deberta-v3-base-finetuned-context_relevance_judge

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 6.6398
• Accuracy: 0.3418

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: 5e-06
• train_batch_size: 2
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.992	93	1.6678	0.0
No log	1.9973	187	4.0565	0.2880
No log	2.992	280	6.1461	0.2846
No log	3.9973	374	5.9717	0.3461
No log	4.992	467	6.4312	0.3327
0.1469	5.9973	561	6.5153	0.3410
0.1469	6.992	654	6.6398	0.3418

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.0
• Datasets 3.1.0
• Tokenizers 0.20.3