testhehehe

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

• Loss: 0.6675
• Accuracy: 0.667
• True Positive: 0.0
• False Negative: 1.0
• False Positive: 0.0
• True Negative: 1.0
• F1: 0.8002

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	True Positive	False Negative	False Positive	True Negative	F1
No log	0.4375	7	0.7175	0.333	1.0	0.0	1.0	0.0	0.0
No log	0.875	14	0.6894	0.679	0.0871	0.9129	0.0255	0.9745	0.802
No log	1.3125	21	0.6765	0.667	0.0	1.0	0.0	1.0	0.8002
No log	1.75	28	0.6675	0.667	0.0	1.0	0.0	1.0	0.8002

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0+cu121
• Datasets 2.19.2
• Tokenizers 0.20.0