eren23's picture
Upload folder using huggingface_hub
ca085e6 verified
[2025-11-23 19:43:09,008][INFO] Args: {
"accelerator": "auto",
"batch_size": 4,
"callbacks": null,
"checkpoint": null,
"data": "/content/unlabeled_idl_images",
"devices": "auto",
"embed_dim": null,
"epochs": "auto",
"float32_matmul_precision": "auto",
"loader_args": null,
"loggers": null,
"method": "distillationv1",
"method_args": {
"teacher": "dinov3/vitb16"
},
"model": "ultralytics/yolo11m",
"model_args": null,
"num_nodes": 1,
"num_workers": "auto",
"optim": "auto",
"optim_args": null,
"out": "/content/dinov3_yolo11_distilled",
"overwrite": false,
"precision": "16-mixed",
"resume": null,
"resume_interrupted": false,
"seed": 0,
"strategy": "auto",
"trainer_args": {
"max_epochs": 10
},
"transform_args": null
}
[2025-11-23 19:43:09,009][INFO] Using output directory '/content/dinov3_yolo11_distilled'.
[2025-11-23 19:43:09,021][DEBUG] '/usr/local/lib/python3.12/dist-packages/lightly_train' is not a git repository.
[2025-11-23 19:43:09,028][DEBUG] Platform: Linux-6.6.105+-x86_64-with-glibc2.35
[2025-11-23 19:43:09,028][DEBUG] Python: 3.12.12
[2025-11-23 19:43:09,029][DEBUG] LightlyTrain: 0.12.2
[2025-11-23 19:43:09,030][DEBUG] LightlyTrain Git Information:
[2025-11-23 19:43:09,030][DEBUG] LightlyTrain is not installed from a git repository.
[2025-11-23 19:43:09,031][DEBUG] Run directory Git Information:
[2025-11-23 19:43:09,031][DEBUG] Branch: main
[2025-11-23 19:43:09,032][DEBUG] Commit: eca2c7bdb08dc783d25929d28ae99539139fed13
[2025-11-23 19:43:09,033][DEBUG] Uncommitted changes: M pre-train_distill_yolo11.py
?? yolo11s-pose.yaml
?? yolo11s.pt
[2025-11-23 19:43:09,033][DEBUG] Dependencies:
[2025-11-23 19:43:09,034][DEBUG] - torch 2.9.0+cu126
[2025-11-23 19:43:09,035][DEBUG] - torchvision 0.24.0+cu126
[2025-11-23 19:43:09,035][DEBUG] - pytorch-lightning 2.5.6
[2025-11-23 19:43:09,036][DEBUG] - Pillow 11.3.0
[2025-11-23 19:43:09,037][DEBUG] - pillow-simd x
[2025-11-23 19:43:09,037][DEBUG] Optional dependencies:
[2025-11-23 19:43:09,038][DEBUG] - super-gradients x
[2025-11-23 19:43:09,038][DEBUG] - timm 1.0.22
[2025-11-23 19:43:09,039][DEBUG] - ultralytics 8.3.230
[2025-11-23 19:43:09,039][DEBUG] - wandb 0.23.0
[2025-11-23 19:43:09,040][DEBUG] CPUs: 12
[2025-11-23 19:43:09,041][DEBUG] GPUs: 1
[2025-11-23 19:43:09,041][DEBUG] - NVIDIA L4 8.9 (23795204096)
[2025-11-23 19:43:09,042][DEBUG] Environment variables:
[2025-11-23 19:43:09,045][DEBUG] Getting transform args for method 'distillationv1'.
[2025-11-23 19:43:09,046][DEBUG] Using additional transform arguments None.
[2025-11-23 19:43:09,046][DEBUG] Getting transform for method 'distillationv1'.
[2025-11-23 19:43:09,051][DEBUG] Creating temporary file '/root/.cache/lightly-train/data/verify-out/5387724c44f656347aaa27f80fcb2110fa35c4f5b1611a1f187104d039136bd5' to verify out path.
[2025-11-23 19:43:09,054][DEBUG] Writing filepaths to '/root/.cache/lightly-train/data/5387724c44f656347aaa27f80fcb2110fa35c4f5b1611a1f187104d039136bd5.8aa0f77845a30c7a4c84f23f927bfbf0aab996e6d3374b1f4865a0d855a60045.temp' (chunk_size=10000)
[2025-11-23 19:43:09,059][DEBUG] Creating memory mapped sequence with 1200 '['filenames']'.
[2025-11-23 19:43:09,060][DEBUG] Found dataset size 1200.
[2025-11-23 19:43:09,060][DEBUG] Using default epochs 100.
