pcam-interpretability/resnet50-val08933-resnet-tuned-sota

resnet50

Best Validation Accuracy: 0.8933

Metadata

• Model Name: resnet50
• Optimizer: adamw
• Scheduler: cosine
• Weight Decay: 0.0005
• Warmup Epochs: 3
• Patience: 10
• Amp: True
• Seed: 42
• Batch Size: 32
• Initial Lr: 0.0005
• Total Epochs Ran: 23
• Early Stopped: True
• Training Time Seconds: 54549.823322057724
• Num Parameters: 22067009
• Device: NVIDIA A100-SXM4-40GB
• Run Id: resnet-tuned-sota

Training Configuration

• Epochs: 23
• Batch size: 32
• Learning rate (initial): 0.0005

Training Logs (Per Epoch)

Epoch	Train Loss	Train Acc	Val Loss	Val Acc	LR
1	0.3234	0.8624	0.2944	0.8783	0.000167
2	0.2762	0.8876	0.3729	0.8444	0.000333
3	0.2600	0.8955	0.4210	0.8333	0.000500
4	0.2325	0.9082	0.4866	0.8172	0.000500
5	0.2136	0.9169	0.3266	0.8844	0.000500
6	0.1992	0.9234	0.4922	0.8232	0.000498
7	0.1883	0.9283	0.3691	0.8651	0.000496
8	0.1794	0.9327	0.3691	0.8743	0.000492
9	0.1722	0.9354	0.3569	0.8720	0.000488
10	0.1640	0.9392	0.5330	0.8265	0.000482
11	0.1591	0.9410	0.3193	0.8854	0.000476
12	0.1543	0.9430	0.4663	0.8514	0.000469
13	0.1495	0.9444	0.3060	0.8933	0.000461
14	0.1430	0.9471	0.4198	0.8758	0.000452
15	0.1389	0.9491	0.3489	0.8885	0.000443
16	0.1347	0.9507	0.4273	0.8712	0.000432
17	0.1303	0.9521	0.4914	0.8585	0.000421
18	0.1273	0.9535	0.4911	0.8599	0.000409
19	0.1231	0.9554	0.4286	0.8658	0.000397
20	0.1190	0.9568	0.5047	0.8569	0.000384
21	0.1156	0.9579	0.4728	0.8651	0.000370
22	0.1118	0.9597	0.3897	0.8899	0.000356
23	0.1104	0.9599	0.5710	0.8513	0.000342