bart-large-cnn-finetuned-pubmed-finetuned-roundup-e16

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

• Loss: 2.6815
• Rouge1: 48.7608
• Rouge2: 29.554
• Rougel: 30.5554
• Rougelsum: 46.4001
• Gen Len: 142.0

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 16
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	25	1.4287	46.5701	28.6267	34.7827	45.0622	142.0
No log	2.0	50	1.4419	46.6171	27.4276	31.0085	43.1797	142.0
No log	3.0	75	1.5418	50.1144	29.3433	32.0144	46.9217	142.0
No log	4.0	100	1.7125	49.1395	28.611	30.9759	46.8346	142.0
No log	5.0	125	1.8978	43.9629	24.1224	26.0032	41.2272	142.0
No log	6.0	150	2.0990	49.0579	29.5182	31.5829	46.0207	142.0
No log	7.0	175	2.2380	48.8754	27.7691	28.8597	45.3281	142.0
No log	8.0	200	2.2922	48.311	29.2517	33.8241	46.6099	142.0
No log	9.0	225	2.3820	45.4663	23.9904	27.5497	41.9446	142.0
No log	10.0	250	2.4856	48.2224	27.7455	28.159	45.4726	142.0
No log	11.0	275	2.4731	46.1799	22.1941	26.8254	43.9986	142.0
No log	12.0	300	2.5278	47.8623	27.6514	26.6377	42.9255	142.0
No log	13.0	325	2.6229	45.573	25.4966	27.7158	42.2306	142.0
No log	14.0	350	2.6032	48.1972	27.0387	28.336	45.0293	142.0
No log	15.0	375	2.6600	47.7301	27.3567	29.3389	44.3516	142.0
No log	16.0	400	2.6815	48.7608	29.554	30.5554	46.4001	142.0

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0+cu113
• Datasets 2.1.0
• Tokenizers 0.12.1