article2keyword2.1b_barthez-orangesum-title_finetuned16_for_mlm

This model is a fine-tuned version of moussaKam/barthez-orangesum-title on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0525

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: 4
• eval_batch_size: 4
• 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
0.2976	1.0	1353	0.0543
0.0566	2.0	2706	0.0509
0.0487	3.0	4059	0.0458
0.0433	4.0	5412	0.0456
0.04	5.0	6765	0.0460
0.0373	6.0	8118	0.0454
0.0355	7.0	9471	0.0465
0.0328	8.0	10824	0.0474
0.0317	9.0	12177	0.0470
0.03	10.0	13530	0.0488
0.0285	11.0	14883	0.0489
0.0272	12.0	16236	0.0500
0.0262	13.0	17589	0.0510
0.0258	14.0	18942	0.0511
0.0245	15.0	20295	0.0522
0.0239	16.0	21648	0.0525

Framework versions

• Transformers 4.21.1
• Pytorch 1.11.0
• Datasets 2.3.2
• Tokenizers 0.12.1