This model is a fine-tuned version of timm/mobilenetv3_small_100.lamb_in1k on the slotwhisperer/symbols-clf dataset. It achieves the following results on the evaluation set:

Loss: 1.6815
Accuracy: 0.8889

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-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
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
num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	4	3.1175	0.0556
No log	2.0	8	2.8743	0.1667
No log	3.0	12	2.5718	0.3333
No log	4.0	16	2.2845	0.8333
No log	5.0	20	2.1047	0.8333
No log	6.0	24	1.9366	0.8333
No log	7.0	28	1.7910	0.8333
No log	8.0	32	1.6815	0.8889
No log	9.0	36	1.5946	0.8889
No log	10.0	40	1.5051	0.8889
No log	11.0	44	1.3821	0.8889
No log	12.0	48	1.2910	0.8889
No log	13.0	52	1.2662	0.8889
No log	14.0	56	1.2408	0.8889
No log	15.0	60	1.1884	0.8889
No log	16.0	64	1.1121	0.8889
No log	17.0	68	1.1140	0.8889
No log	18.0	72	1.0818	0.8889
No log	19.0	76	1.0813	0.8889
No log	20.0	80	1.0582	0.8889

Framework versions

Transformers 5.8.1
Pytorch 2.12.0+cu130
Datasets 4.8.5
Tokenizers 0.22.2

slotwhisperer/symbols-mnv3

symbols-mnv3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

slotwhisperer/
symbols-mnv3