[2025-11-23 19:43:10,642][DEBUG] Freezing parameters with names ['.dfl']
[2025-11-23 19:43:10,643][INFO] Enabling gradients for parameter 'model.model.0.conv.weight'
[2025-11-23 19:43:10,644][INFO] Enabling gradients for parameter 'model.model.0.bn.weight'
[2025-11-23 19:43:10,645][INFO] Enabling gradients for parameter 'model.model.0.bn.bias'
[2025-11-23 19:43:10,647][INFO] Enabling gradients for parameter 'model.model.1.conv.weight'
[2025-11-23 19:43:10,648][INFO] Enabling gradients for parameter 'model.model.1.bn.weight'
[2025-11-23 19:43:10,649][INFO] Enabling gradients for parameter 'model.model.1.bn.bias'
[2025-11-23 19:43:10,650][INFO] Enabling gradients for parameter 'model.model.2.cv1.conv.weight'
[2025-11-23 19:43:10,651][INFO] Enabling gradients for parameter 'model.model.2.cv1.bn.weight'
[2025-11-23 19:43:10,654][INFO] Enabling gradients for parameter 'model.model.2.cv1.bn.bias'
[2025-11-23 19:43:10,655][INFO] Enabling gradients for parameter 'model.model.2.cv2.conv.weight'
[2025-11-23 19:43:10,656][INFO] Enabling gradients for parameter 'model.model.2.cv2.bn.weight'
[2025-11-23 19:43:10,658][INFO] Enabling gradients for parameter 'model.model.2.cv2.bn.bias'
[2025-11-23 19:43:10,659][INFO] Enabling gradients for parameter 'model.model.2.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,660][INFO] Enabling gradients for parameter 'model.model.2.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,662][INFO] Enabling gradients for parameter 'model.model.2.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,663][INFO] Enabling gradients for parameter 'model.model.2.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,664][INFO] Enabling gradients for parameter 'model.model.2.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,665][INFO] Enabling gradients for parameter 'model.model.2.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,666][INFO] Enabling gradients for parameter 'model.model.2.m.0.cv3.conv.weight'
[2025-11-23 19:43:10,667][INFO] Enabling gradients for parameter 'model.model.2.m.0.cv3.bn.weight'
[2025-11-23 19:43:10,668][INFO] Enabling gradients for parameter 'model.model.2.m.0.cv3.bn.bias'
[2025-11-23 19:43:10,669][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,671][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,672][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,673][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,674][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,675][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,676][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.1.cv1.conv.weight'
[2025-11-23 19:43:10,677][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.1.cv1.bn.weight'
[2025-11-23 19:43:10,679][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.1.cv1.bn.bias'
[2025-11-23 19:43:10,680][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.1.cv2.conv.weight'
[2025-11-23 19:43:10,681][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.1.cv2.bn.weight'
[2025-11-23 19:43:10,682][INFO] Enabling gradients for parameter 'model.model.2.m.0.m.1.cv2.bn.bias'
[2025-11-23 19:43:10,683][INFO] Enabling gradients for parameter 'model.model.3.conv.weight'
[2025-11-23 19:43:10,684][INFO] Enabling gradients for parameter 'model.model.3.bn.weight'
[2025-11-23 19:43:10,685][INFO] Enabling gradients for parameter 'model.model.3.bn.bias'
[2025-11-23 19:43:10,686][INFO] Enabling gradients for parameter 'model.model.4.cv1.conv.weight'
[2025-11-23 19:43:10,688][INFO] Enabling gradients for parameter 'model.model.4.cv1.bn.weight'
[2025-11-23 19:43:10,689][INFO] Enabling gradients for parameter 'model.model.4.cv1.bn.bias'
[2025-11-23 19:43:10,691][INFO] Enabling gradients for parameter 'model.model.4.cv2.conv.weight'
[2025-11-23 19:43:10,692][INFO] Enabling gradients for parameter 'model.model.4.cv2.bn.weight'
[2025-11-23 19:43:10,693][INFO] Enabling gradients for parameter 'model.model.4.cv2.bn.bias'
[2025-11-23 19:43:10,694][INFO] Enabling gradients for parameter 'model.model.4.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,695][INFO] Enabling gradients for parameter 'model.model.4.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,696][INFO] Enabling gradients for parameter 'model.model.4.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,698][INFO] Enabling gradients for parameter 'model.model.4.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,699][INFO] Enabling gradients for parameter 'model.model.4.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,700][INFO] Enabling gradients for parameter 'model.model.4.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,701][INFO] Enabling gradients for parameter 'model.model.4.m.0.cv3.conv.weight'
[2025-11-23 19:43:10,703][INFO] Enabling gradients for parameter 'model.model.4.m.0.cv3.bn.weight'
[2025-11-23 19:43:10,704][INFO] Enabling gradients for parameter 'model.model.4.m.0.cv3.bn.bias'
[2025-11-23 19:43:10,705][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,706][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,708][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,709][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,710][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,711][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,713][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.1.cv1.conv.weight'
[2025-11-23 19:43:10,714][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.1.cv1.bn.weight'
