v5-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: 1.0208

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	264	0.9325
1.0258	2.0	528	0.8500
1.0258	3.0	792	0.8358
0.3925	4.0	1056	0.8538
0.3925	5.0	1320	0.8462
0.2	6.0	1584	0.9122
0.2	7.0	1848	0.8987
0.1246	8.0	2112	0.8859
0.1246	9.0	2376	0.8990
0.0834	10.0	2640	0.9022
0.0834	11.0	2904	0.9212
0.058	12.0	3168	0.9542
0.058	13.0	3432	0.9466
0.0431	14.0	3696	0.9615
0.0431	15.0	3960	0.9675
0.0321	16.0	4224	0.9719
0.0321	17.0	4488	0.9786
0.0237	18.0	4752	0.9918
0.0189	19.0	5016	0.9911
0.0189	20.0	5280	0.9983
0.0143	21.0	5544	0.9973
0.0143	22.0	5808	1.0100
0.0129	23.0	6072	1.0160
0.0129	24.0	6336	1.0091
0.0097	25.0	6600	1.0191
0.0097	26.0	6864	1.0224
0.0084	27.0	7128	1.0238
0.0084	28.0	7392	1.0201
0.0079	29.0	7656	1.0200
0.0079	30.0	7920	1.0208

Framework versions

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