adima_training_new – AI Model by Arnold145 | AlphaNeural AI

You can deploy this model and start earning money today!

Arnold145/
adima_training_new

like

0

generated_from_trainer

openai/whisper-medium

endpoints_compatible

Views

No views yet

adima_training_new

This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6991
Accuracy: 0.4457
F1: 0.6081
Precision: 0.4396
Recall: 0.9861
Auc: 0.5362

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: 8
eval_batch_size: 8
seed: 42
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
lr_scheduler_warmup_steps: 100
num_epochs: 6
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Auc
0.7399	1.0	25	0.7019	0.4375	0.6018	0.4304	1.0	0.5045
0.7101	2.0	50	0.6837	0.6625	0.5846	0.6129	0.5588	0.7033
0.7101	3.0	75	0.6608	0.575	0.0	0.0	0.0	0.8223
0.6606	4.0	100	0.6394	0.575	0.0	0.0	0.0	0.8504
0.6606	5.0	125	0.6192	0.6	0.1111	1.0	0.0588	0.8600
0.6128	6.0	150	0.6126	0.6125	0.1622	1.0	0.0882	0.8600

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1