[2025-11-23 19:43:10,715][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.1.cv1.bn.bias'
[2025-11-23 19:43:10,717][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.1.cv2.conv.weight'
[2025-11-23 19:43:10,718][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.1.cv2.bn.weight'
[2025-11-23 19:43:10,719][INFO] Enabling gradients for parameter 'model.model.4.m.0.m.1.cv2.bn.bias'
[2025-11-23 19:43:10,721][INFO] Enabling gradients for parameter 'model.model.5.conv.weight'
[2025-11-23 19:43:10,722][INFO] Enabling gradients for parameter 'model.model.5.bn.weight'
[2025-11-23 19:43:10,723][INFO] Enabling gradients for parameter 'model.model.5.bn.bias'
[2025-11-23 19:43:10,724][INFO] Enabling gradients for parameter 'model.model.6.cv1.conv.weight'
[2025-11-23 19:43:10,725][INFO] Enabling gradients for parameter 'model.model.6.cv1.bn.weight'
[2025-11-23 19:43:10,726][INFO] Enabling gradients for parameter 'model.model.6.cv1.bn.bias'
[2025-11-23 19:43:10,727][INFO] Enabling gradients for parameter 'model.model.6.cv2.conv.weight'
[2025-11-23 19:43:10,728][INFO] Enabling gradients for parameter 'model.model.6.cv2.bn.weight'
[2025-11-23 19:43:10,731][INFO] Enabling gradients for parameter 'model.model.6.cv2.bn.bias'
[2025-11-23 19:43:10,732][INFO] Enabling gradients for parameter 'model.model.6.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,733][INFO] Enabling gradients for parameter 'model.model.6.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,734][INFO] Enabling gradients for parameter 'model.model.6.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,735][INFO] Enabling gradients for parameter 'model.model.6.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,736][INFO] Enabling gradients for parameter 'model.model.6.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,737][INFO] Enabling gradients for parameter 'model.model.6.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,739][INFO] Enabling gradients for parameter 'model.model.6.m.0.cv3.conv.weight'
[2025-11-23 19:43:10,740][INFO] Enabling gradients for parameter 'model.model.6.m.0.cv3.bn.weight'
[2025-11-23 19:43:10,741][INFO] Enabling gradients for parameter 'model.model.6.m.0.cv3.bn.bias'
[2025-11-23 19:43:10,742][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,743][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,744][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,745][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,746][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,747][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,749][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.1.cv1.conv.weight'
[2025-11-23 19:43:10,750][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.1.cv1.bn.weight'
[2025-11-23 19:43:10,751][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.1.cv1.bn.bias'
[2025-11-23 19:43:10,753][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.1.cv2.conv.weight'
[2025-11-23 19:43:10,754][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.1.cv2.bn.weight'
[2025-11-23 19:43:10,754][INFO] Enabling gradients for parameter 'model.model.6.m.0.m.1.cv2.bn.bias'
[2025-11-23 19:43:10,755][INFO] Enabling gradients for parameter 'model.model.7.conv.weight'
[2025-11-23 19:43:10,756][INFO] Enabling gradients for parameter 'model.model.7.bn.weight'
[2025-11-23 19:43:10,758][INFO] Enabling gradients for parameter 'model.model.7.bn.bias'
[2025-11-23 19:43:10,759][INFO] Enabling gradients for parameter 'model.model.8.cv1.conv.weight'
[2025-11-23 19:43:10,760][INFO] Enabling gradients for parameter 'model.model.8.cv1.bn.weight'
[2025-11-23 19:43:10,761][INFO] Enabling gradients for parameter 'model.model.8.cv1.bn.bias'
[2025-11-23 19:43:10,763][INFO] Enabling gradients for parameter 'model.model.8.cv2.conv.weight'
[2025-11-23 19:43:10,764][INFO] Enabling gradients for parameter 'model.model.8.cv2.bn.weight'
[2025-11-23 19:43:10,766][INFO] Enabling gradients for parameter 'model.model.8.cv2.bn.bias'
[2025-11-23 19:43:10,767][INFO] Enabling gradients for parameter 'model.model.8.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,768][INFO] Enabling gradients for parameter 'model.model.8.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,770][INFO] Enabling gradients for parameter 'model.model.8.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,771][INFO] Enabling gradients for parameter 'model.model.8.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,772][INFO] Enabling gradients for parameter 'model.model.8.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,773][INFO] Enabling gradients for parameter 'model.model.8.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,774][INFO] Enabling gradients for parameter 'model.model.8.m.0.cv3.conv.weight'
[2025-11-23 19:43:10,775][INFO] Enabling gradients for parameter 'model.model.8.m.0.cv3.bn.weight'
[2025-11-23 19:43:10,777][INFO] Enabling gradients for parameter 'model.model.8.m.0.cv3.bn.bias'
[2025-11-23 19:43:10,778][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,779][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,781][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,782][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,783][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,784][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,785][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.1.cv1.conv.weight'
