Upload folder using huggingface_hub

checkpoint-1970/config.json

@@ -0,0 +1,132 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "airplane",
+    "1": "airport",
+    "2": "baseball diamond",
+    "3": "basketball court",
+    "4": "beach",
+    "5": "bridge",
+    "6": "chaparral",
+    "7": "church",
+    "8": "circular farmland",
+    "9": "cloud",
+    "10": "commercial area",
+    "11": "dense residential",
+    "12": "desert",
+    "13": "forest",
+    "14": "freeway",
+    "15": "golf course",
+    "16": "ground track field",
+    "17": "harbor",
+    "18": "industrial area",
+    "19": "intersection",
+    "20": "island",
+    "21": "lake",
+    "22": "meadow",
+    "23": "medium residential",
+    "24": "mobile home park",
+    "25": "mountain",
+    "26": "overpass",
+    "27": "palace",
+    "28": "parking lot",
+    "29": "railway",
+    "30": "railway station",
+    "31": "rectangular farmland",
+    "32": "river",
+    "33": "roundabout",
+    "34": "runway",
+    "35": "sea ice",
+    "36": "ship",
+    "37": "snowberg",
+    "38": "sparse residential",
+    "39": "stadium",
+    "40": "storage tank",
+    "41": "tennis court",
+    "42": "terrace",
+    "43": "thermal power station",
+    "44": "wetland"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "airplane": 0,
+    "airport": 1,
+    "baseball diamond": 2,
+    "basketball court": 3,
+    "beach": 4,
+    "bridge": 5,
+    "chaparral": 6,
+    "church": 7,
+    "circular farmland": 8,
+    "cloud": 9,
+    "commercial area": 10,
+    "dense residential": 11,
+    "desert": 12,
+    "forest": 13,
+    "freeway": 14,
+    "golf course": 15,
+    "ground track field": 16,
+    "harbor": 17,
+    "industrial area": 18,
+    "intersection": 19,
+    "island": 20,
+    "lake": 21,
+    "meadow": 22,
+    "medium residential": 23,
+    "mobile home park": 24,
+    "mountain": 25,
+    "overpass": 26,
+    "palace": 27,
+    "parking lot": 28,
+    "railway": 29,
+    "railway station": 30,
+    "rectangular farmland": 31,
+    "river": 32,
+    "roundabout": 33,
+    "runway": 34,
+    "sea ice": 35,
+    "ship": 36,
+    "snowberg": 37,
+    "sparse residential": 38,
+    "stadium": 39,
+    "storage tank": 40,
+    "tennis court": 41,
+    "terrace": 42,
+    "thermal power station": 43,
+    "wetland": 44
+  },
+  "model_type": "siglip",
+  "problem_type": "single_label_classification",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_size": 768,
+    "torch_dtype": "float32",
+    "vocab_size": 256000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 224,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "torch_dtype": "float32"
+  }
+}

checkpoint-1970/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7735b9c19f11a56c6b5f961a56bbf3642ab81f80f42667c04d85b912688995
+size 371700268

checkpoint-1970/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ae95bbd3ad4380821502da8269b682ac908a13704ad9681fe6fe2e7df95ac4
+size 686820218

checkpoint-1970/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-1970/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6759887a343b9a59e49e3e78978b8dbec94acefcbc28d0c9a26661bf7c8325
+size 14244

checkpoint-1970/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17410f7b586375e7f0144698da2a32380c4ff4c732cbf740c0889ec436006593
+size 1064

