bart-samsum

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

• Loss: 1.4587

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
1.2901	0.64	500	1.2203
1.2057	1.28	1000	1.1384
1.1364	1.93	1500	1.1225
0.9711	2.57	2000	1.1362
0.786	3.21	2500	1.1461
0.818	3.85	3000	1.1298
0.7135	4.49	3500	1.1666
0.6222	5.14	4000	1.2114
0.64	5.78	4500	1.2103
0.5272	6.42	5000	1.2571
0.5057	7.06	5500	1.2963
0.4917	7.7	6000	1.2937
0.4291	8.35	6500	1.3286
0.4171	8.99	7000	1.3125
0.418	9.63	7500	1.3516
0.3576	10.27	8000	1.3778
0.3736	10.91	8500	1.3847
0.3443	11.56	9000	1.4215
0.2952	12.2	9500	1.4324
0.3236	12.84	10000	1.4355
0.2978	13.48	10500	1.4473
0.2828	14.13	11000	1.4557
0.304	14.77	11500	1.4587

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3