test-dialogue-summarization

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: 0.9653
• Rouge1: 61.2091
• Rouge2: 36.8979
• Rougel: 46.3962
• Rougelsum: 58.3082
• Gen Len: 135.6733

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	94	1.3755	53.9112	25.5975	36.8507	50.0306	132.7733
No log	2.0	188	1.2081	55.5956	27.4849	37.7785	51.7906	137.1267
No log	3.0	282	1.1149	55.714	28.3629	39.0763	52.439	137.62
No log	4.0	376	1.0564	56.6202	29.789	39.9223	53.3054	135.1733
No log	5.0	470	1.0107	57.8272	31.5716	41.9775	54.5114	135.1733
1.1609	6.0	564	0.9775	58.561	32.5462	42.9577	55.1653	133.5533
1.1609	7.0	658	0.9683	59.0592	33.8153	43.918	56.0493	135.3267
1.1609	8.0	752	0.9626	60.4587	35.8511	45.9511	57.3658	134.38
1.1609	9.0	846	0.9623	60.3938	35.8996	45.7161	57.2104	135.2333
1.1609	10.0	940	0.9653	61.2091	36.8979	46.3962	58.3082	135.6733

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.2
• Tokenizers 0.13.3