	64.2325
0.9968	3.0	3402	1.9795	0.3215	0.1236	0.2335	0.2335	65.0935
0.7786	4.0	4536	2.1211	0.3212	0.1225	0.2329	0.2327	65.4998

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3