v4-my_awesome

This model is a fine-tuned version of Patcas/plbart-works on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0897

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	230	0.9567
No log	2.0	460	0.8849
0.9747	3.0	690	0.8750
0.9747	4.0	920	0.9034
0.3363	5.0	1150	0.9130
0.3363	6.0	1380	0.9173
0.1657	7.0	1610	0.9336
0.1657	8.0	1840	0.9556
0.0957	9.0	2070	0.9811
0.0957	10.0	2300	0.9835
0.0625	11.0	2530	0.9950
0.0625	12.0	2760	0.9918
0.0625	13.0	2990	1.0242
0.0429	14.0	3220	1.0211
0.0429	15.0	3450	1.0181
0.0317	16.0	3680	1.0250
0.0317	17.0	3910	1.0389
0.0244	18.0	4140	1.0467
0.0244	19.0	4370	1.0638
0.0192	20.0	4600	1.0697
0.0192	21.0	4830	1.0614
0.0124	22.0	5060	1.0723
0.0124	23.0	5290	1.0754
0.0122	24.0	5520	1.0809
0.0122	25.0	5750	1.0854
0.0122	26.0	5980	1.0937
0.0085	27.0	6210	1.0886
0.0085	28.0	6440	1.0892
0.0072	29.0	6670	1.0896
0.0072	30.0	6900	1.0897

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0