resume6

This model is a fine-tuned version of AKbuyer/resume5 on the multi_news dataset. It achieves the following results on the evaluation set:

• Loss: 2.9796
• Rouge1: 22.1762
• Rouge2: 6.6459
• Rougel: 18.3710
• Rougelsum: 18.3626
• Gen Len: 1893.4899

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-07
• 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: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.3348	1.0	5622	3.0918	21.3362	6.1922	17.7104	17.6992	1893.0630
3.2854	2.0	11244	3.0466	21.6506	6.3791	17.9362	17.9246	1891.6044
3.2205	3.0	16866	3.0200	21.8475	6.4847	18.0981	18.0882	1892.4760
3.2251	4.0	22488	3.0029	22.0082	6.5196	18.2405	18.2301	1892.9385
3.2348	5.0	28110	2.9916	22.1078	6.5975	18.3134	18.2985	1893.3298
3.2257	6.0	33732	2.9845	22.1627	6.6119	18.3677	18.3496	1893.5788
3.2106	7.0	39354	2.9806	22.1825	6.6472	18.3798	18.3664	1893.5432
3.22	8.0	44976	2.9796	22.1762	6.6459	18.3710	18.3626	1893.4899

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3