bart_left_heading_torch

This model is a fine-tuned version of facebook/bart-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.1853

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: 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	8	10.9542
No log	2.0	16	9.4997
No log	3.0	24	8.7858
No log	4.0	32	8.4885
No log	5.0	40	8.0916
No log	6.0	48	7.9659
No log	7.0	56	7.6608
No log	8.0	64	7.2812
No log	9.0	72	7.0035
No log	10.0	80	6.7113
No log	11.0	88	6.3708
No log	12.0	96	5.9869
No log	13.0	104	5.6537
No log	14.0	112	5.3304
No log	15.0	120	5.0117
No log	16.0	128	4.7120
No log	17.0	136	4.4874
No log	18.0	144	4.3164
No log	19.0	152	4.2133
No log	20.0	160	4.1853

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.1
• Tokenizers 0.13.3