[2025-11-23 19:43:10,786][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.1.cv1.bn.weight'
[2025-11-23 19:43:10,788][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.1.cv1.bn.bias'
[2025-11-23 19:43:10,789][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.1.cv2.conv.weight'
[2025-11-23 19:43:10,790][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.1.cv2.bn.weight'
[2025-11-23 19:43:10,792][INFO] Enabling gradients for parameter 'model.model.8.m.0.m.1.cv2.bn.bias'
[2025-11-23 19:43:10,793][INFO] Enabling gradients for parameter 'model.model.9.cv1.conv.weight'
[2025-11-23 19:43:10,794][INFO] Enabling gradients for parameter 'model.model.9.cv1.bn.weight'
[2025-11-23 19:43:10,796][INFO] Enabling gradients for parameter 'model.model.9.cv1.bn.bias'
[2025-11-23 19:43:10,797][INFO] Enabling gradients for parameter 'model.model.9.cv2.conv.weight'
[2025-11-23 19:43:10,798][INFO] Enabling gradients for parameter 'model.model.9.cv2.bn.weight'
[2025-11-23 19:43:10,799][INFO] Enabling gradients for parameter 'model.model.9.cv2.bn.bias'
[2025-11-23 19:43:10,801][INFO] Enabling gradients for parameter 'model.model.10.cv1.conv.weight'
[2025-11-23 19:43:10,802][INFO] Enabling gradients for parameter 'model.model.10.cv1.bn.weight'
[2025-11-23 19:43:10,803][INFO] Enabling gradients for parameter 'model.model.10.cv1.bn.bias'
[2025-11-23 19:43:10,804][INFO] Enabling gradients for parameter 'model.model.10.cv2.conv.weight'
[2025-11-23 19:43:10,806][INFO] Enabling gradients for parameter 'model.model.10.cv2.bn.weight'
[2025-11-23 19:43:10,807][INFO] Enabling gradients for parameter 'model.model.10.cv2.bn.bias'
[2025-11-23 19:43:10,808][INFO] Enabling gradients for parameter 'model.model.10.m.0.attn.qkv.conv.weight'
[2025-11-23 19:43:10,810][INFO] Enabling gradients for parameter 'model.model.10.m.0.attn.qkv.bn.weight'
[2025-11-23 19:43:10,811][INFO] Enabling gradients for parameter 'model.model.10.m.0.attn.qkv.bn.bias'
[2025-11-23 19:43:10,812][INFO] Enabling gradients for parameter 'model.model.10.m.0.attn.proj.conv.weight'
[2025-11-23 19:43:10,813][INFO] Enabling gradients for parameter 'model.model.10.m.0.attn.proj.bn.weight'
[2025-11-23 19:43:10,814][INFO] Enabling gradients for parameter 'model.model.10.m.0.attn.proj.bn.bias'
[2025-11-23 19:43:10,815][INFO] Enabling gradients for parameter 'model.model.10.m.0.attn.pe.conv.weight'
[2025-11-23 19:43:10,816][INFO] Enabling gradients for parameter 'model.model.10.m.0.attn.pe.bn.weight'
[2025-11-23 19:43:10,818][INFO] Enabling gradients for parameter 'model.model.10.m.0.attn.pe.bn.bias'
[2025-11-23 19:43:10,819][INFO] Enabling gradients for parameter 'model.model.10.m.0.ffn.0.conv.weight'
[2025-11-23 19:43:10,821][INFO] Enabling gradients for parameter 'model.model.10.m.0.ffn.0.bn.weight'
[2025-11-23 19:43:10,822][INFO] Enabling gradients for parameter 'model.model.10.m.0.ffn.0.bn.bias'
[2025-11-23 19:43:10,823][INFO] Enabling gradients for parameter 'model.model.10.m.0.ffn.1.conv.weight'
[2025-11-23 19:43:10,824][INFO] Enabling gradients for parameter 'model.model.10.m.0.ffn.1.bn.weight'
[2025-11-23 19:43:10,825][INFO] Enabling gradients for parameter 'model.model.10.m.0.ffn.1.bn.bias'
[2025-11-23 19:43:10,826][INFO] Enabling gradients for parameter 'model.model.13.cv1.conv.weight'
[2025-11-23 19:43:10,827][INFO] Enabling gradients for parameter 'model.model.13.cv1.bn.weight'
[2025-11-23 19:43:10,828][INFO] Enabling gradients for parameter 'model.model.13.cv1.bn.bias'
[2025-11-23 19:43:10,830][INFO] Enabling gradients for parameter 'model.model.13.cv2.conv.weight'
[2025-11-23 19:43:10,831][INFO] Enabling gradients for parameter 'model.model.13.cv2.bn.weight'
[2025-11-23 19:43:10,832][INFO] Enabling gradients for parameter 'model.model.13.cv2.bn.bias'
[2025-11-23 19:43:10,833][INFO] Enabling gradients for parameter 'model.model.13.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,834][INFO] Enabling gradients for parameter 'model.model.13.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,835][INFO] Enabling gradients for parameter 'model.model.13.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,837][INFO] Enabling gradients for parameter 'model.model.13.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,838][INFO] Enabling gradients for parameter 'model.model.13.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,839][INFO] Enabling gradients for parameter 'model.model.13.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,840][INFO] Enabling gradients for parameter 'model.model.13.m.0.cv3.conv.weight'
[2025-11-23 19:43:10,842][INFO] Enabling gradients for parameter 'model.model.13.m.0.cv3.bn.weight'
[2025-11-23 19:43:10,843][INFO] Enabling gradients for parameter 'model.model.13.m.0.cv3.bn.bias'
[2025-11-23 19:43:10,844][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,845][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,846][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,847][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,849][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,850][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,851][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.1.cv1.conv.weight'
[2025-11-23 19:43:10,852][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.1.cv1.bn.weight'
[2025-11-23 19:43:10,853][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.1.cv1.bn.bias'
[2025-11-23 19:43:10,854][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.1.cv2.conv.weight'
