You can deploy this model and start earning money today!

haval995/
results_v2.2

Name: results_v2.2
Availability: InStock

Views

No views yet

results_v2.2

This model is a fine-tuned version of haval995/roberta-large-causal-hallucination-detector_V_2.1 on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 6
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Supported	Recall Supported	F1 Hallucination	Recall Hallucination
0.6675	1.0	54	0.3172	0.9338	0.9334	0.9286	0.9848	0.9383	0.8941
0.5336	2.0	108	0.3151	0.9404	0.9395	0.9323	0.9394	0.9467	0.9412
0.5047	3.0	162	0.3452	0.9470	0.9466	0.9420	0.9848	0.9512	0.9176
0.4754	4.0	216	0.3812	0.9205	0.9202	0.9155	0.9848	0.925	0.8706
0.4676	5.0	270	0.3236	0.9470	0.9465	0.9412	0.9697	0.9518	0.9294