resnet-152_rice-leaf-disease-augmented-v4_tl

This model is a fine-tuned version of microsoft/resnet-152 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2256
• Accuracy: 0.6477

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: 0.0003
• train_batch_size: 64
• eval_batch_size: 64
• 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_with_restarts
• lr_scheduler_warmup_steps: 256
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0703	0.5	64	2.0574	0.2383
2.0334	1.0	128	2.0009	0.3826
1.9632	1.5	192	1.9175	0.4732
1.8743	2.0	256	1.8030	0.5570
1.7723	2.5	320	1.7035	0.6007
1.6895	3.0	384	1.6242	0.5839
1.6201	3.5	448	1.5710	0.5839
1.5769	4.0	512	1.5331	0.6074
1.5417	4.5	576	1.5034	0.6107
1.5175	5.0	640	1.4916	0.5940
1.5083	5.5	704	1.4881	0.6074
1.5006	6.0	768	1.4846	0.6040
1.5107	6.5	832	1.4729	0.5805
1.4573	7.0	896	1.4234	0.6174
1.4301	7.5	960	1.3880	0.6174
1.3891	8.0	1024	1.3660	0.6174
1.3551	8.5	1088	1.3354	0.6275
1.3576	9.0	1152	1.3350	0.6208
1.348	9.5	1216	1.3226	0.6342
1.3288	10.0	1280	1.3211	0.6376
1.3361	10.5	1344	1.3302	0.6242
1.3256	11.0	1408	1.2959	0.6275
1.2922	11.5	1472	1.2862	0.6342
1.2886	12.0	1536	1.2463	0.6443
1.263	12.5	1600	1.2523	0.6309
1.2471	13.0	1664	1.2478	0.6409
1.2389	13.5	1728	1.2363	0.6141
1.2352	14.0	1792	1.2276	0.6409
1.2292	14.5	1856	1.2252	0.6510
1.2203	15.0	1920	1.2256	0.6477

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0