[2025-11-23 19:43:10,855][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.1.cv2.bn.weight'
[2025-11-23 19:43:10,858][INFO] Enabling gradients for parameter 'model.model.13.m.0.m.1.cv2.bn.bias'
[2025-11-23 19:43:10,859][INFO] Enabling gradients for parameter 'model.model.16.cv1.conv.weight'
[2025-11-23 19:43:10,860][INFO] Enabling gradients for parameter 'model.model.16.cv1.bn.weight'
[2025-11-23 19:43:10,861][INFO] Enabling gradients for parameter 'model.model.16.cv1.bn.bias'
[2025-11-23 19:43:10,862][INFO] Enabling gradients for parameter 'model.model.16.cv2.conv.weight'
[2025-11-23 19:43:10,864][INFO] Enabling gradients for parameter 'model.model.16.cv2.bn.weight'
[2025-11-23 19:43:10,865][INFO] Enabling gradients for parameter 'model.model.16.cv2.bn.bias'
[2025-11-23 19:43:10,866][INFO] Enabling gradients for parameter 'model.model.16.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,868][INFO] Enabling gradients for parameter 'model.model.16.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,869][INFO] Enabling gradients for parameter 'model.model.16.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,871][INFO] Enabling gradients for parameter 'model.model.16.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,872][INFO] Enabling gradients for parameter 'model.model.16.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,873][INFO] Enabling gradients for parameter 'model.model.16.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,874][INFO] Enabling gradients for parameter 'model.model.16.m.0.cv3.conv.weight'
[2025-11-23 19:43:10,877][INFO] Enabling gradients for parameter 'model.model.16.m.0.cv3.bn.weight'
[2025-11-23 19:43:10,878][INFO] Enabling gradients for parameter 'model.model.16.m.0.cv3.bn.bias'
[2025-11-23 19:43:10,880][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,881][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,882][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,884][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,886][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,887][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,888][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.1.cv1.conv.weight'
[2025-11-23 19:43:10,889][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.1.cv1.bn.weight'
[2025-11-23 19:43:10,890][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.1.cv1.bn.bias'
[2025-11-23 19:43:10,891][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.1.cv2.conv.weight'
[2025-11-23 19:43:10,894][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.1.cv2.bn.weight'
[2025-11-23 19:43:10,895][INFO] Enabling gradients for parameter 'model.model.16.m.0.m.1.cv2.bn.bias'
[2025-11-23 19:43:10,896][INFO] Enabling gradients for parameter 'model.model.17.conv.weight'
[2025-11-23 19:43:10,897][INFO] Enabling gradients for parameter 'model.model.17.bn.weight'
[2025-11-23 19:43:10,899][INFO] Enabling gradients for parameter 'model.model.17.bn.bias'
[2025-11-23 19:43:10,900][INFO] Enabling gradients for parameter 'model.model.19.cv1.conv.weight'
[2025-11-23 19:43:10,901][INFO] Enabling gradients for parameter 'model.model.19.cv1.bn.weight'
[2025-11-23 19:43:10,903][INFO] Enabling gradients for parameter 'model.model.19.cv1.bn.bias'
[2025-11-23 19:43:10,904][INFO] Enabling gradients for parameter 'model.model.19.cv2.conv.weight'
[2025-11-23 19:43:10,905][INFO] Enabling gradients for parameter 'model.model.19.cv2.bn.weight'
[2025-11-23 19:43:10,908][INFO] Enabling gradients for parameter 'model.model.19.cv2.bn.bias'
[2025-11-23 19:43:10,909][INFO] Enabling gradients for parameter 'model.model.19.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,910][INFO] Enabling gradients for parameter 'model.model.19.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,911][INFO] Enabling gradients for parameter 'model.model.19.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,912][INFO] Enabling gradients for parameter 'model.model.19.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,914][INFO] Enabling gradients for parameter 'model.model.19.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,915][INFO] Enabling gradients for parameter 'model.model.19.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,916][INFO] Enabling gradients for parameter 'model.model.19.m.0.cv3.conv.weight'
[2025-11-23 19:43:10,918][INFO] Enabling gradients for parameter 'model.model.19.m.0.cv3.bn.weight'
[2025-11-23 19:43:10,919][INFO] Enabling gradients for parameter 'model.model.19.m.0.cv3.bn.bias'
[2025-11-23 19:43:10,920][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,921][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,922][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,924][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,925][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,926][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,927][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.1.cv1.conv.weight'
[2025-11-23 19:43:10,928][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.1.cv1.bn.weight'
[2025-11-23 19:43:10,930][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.1.cv1.bn.bias'
[2025-11-23 19:43:10,931][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.1.cv2.conv.weight'
[2025-11-23 19:43:10,932][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.1.cv2.bn.weight'
[2025-11-23 19:43:10,933][INFO] Enabling gradients for parameter 'model.model.19.m.0.m.1.cv2.bn.bias'
