swept-brook-197

This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6066
• Accuracy: 0.7402

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: 0.0001
• train_batch_size: 256
• eval_batch_size: 256
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1424	1.0	18	0.9758	0.5527
0.937	2.0	36	0.8802	0.5488
0.9044	3.0	54	0.9013	0.5215
0.8604	4.0	72	0.8435	0.5781
0.8388	5.0	90	0.8415	0.5859
0.8287	6.0	108	0.9338	0.5098
0.8042	7.0	126	0.7766	0.6152
0.7452	8.0	144	0.7439	0.6328
0.701	9.0	162	0.7072	0.6543
0.6725	10.0	180	0.6605	0.7070
0.6326	11.0	198	0.6436	0.7012
0.6066	12.0	216	0.6437	0.7129
0.5878	13.0	234	0.6104	0.7461
0.5813	14.0	252	0.6086	0.7344
0.5753	15.0	270	0.6066	0.7402

Framework versions

• Transformers 4.52.3
• Pytorch 2.7.0+cpu
• Datasets 3.6.0
• Tokenizers 0.21.0