distilbert-base-uncased-finetuned-moral-action

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4632
• Accuracy: 0.7912
• F1: 0.7912

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: 9.716387809233253e-05
• train_batch_size: 2000
• eval_batch_size: 2000
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	10	0.5406	0.742	0.7399
No log	2.0	20	0.4810	0.7628	0.7616
No log	3.0	30	0.4649	0.786	0.7856
No log	4.0	40	0.4600	0.7916	0.7916
No log	5.0	50	0.4632	0.7912	0.7912

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.1
• Datasets 2.0.0
• Tokenizers 0.11.0