[2025-11-23 19:43:10,934][INFO] Enabling gradients for parameter 'model.model.20.conv.weight'
[2025-11-23 19:43:10,936][INFO] Enabling gradients for parameter 'model.model.20.bn.weight'
[2025-11-23 19:43:10,938][INFO] Enabling gradients for parameter 'model.model.20.bn.bias'
[2025-11-23 19:43:10,939][INFO] Enabling gradients for parameter 'model.model.22.cv1.conv.weight'
[2025-11-23 19:43:10,940][INFO] Enabling gradients for parameter 'model.model.22.cv1.bn.weight'
[2025-11-23 19:43:10,942][INFO] Enabling gradients for parameter 'model.model.22.cv1.bn.bias'
[2025-11-23 19:43:10,943][INFO] Enabling gradients for parameter 'model.model.22.cv2.conv.weight'
[2025-11-23 19:43:10,944][INFO] Enabling gradients for parameter 'model.model.22.cv2.bn.weight'
[2025-11-23 19:43:10,945][INFO] Enabling gradients for parameter 'model.model.22.cv2.bn.bias'
[2025-11-23 19:43:10,946][INFO] Enabling gradients for parameter 'model.model.22.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,947][INFO] Enabling gradients for parameter 'model.model.22.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,948][INFO] Enabling gradients for parameter 'model.model.22.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,949][INFO] Enabling gradients for parameter 'model.model.22.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,950][INFO] Enabling gradients for parameter 'model.model.22.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,951][INFO] Enabling gradients for parameter 'model.model.22.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,952][INFO] Enabling gradients for parameter 'model.model.22.m.0.cv3.conv.weight'
[2025-11-23 19:43:10,953][INFO] Enabling gradients for parameter 'model.model.22.m.0.cv3.bn.weight'
[2025-11-23 19:43:10,954][INFO] Enabling gradients for parameter 'model.model.22.m.0.cv3.bn.bias'
[2025-11-23 19:43:10,955][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.0.cv1.conv.weight'
[2025-11-23 19:43:10,956][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.0.cv1.bn.weight'
[2025-11-23 19:43:10,958][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.0.cv1.bn.bias'
[2025-11-23 19:43:10,959][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.0.cv2.conv.weight'
[2025-11-23 19:43:10,960][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.0.cv2.bn.weight'
[2025-11-23 19:43:10,961][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.0.cv2.bn.bias'
[2025-11-23 19:43:10,962][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.1.cv1.conv.weight'
[2025-11-23 19:43:10,966][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.1.cv1.bn.weight'
[2025-11-23 19:43:10,967][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.1.cv1.bn.bias'
[2025-11-23 19:43:10,968][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.1.cv2.conv.weight'
[2025-11-23 19:43:10,970][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.1.cv2.bn.weight'
[2025-11-23 19:43:10,971][INFO] Enabling gradients for parameter 'model.model.22.m.0.m.1.cv2.bn.bias'
[2025-11-23 19:43:10,972][INFO] Enabling gradients for parameter 'model.model.23.cv2.0.0.conv.weight'
[2025-11-23 19:43:10,973][INFO] Enabling gradients for parameter 'model.model.23.cv2.0.0.bn.weight'
[2025-11-23 19:43:10,974][INFO] Enabling gradients for parameter 'model.model.23.cv2.0.0.bn.bias'
[2025-11-23 19:43:10,975][INFO] Enabling gradients for parameter 'model.model.23.cv2.0.1.conv.weight'
[2025-11-23 19:43:10,976][INFO] Enabling gradients for parameter 'model.model.23.cv2.0.1.bn.weight'
[2025-11-23 19:43:10,977][INFO] Enabling gradients for parameter 'model.model.23.cv2.0.1.bn.bias'
[2025-11-23 19:43:10,979][INFO] Enabling gradients for parameter 'model.model.23.cv2.0.2.weight'
[2025-11-23 19:43:10,980][INFO] Enabling gradients for parameter 'model.model.23.cv2.0.2.bias'
[2025-11-23 19:43:10,981][INFO] Enabling gradients for parameter 'model.model.23.cv2.1.0.conv.weight'
[2025-11-23 19:43:10,983][INFO] Enabling gradients for parameter 'model.model.23.cv2.1.0.bn.weight'
[2025-11-23 19:43:10,984][INFO] Enabling gradients for parameter 'model.model.23.cv2.1.0.bn.bias'
[2025-11-23 19:43:10,985][INFO] Enabling gradients for parameter 'model.model.23.cv2.1.1.conv.weight'
[2025-11-23 19:43:10,987][INFO] Enabling gradients for parameter 'model.model.23.cv2.1.1.bn.weight'
[2025-11-23 19:43:10,988][INFO] Enabling gradients for parameter 'model.model.23.cv2.1.1.bn.bias'
[2025-11-23 19:43:10,989][INFO] Enabling gradients for parameter 'model.model.23.cv2.1.2.weight'
[2025-11-23 19:43:10,990][INFO] Enabling gradients for parameter 'model.model.23.cv2.1.2.bias'
[2025-11-23 19:43:10,991][INFO] Enabling gradients for parameter 'model.model.23.cv2.2.0.conv.weight'
[2025-11-23 19:43:10,992][INFO] Enabling gradients for parameter 'model.model.23.cv2.2.0.bn.weight'
[2025-11-23 19:43:10,994][INFO] Enabling gradients for parameter 'model.model.23.cv2.2.0.bn.bias'
[2025-11-23 19:43:10,995][INFO] Enabling gradients for parameter 'model.model.23.cv2.2.1.conv.weight'
[2025-11-23 19:43:10,996][INFO] Enabling gradients for parameter 'model.model.23.cv2.2.1.bn.weight'
[2025-11-23 19:43:10,997][INFO] Enabling gradients for parameter 'model.model.23.cv2.2.1.bn.bias'
[2025-11-23 19:43:10,998][INFO] Enabling gradients for parameter 'model.model.23.cv2.2.2.weight'
[2025-11-23 19:43:10,999][INFO] Enabling gradients for parameter 'model.model.23.cv2.2.2.bias'
[2025-11-23 19:43:11,001][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.0.0.conv.weight'
