Upload logs/resnet_20260331_102144.log with huggingface_hub

logs/resnet_20260331_102144.log

@@ -0,0 +1,654 @@
+==> Checking internet connectivity...
+==> Internet + pip OK
+==> Installing dependencies
+ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
+torchaudio 2.5.1+cu124 requires torch==2.5.1, but you have torch 2.6.0+cu124 which is incompatible.
+WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.
+WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.
+==> CUDA OK (torch 2.6.0+cu124, CUDA 12.4, NVIDIA GeForce RTX 3090)
+==> System info:
+  GPU: NVIDIA GeForce RTX 3090, 24576 MiB, 565.57.01
+  RAM: 251Gi
+  CPU: 64 cores
+  Disk: 50G total, 47G free
+==> Cloning font-model repo
+Cloning into 'font-model'...
+==> Downloading dataset from HuggingFace: dchen0/font_crops_test
+
+==> Extracting data/train.tar...
+==> Extracting data/test.tar...
+==> Dataset ready: 3 train variants, 3 test variants
+overlay          50G  4.0G   47G   8% /
+
+============================================
+  Training: resnet50 (GPUs: 1)
+============================================
+2026-03-31 10:21:32 - INFO - Loading dataset from data - train_model.py:163
+2026-03-31 10:21:32 - INFO - Found 3 labels - train_model.py:167
+2026-03-31 10:21:32 - INFO - Setting up image processor and augmentations - train_model.py:177
+2026-03-31 10:21:32 - INFO - HTTP Request: HEAD https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer/resolve/main/processor_config.json "HTTP/1.1 404 Not Found" - _client.py:1025
+2026-03-31 10:21:32 - INFO - HTTP Request: HEAD https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer/resolve/main/preprocessor_config.json "HTTP/1.1 307 Temporary Redirect" - _client.py:1025
+2026-03-31 10:21:32 - INFO - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/facebook/dinov2-base-imagenet1k-1-layer/f9305d2c8048bd65783f64fabfa25429d13cbdbb/preprocessor_config.json "HTTP/1.1 200 OK" - _client.py:1025
+2026-03-31 10:21:32 - INFO - HTTP Request: GET https://huggingface.co/api/resolve-cache/models/facebook/dinov2-base-imagenet1k-1-layer/f9305d2c8048bd65783f64fabfa25429d13cbdbb/preprocessor_config.json "HTTP/1.1 200 OK" - _client.py:1025
+2026-03-31 10:21:32 - INFO - HTTP Request: HEAD https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer/resolve/main/processor_config.json "HTTP/1.1 404 Not Found" - _client.py:1025
+2026-03-31 10:21:32 - INFO - HTTP Request: HEAD https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer/resolve/main/preprocessor_config.json "HTTP/1.1 307 Temporary Redirect" - _client.py:1025
+2026-03-31 10:21:32 - INFO - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/facebook/dinov2-base-imagenet1k-1-layer/f9305d2c8048bd65783f64fabfa25429d13cbdbb/preprocessor_config.json "HTTP/1.1 200 OK" - _client.py:1025
+2026-03-31 10:21:33 - INFO - HTTP Request: HEAD https://s3.amazonaws.com/datasets.huggingface.co/datasets/datasets/imagefolder/imagefolder.py "HTTP/1.1 404 Not Found" - _client.py:1025
+
+
+
+2026-03-31 10:21:33 - INFO - Train size: 30, Validation size: 9 - train_model.py:187
+2026-03-31 10:21:33 - INFO - Applying data transformations - train_model.py:191
+
+
+2026-03-31 10:21:33 - INFO - Data preprocessing complete - train_model.py:207
+2026-03-31 10:21:33 - INFO - Loading ResNet-50 (ImageNet-pretrained) as CNN baseline - train_model.py:211
+Downloading: "https://download.pytorch.org/models/resnet50-11ad3fa6.pth" to /root/.cache/torch/hub/checkpoints/resnet50-11ad3fa6.pth
+
  0%|          | 0.00/97.8M [00:00<?, ?B/s]
  9%|▉         | 8.75M/97.8M [00:00<00:01, 91.5MB/s]
 20%|██        | 19.9M/97.8M [00:00<00:00, 106MB/s] 
 31%|███       | 30.0M/97.8M [00:00<00:00, 100MB/s]
 41%|████      | 39.6M/97.8M [00:00<00:00, 88.7MB/s]
 50%|████▉     | 48.8M/97.8M [00:00<00:00, 90.7MB/s]
 61%|██████▏   | 60.0M/97.8M [00:00<00:00, 99.1MB/s]
 71%|███████   | 69.6M/97.8M [00:00<00:00, 97.2MB/s]
 81%|████████  | 79.0M/97.8M [00:00<00:00, 89.5MB/s]
 90%|████████▉ | 87.8M/97.8M [00:01<00:00, 86.6MB/s]
 98%|█████████▊| 96.1M/97.8M [00:01<00:00, 84.2MB/s]
+2026-03-31 10:21:35 - INFO - trainable params: 23,514,179 || all params: 23,514,179 || trainable%: 100.0000 - train_model.py:237
+2026-03-31 10:21:35 - INFO - Setting up training arguments - train_model.py:295
+2026-03-31 10:21:35 - INFO - Using device: cuda - train_model.py:298
+`logging_dir` is deprecated and will be removed in v5.2. Please set `TENSORBOARD_LOGGING_DIR` instead.
+2026-03-31 10:21:35 - INFO - Starting training - train_model.py:337
+
  0%|          | 0/1 [00:00<?, ?it/s]
+
  0%|          | 0/1 [00:00<?, ?it/s]
                                             