checkpoint-1970/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_global_step": 1970,
+  "best_metric": 0.13895583152770996,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1970",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1970,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5076142131979695,
+      "grad_norm": 8.941224098205566,
+      "learning_rate": 0.000153125,
+      "loss": 1.4212,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8340634920634921,
+      "eval_loss": 0.5306099653244019,
+      "eval_model_preparation_time": 0.003,
+      "eval_runtime": 415.7745,
+      "eval_samples_per_second": 75.762,
+      "eval_steps_per_second": 9.471,
+      "step": 985
+    },
+    {
+      "epoch": 1.015228426395939,
+      "grad_norm": 8.13437557220459,
+      "learning_rate": 0.00010104166666666668,
+      "loss": 0.686,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5228426395939088,
+      "grad_norm": 7.881953239440918,
+      "learning_rate": 4.8958333333333335e-05,
+      "loss": 0.3992,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9532063492063492,
+      "eval_loss": 0.13895583152770996,
+      "eval_model_preparation_time": 0.003,
+      "eval_runtime": 418.2101,
+      "eval_samples_per_second": 75.321,
+      "eval_steps_per_second": 9.416,
+      "step": 1970
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1970,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.278477735286784e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1970/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5371dc4f3b7759a694db9f7dd1b77d5c2e28b4074a617a682427c213e9fb3ec6
+size 5304

checkpoint-985/config.json

@@ -0,0 +1,132 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "airplane",
+    "1": "airport",
+    "2": "baseball diamond",
+    "3": "basketball court",
+    "4": "beach",
+    "5": "bridge",
+    "6": "chaparral",
+    "7": "church",
+    "8": "circular farmland",
+    "9": "cloud",
+    "10": "commercial area",
+    "11": "dense residential",
+    "12": "desert",
+    "13": "forest",
+    "14": "freeway",
+    "15": "golf course",
+    "16": "ground track field",
+    "17": "harbor",
+    "18": "industrial area",
+    "19": "intersection",
+    "20": "island",
+    "21": "lake",
+    "22": "meadow",
+    "23": "medium residential",
+    "24": "mobile home park",
+    "25": "mountain",
+    "26": "overpass",
+    "27": "palace",
+    "28": "parking lot",
+    "29": "railway",
+    "30": "railway station",
+    "31": "rectangular farmland",
+    "32": "river",
+    "33": "roundabout",
+    "34": "runway",
+    "35": "sea ice",
+    "36": "ship",
+    "37": "snowberg",
+    "38": "sparse residential",
+    "39": "stadium",
+    "40": "storage tank",
+    "41": "tennis court",
+    "42": "terrace",
+    "43": "thermal power station",
+    "44": "wetland"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "airplane": 0,
+    "airport": 1,
+    "baseball diamond": 2,
+    "basketball court": 3,
+    "beach": 4,
+    "bridge": 5,
+    "chaparral": 6,
+    "church": 7,
+    "circular farmland": 8,
+    "cloud": 9,
+    "commercial area": 10,
+    "dense residential": 11,
+    "desert": 12,
+    "forest": 13,
+    "freeway": 14,
+    "golf course": 15,
+    "ground track field": 16,
+    "harbor": 17,
+    "industrial area": 18,
+    "intersection": 19,
+    "island": 20,
+    "lake": 21,
+    "meadow": 22,
+    "medium residential": 23,
+    "mobile home park": 24,
+    "mountain": 25,
+    "overpass": 26,
+    "palace": 27,
+    "parking lot": 28,
+    "railway": 29,
+    "railway station": 30,
+    "rectangular farmland": 31,
+    "river": 32,
+    "roundabout": 33,
+    "runway": 34,
+    "sea ice": 35,
+    "ship": 36,
+    "snowberg": 37,
+    "sparse residential": 38,
+    "stadium": 39,
+    "storage tank": 40,
+    "tennis court": 41,
+    "terrace": 42,
+    "thermal power station": 43,
+    "wetland": 44
+  },
+  "model_type": "siglip",
+  "problem_type": "single_label_classification",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_size": 768,
+    "torch_dtype": "float32",
+    "vocab_size": 256000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 224,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "torch_dtype": "float32"
+  }
+}

checkpoint-985/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55af477d364fa49ebf55166850ad91444a8211c41d17f111249b0ad40c588b0f
+size 371700268

checkpoint-985/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1355263d8f83f260a7aa62e7c4130be86af2a237592e67960054e3e7e2ad031
+size 686820218