[2025-11-23 19:43:11,002][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.0.0.bn.weight'
[2025-11-23 19:43:11,003][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.0.0.bn.bias'
[2025-11-23 19:43:11,004][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.0.1.conv.weight'
[2025-11-23 19:43:11,006][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.0.1.bn.weight'
[2025-11-23 19:43:11,007][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.0.1.bn.bias'
[2025-11-23 19:43:11,008][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.1.0.conv.weight'
[2025-11-23 19:43:11,010][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.1.0.bn.weight'
[2025-11-23 19:43:11,011][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.1.0.bn.bias'
[2025-11-23 19:43:11,012][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.1.1.conv.weight'
[2025-11-23 19:43:11,013][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.1.1.bn.weight'
[2025-11-23 19:43:11,015][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.1.1.bn.bias'
[2025-11-23 19:43:11,015][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.2.weight'
[2025-11-23 19:43:11,016][INFO] Enabling gradients for parameter 'model.model.23.cv3.0.2.bias'
[2025-11-23 19:43:11,018][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.0.0.conv.weight'
[2025-11-23 19:43:11,019][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.0.0.bn.weight'
[2025-11-23 19:43:11,020][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.0.0.bn.bias'
[2025-11-23 19:43:11,021][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.0.1.conv.weight'
[2025-11-23 19:43:11,022][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.0.1.bn.weight'
[2025-11-23 19:43:11,023][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.0.1.bn.bias'
[2025-11-23 19:43:11,026][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.1.0.conv.weight'
[2025-11-23 19:43:11,027][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.1.0.bn.weight'
[2025-11-23 19:43:11,028][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.1.0.bn.bias'
[2025-11-23 19:43:11,029][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.1.1.conv.weight'
[2025-11-23 19:43:11,029][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.1.1.bn.weight'
[2025-11-23 19:43:11,032][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.1.1.bn.bias'
[2025-11-23 19:43:11,032][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.2.weight'
[2025-11-23 19:43:11,033][INFO] Enabling gradients for parameter 'model.model.23.cv3.1.2.bias'
[2025-11-23 19:43:11,034][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.0.0.conv.weight'
[2025-11-23 19:43:11,035][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.0.0.bn.weight'
[2025-11-23 19:43:11,036][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.0.0.bn.bias'
[2025-11-23 19:43:11,038][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.0.1.conv.weight'
[2025-11-23 19:43:11,039][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.0.1.bn.weight'
[2025-11-23 19:43:11,040][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.0.1.bn.bias'
[2025-11-23 19:43:11,043][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.1.0.conv.weight'
[2025-11-23 19:43:11,044][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.1.0.bn.weight'
[2025-11-23 19:43:11,045][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.1.0.bn.bias'
[2025-11-23 19:43:11,046][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.1.1.conv.weight'
[2025-11-23 19:43:11,048][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.1.1.bn.weight'
[2025-11-23 19:43:11,049][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.1.1.bn.bias'
[2025-11-23 19:43:11,050][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.2.weight'
[2025-11-23 19:43:11,052][INFO] Enabling gradients for parameter 'model.model.23.cv3.2.2.bias'
[2025-11-23 19:43:11,053][INFO] Disabling gradients for parameter 'model.model.23.dfl.conv.weight'
[2025-11-23 19:43:11,057][DEBUG] Getting embedding model with embedding dimension None.
[2025-11-23 19:43:11,057][DEBUG] Using jsonl logger with args flush_logs_every_n_steps=100
[2025-11-23 19:43:11,058][DEBUG] Using tensorboard logger with args name='' version='' log_graph=False default_hp_metric=True prefix='' sub_dir=None
[2025-11-23 19:43:11,059][DEBUG] Using loggers ['JSONLLogger', 'TensorBoardLogger'].
[2025-11-23 19:43:11,062][DEBUG] Getting accelerator for 'auto'.
[2025-11-23 19:43:11,063][DEBUG] CUDA is available, defaulting to CUDA.
[2025-11-23 19:43:11,064][DEBUG] Detected 1 devices.
[2025-11-23 19:43:11,065][DEBUG] Using strategy 'auto'.
[2025-11-23 19:43:11,066][DEBUG] Using provided precision '16-mixed'.
[2025-11-23 19:43:11,066][DEBUG] Getting trainer.
[2025-11-23 19:43:11,067][DEBUG] Using sync_batchnorm 'True'.
[2025-11-23 19:43:11,067][DEBUG] Using additional trainer arguments {'max_epochs': 10}.
[2025-11-23 19:43:11,069][INFO] Using 16bit Automatic Mixed Precision (AMP)
[2025-11-23 19:43:11,111][INFO] GPU available: True (cuda), used: True
[2025-11-23 19:43:11,113][INFO] TPU available: False, using: 0 TPU cores
[2025-11-23 19:43:11,114][DEBUG] Detected 1 nodes and 1 devices per node.
[2025-11-23 19:43:11,115][DEBUG] Total number of devices: 1.
[2025-11-23 19:43:11,116][DEBUG] Detected dataset size 1200.
[2025-11-23 19:43:11,116][DEBUG] Using batch size per device 4.
[2025-11-23 19:43:11,117][DEBUG] Using optimizer 'OptimizerType.LARS'.