+
                                     
+
+
                                              
                                             
+2026-03-31 10:21:37 - INFO - Training complete - train_model.py:343
+2026-03-31 10:21:37 - INFO - Saving result model to the output directory - train_model.py:350
+{'eval_loss': '1.124', 'eval_accuracy': '0.3333', 'eval_runtime': '0.406', 'eval_samples_per_second': '22.17', 'eval_steps_per_second': '2.463', 'epoch': '1'}
+{'train_runtime': '1.543', 'train_samples_per_second': '19.44', 'train_steps_per_second': '0.648', 'train_loss': '1.128', 'epoch': '1'}
+==> Finished: resnet50
+
+============================================
+  ALL TRAINING COMPLETE
+  Results in: /workspace/output/
+============================================
+==> Uploading results to HuggingFace: dchen0/font-model-dry-run
+
+
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors:  93%|█████████▎| 87.9MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors:  93%|█████████▎| 87.9MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors:  93%|█████████▎| 87.9MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors:  93%|█████████▎| 87.9MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|█████████▉| 94.2MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
+
+
+
+
+
+
+
+
+
  ...952495.620ce50c8876.612.0: 100%|██████████| 4.63kB / 4.63kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
+
+
+
+
+
+
+
+
+
  ...952495.620ce50c8876.612.0: 100%|██████████| 4.63kB / 4.63kB            
+
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
+
+
+
+
+
+
+
+
+
  ...952495.620ce50c8876.612.0: 100%|██████████| 4.63kB / 4.63kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
+
+
+
+
+
+
+
+
+
  ...952495.620ce50c8876.612.0: 100%|██████████| 4.63kB / 4.63kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
+
+
+
+
+
+
+
+
+
  ...952495.620ce50c8876.612.0: 100%|██████████| 4.63kB / 4.63kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
+
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
+
+
+
  ...point-1/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
+
+
+
+
+
  ...t_model/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
+
+
+
+
+
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
+
+
+
+
+
+
+
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
+
+
+
+
+
+
+
+
+
  ...952495.620ce50c8876.612.0: 100%|██████████| 4.63kB / 4.63kB            
+
+
  ...heckpoint-1/rng_state.pth: 100%|██████████| 14.2kB / 14.2kB            
+
  ...50/checkpoint-1/scaler.pt: 100%|██████████|   988B /   988B            
+
  ...point-1/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
  ...checkpoint-1/optimizer.pt: 100%|██████████| 1.58kB / 1.58kB            
+
  ...t_model/model.safetensors: 100%|██████████| 94.3MB / 94.3MB            
+
  ...point-1/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
  ...t_model/training_args.bin: 100%|██████████| 4.86kB / 4.86kB            
+
  ...checkpoint-1/scheduler.pt: 100%|██████████| 1.06kB / 1.06kB            
+
  ...952495.620ce50c8876.612.0: 100%|██████████| 4.63kB / 4.63kB            
+Upload complete.
+==> Uploading training log to HuggingFace...