checkpoint-985/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-985/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03065d21ca2e32ab40ef969161b89aacc21f83bf3df69a74f0df011f4954660
+size 14244

checkpoint-985/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248877ee4d1e62307eb7d45650f10cdca8991a166a68f8918d0986a6c12d748e
+size 1064

checkpoint-985/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_global_step": 985,
+  "best_metric": 0.5306099653244019,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-985",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 985,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5076142131979695,
+      "grad_norm": 8.941224098205566,
+      "learning_rate": 0.000153125,
+      "loss": 1.4212,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8340634920634921,
+      "eval_loss": 0.5306099653244019,
+      "eval_model_preparation_time": 0.003,
+      "eval_runtime": 415.7745,
+      "eval_samples_per_second": 75.762,
+      "eval_steps_per_second": 9.471,
+      "step": 985
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1970,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.639238867643392e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-985/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5371dc4f3b7759a694db9f7dd1b77d5c2e28b4074a617a682427c213e9fb3ec6
+size 5304

config.json

@@ -0,0 +1,132 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "airplane",
+    "1": "airport",
+    "2": "baseball diamond",
+    "3": "basketball court",
+    "4": "beach",
+    "5": "bridge",
+    "6": "chaparral",
+    "7": "church",
+    "8": "circular farmland",
+    "9": "cloud",
+    "10": "commercial area",
+    "11": "dense residential",
+    "12": "desert",
+    "13": "forest",
+    "14": "freeway",
+    "15": "golf course",
+    "16": "ground track field",
+    "17": "harbor",
+    "18": "industrial area",
+    "19": "intersection",
+    "20": "island",
+    "21": "lake",
+    "22": "meadow",
+    "23": "medium residential",
+    "24": "mobile home park",
+    "25": "mountain",
+    "26": "overpass",
+    "27": "palace",
+    "28": "parking lot",
+    "29": "railway",
+    "30": "railway station",
+    "31": "rectangular farmland",
+    "32": "river",
+    "33": "roundabout",
+    "34": "runway",
+    "35": "sea ice",
+    "36": "ship",
+    "37": "snowberg",
+    "38": "sparse residential",
+    "39": "stadium",
+    "40": "storage tank",
+    "41": "tennis court",
+    "42": "terrace",
+    "43": "thermal power station",
+    "44": "wetland"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "airplane": 0,
+    "airport": 1,
+    "baseball diamond": 2,
+    "basketball court": 3,
+    "beach": 4,
+    "bridge": 5,
+    "chaparral": 6,
+    "church": 7,
+    "circular farmland": 8,
+    "cloud": 9,
+    "commercial area": 10,
+    "dense residential": 11,
+    "desert": 12,
+    "forest": 13,
+    "freeway": 14,
+    "golf course": 15,
+    "ground track field": 16,
+    "harbor": 17,
+    "industrial area": 18,
+    "intersection": 19,
+    "island": 20,
+    "lake": 21,
+    "meadow": 22,
+    "medium residential": 23,
+    "mobile home park": 24,
+    "mountain": 25,
+    "overpass": 26,
+    "palace": 27,
+    "parking lot": 28,
+    "railway": 29,
+    "railway station": 30,
+    "rectangular farmland": 31,
+    "river": 32,
+    "roundabout": 33,
+    "runway": 34,
+    "sea ice": 35,
+    "ship": 36,
+    "snowberg": 37,
+    "sparse residential": 38,
+    "stadium": 39,
+    "storage tank": 40,
+    "tennis court": 41,
+    "terrace": 42,
+    "thermal power station": 43,
+    "wetland": 44
+  },
+  "model_type": "siglip",
+  "problem_type": "single_label_classification",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_size": 768,
+    "torch_dtype": "float32",
+    "vocab_size": 256000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 224,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "torch_dtype": "float32"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7735b9c19f11a56c6b5f961a56bbf3642ab81f80f42667c04d85b912688995
+size 371700268

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5371dc4f3b7759a694db9f7dd1b77d5c2e28b4074a617a682427c213e9fb3ec6
+size 5304