rate-jokes-bert

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.0871
• F1: 0.0444

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-06
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	64	2.4209	0.0028
No log	2.0	128	2.3785	0.0130
No log	3.0	192	2.3215	0.0729
No log	4.0	256	2.1787	0.0444
No log	5.0	320	2.1038	0.0444
No log	6.0	384	2.0944	0.0444
No log	7.0	448	2.0911	0.0444
2.2915	8.0	512	2.0901	0.0444
2.2915	9.0	576	2.0892	0.0444
2.2915	10.0	640	2.0871	0.0444

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3