fb-bart-large-finetuned-trade-the-event-finance-summarizer-finetuned-roundup-1-4

This model is a fine-tuned version of nickmuchi/fb-bart-large-finetuned-trade-the-event-finance-summarizer on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8305
• Rouge1: 54.122
• Rouge2: 35.2787
• Rougel: 37.6989
• Rougelsum: 51.4679
• 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: 1
• eval_batch_size: 1
• 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
1.7158	1.0	795	0.9986	53.1755	33.3503	35.235	50.6513	142.0
0.7643	2.0	1590	0.8622	53.3646	34.429	36.7998	51.0487	141.1852
0.5894	3.0	2385	0.8345	54.2777	35.0495	37.8567	51.7937	142.0
0.4039	4.0	3180	0.8305	54.122	35.2787	37.6989	51.4679	142.0

Framework versions

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