[2025-11-23 19:43:11,118][DEBUG] Getting method args for 'Distillation'
[2025-11-23 19:43:11,118][DEBUG] Getting method for 'Distillation'
[2025-11-23 19:43:11,837][INFO] Resolved configuration:
{
"accelerator": "CUDAAccelerator",
"batch_size": 4,
"callbacks": {
"device_stats_monitor": null,
"early_stopping": {
"check_finite": true,
"monitor": "train_loss",
"patience": 1000000000000
},
"learning_rate_monitor": {},
"model_checkpoint": {
"auto_insert_metric_name": true,
"dirpath": "/content/dinov3_yolo11_distilled/checkpoints",
"enable_version_counter": false,
"every_n_epochs": null,
"every_n_train_steps": null,
"filename": null,
"mode": "min",
"monitor": null,
"save_last": true,
"save_on_train_epoch_end": null,
"save_top_k": 1,
"save_weights_only": false,
"train_time_interval": null,
"verbose": false
},
"model_export": {
"every_n_epochs": 1
}
},
"checkpoint": null,
"data": "/content/unlabeled_idl_images",
"devices": 1,
"embed_dim": null,
"epochs": 100,
"float32_matmul_precision": "highest",
"loader_args": null,
"loggers": {
"jsonl": {
"flush_logs_every_n_steps": 100
},
"mlflow": null,
"tensorboard": {
"default_hp_metric": true,
"log_graph": false,
"name": "",
"prefix": "",
"sub_dir": null,
"version": ""
},
"wandb": null
},
"method": "distillationv1",
"method_args": {
"lr_scale_method": "sqrt",
"queue_size": 512,
"reference_batch_size": 1536,
"teacher": "dinov3/vitb16",
"teacher_url": null,
"teacher_weights": null,
"temperature": 0.07
},
"model": "ultralytics/yolo11m",
"model_args": null,
"num_nodes": 1,
"num_workers": 8,
"optim": "lars",
"optim_args": {
"dampening": 0.0,
"eps": 1e-08,
"lr": 1.8,
"momentum": 0.9,
"nesterov": false,
"trust_coefficient": 0.001,
"weight_decay": 1e-06
},
"out": "/content/dinov3_yolo11_distilled",
"overwrite": false,
"precision": "16-mixed",
"resume": null,
"resume_interrupted": false,
"seed": 0,
"strategy": "SingleDeviceStrategy",
"trainer_args": {
"max_epochs": 10
},
"transform_args": {
"channel_drop": null,
"color_jitter": {
"brightness": 0.8,
"contrast": 0.8,
"hue": 0.2,
"prob": 0.8,
"saturation": 0.4,
"strength": 0.5
},
"gaussian_blur": {
"blur_limit": 0,
"prob": 1.0,
"sigmas": [
0.0,
0.1
]
},
"image_size": [
224,
224
],
"normalize": {
"mean": [
0.485,
0.456,
0.406
],
"std": [
0.229,
0.224,
0.225
]
},
"num_channels": 3,
"random_flip": {
"horizontal_prob": 0.5,
"vertical_prob": 0.0
},
"random_gray_scale": 0.2,
"random_resize": {
"max_scale": 1.0,
"min_scale": 0.14
},
"random_rotation": null,
"solarize": null
}
}
[2025-11-23 19:43:11,857][INFO] LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
[2025-11-23 19:43:11,968][INFO] Loading `train_dataloader` to estimate number of stepping batches.
[2025-11-23 19:43:12,515][WARNING] /usr/local/lib/python3.12/dist-packages/pytorch_lightning/utilities/model_summary/model_summary.py:231: Precision 16-mixed is not supported by the model summary. Estimated model size in MB will not be accurate. Using 32 bits instead.
[2025-11-23 19:43:12,533][INFO]
| Name | Type | Params | Mode
--------------------------------------------------------------------------
0 | teacher_embedding_model | DinoVisionTransformer | 85.7 M | eval
1 | student_embedding_model | EmbeddingModel | 10.4 M | train
2 | flatten | Flatten | 0 | train
3 | student_projection_head | Linear | 393 K | train
4 | criterion | DistillationLoss | 0 | train
--------------------------------------------------------------------------
10.7 M Trainable params
85.7 M Non-trainable params
96.4 M Total params
385.663 Total estimated model params size (MB)
195 Modules in train mode
212 Modules in eval mode
[2025-11-23 19:43:12,540][WARNING] /usr/local/lib/python3.12/dist-packages/pytorch_lightning/loops/fit_loop.py:527: Found 212 module(s) in eval mode at the start of training. This may lead to unexpected behavior during training. If this is intentional, you can ignore this warning.
[2025-11-23 19:43:38,966][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:44:08,441][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:44:39,519][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:45:09,775][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:45:40,349][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:46:10,399][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:46:41,368][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:47:11,742][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:47:41,808][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:48:12,054][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:48:15,355][INFO] `Trainer.fit` stopped: `max_epochs=10` reached.
[2025-11-23 19:48:15,945][INFO] Training completed.
[2025-11-23 19:48:15,947][DEBUG] Exporting model to '/content/dinov3_yolo11_distilled/exported_models/exported_last.pt' in format 'ModelFormat.PACKAGE_DEFAULT'.
[2025-11-23 19:48:16,213][INFO] Example: How to use the exported model
----------------------------------------------------------------------------------------
from ultralytics import YOLO
# Load the pretrained model
model = YOLO('/content/dinov3_yolo11_distilled/exported_models/exported_last.pt')
# Finetune or evaluate the model
...
----------------------------------------------------------------------------------------
[2025-11-23 19:48:16,217][INFO] Model exported.