bart-mawpnli-calcx-nli-pt

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

• Loss: 0.1453
• Rouge1: 93.7662
• Rouge2: 86.4184
• Rougel: 93.67
• Rougelsum: 93.6822
• Gen Len: 12.2028

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.2619	1.0	819	0.1578	91.4167	81.2366	91.3175	91.299	11.9994
0.0848	2.0	1638	0.1296	92.7573	84.2145	92.6627	92.6429	12.2395
0.0537	3.0	2457	0.1217	93.2594	85.3616	93.145	93.1393	12.1851
0.0278	4.0	3276	0.1358	93.6089	86.1785	93.473	93.4733	12.2272
0.0119	5.0	4095	0.1453	93.7662	86.4184	93.67	93.6822	12.2028

Framework versions

• Transformers 4.35.2
• Pytorch 1.12.1+cu113
• Datasets 2.15.0
• Tokenizers 0.15.0