Upload folder using huggingface_hub

checkpoint-1012/config.json

@@ -0,0 +1,100 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "\u090b",
+    "1": "\u0915",
+    "2": "\u0916",
+    "3": "\u0917",
+    "4": "\u0918",
+    "5": "\u0919",
+    "6": "\u091a",
+    "7": "\u091b",
+    "8": "\u091c",
+    "9": "\u091d",
+    "10": "\u091f",
+    "11": "\u0920",
+    "12": "\u0922",
+    "13": "\u0923",
+    "14": "\u0924",
+    "15": "\u0925",
+    "16": "\u0926",
+    "17": "\u0928",
+    "18": "\u092a",
+    "19": "\u092b",
+    "20": "\u092c",
+    "21": "\u092d",
+    "22": "\u092e",
+    "23": "\u092f",
+    "24": "\u0930",
+    "25": "\u0932",
+    "26": "\u0935",
+    "27": "\u0938",
+    "28": "\u0939"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "\u090b": 0,
+    "\u0915": 1,
+    "\u0916": 2,
+    "\u0917": 3,
+    "\u0918": 4,
+    "\u0919": 5,
+    "\u091a": 6,
+    "\u091b": 7,
+    "\u091c": 8,
+    "\u091d": 9,
+    "\u091f": 10,
+    "\u0920": 11,
+    "\u0922": 12,
+    "\u0923": 13,
+    "\u0924": 14,
+    "\u0925": 15,
+    "\u0926": 16,
+    "\u0928": 17,
+    "\u092a": 18,
+    "\u092b": 19,
+    "\u092c": 20,
+    "\u092d": 21,
+    "\u092e": 22,
+    "\u092f": 23,
+    "\u0930": 24,
+    "\u0932": 25,
+    "\u0935": 26,
+    "\u0938": 27,
+    "\u0939": 28
+  },
+  "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-1012/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eeed8acb82365002266bf98361ceebe19f9b74d7c885c5c8854bb58082b85b5
+size 371651052

checkpoint-1012/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab5ec3029daa57091d26102843cc6f8836441fb1ec8c16e2d2fddf7a9962410
+size 686721786

checkpoint-1012/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-1012/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60dcddd0310ead2325fb47c425ece444a249bce9a834f715a65aba50af7e4e65
+size 14244

checkpoint-1012/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a3d4b07dce2a397d81d3bb6d2ef9dfe1be3b5c8b1421b9e8b8a06fb1bda866
+size 1064

checkpoint-1012/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_global_step": 1012,
+  "best_metric": 0.18154847621917725,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1012",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1012,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9881422924901185,
+      "grad_norm": 7.464842796325684,
+      "learning_rate": 0.0002661122661122661,
+      "loss": 1.5544,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6886938245657415,
+      "eval_loss": 0.9519435167312622,
+      "eval_model_preparation_time": 0.0026,
+      "eval_runtime": 216.1541,
+      "eval_samples_per_second": 74.84,
+      "eval_steps_per_second": 9.359,
+      "step": 506
+    },
+    {
+      "epoch": 1.9762845849802373,
+      "grad_norm": 4.09387731552124,
+      "learning_rate": 6.237006237006238e-06,
+      "loss": 0.3209,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.942510972368177,
+      "eval_loss": 0.18154847621917725,
+      "eval_model_preparation_time": 0.0026,
+      "eval_runtime": 211.4297,
+      "eval_samples_per_second": 76.512,
+      "eval_steps_per_second": 9.568,
+      "step": 1012
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1012,
+  "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": 2.7104320294495396e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1012/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c09778d5590b0474b689b82857e5d45343043143dcc53e05f5cce8ccfc8a9d
+size 5304

checkpoint-506/config.json

@@ -0,0 +1,100 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "\u090b",
+    "1": "\u0915",
+    "2": "\u0916",
+    "3": "\u0917",
+    "4": "\u0918",
+    "5": "\u0919",
+    "6": "\u091a",
+    "7": "\u091b",
+    "8": "\u091c",
+    "9": "\u091d",
+    "10": "\u091f",
+    "11": "\u0920",
+    "12": "\u0922",
+    "13": "\u0923",
+    "14": "\u0924",
+    "15": "\u0925",
+    "16": "\u0926",
+    "17": "\u0928",
+    "18": "\u092a",
+    "19": "\u092b",
+    "20": "\u092c",
+    "21": "\u092d",
+    "22": "\u092e",
+    "23": "\u092f",
+    "24": "\u0930",
+    "25": "\u0932",
+    "26": "\u0935",
+    "27": "\u0938",
+    "28": "\u0939"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "\u090b": 0,
+    "\u0915": 1,
+    "\u0916": 2,
+    "\u0917": 3,
+    "\u0918": 4,
+    "\u0919": 5,
+    "\u091a": 6,
+    "\u091b": 7,
+    "\u091c": 8,
+    "\u091d": 9,
+    "\u091f": 10,
+    "\u0920": 11,
+    "\u0922": 12,
+    "\u0923": 13,
+    "\u0924": 14,
+    "\u0925": 15,
+    "\u0926": 16,
+    "\u0928": 17,
+    "\u092a": 18,
+    "\u092b": 19,
+    "\u092c": 20,
+    "\u092d": 21,
+    "\u092e": 22,
+    "\u092f": 23,
+    "\u0930": 24,
+    "\u0932": 25,
+    "\u0935": 26,
+    "\u0938": 27,
+    "\u0939": 28
+  },
+  "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-506/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa903d122e259342a46c3ac081f8d19563114eb9bb7db7c5bfdb67d24a62bdd4
+size 371651052

checkpoint-506/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb0a64e7796e9eb478c5cf7570b66552e509a93c10adbf0505432dda9765b3a
+size 686721786

checkpoint-506/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-506/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7a3ff1649e401d94a91becbafa8d11f11d4e193fd044acf4e7235db5744c68
+size 14244

checkpoint-506/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2314145c30e33e8a87c3dc43ed7c74c396737c2ecc3740d8dca1984b5a8e2ab6
+size 1064

checkpoint-506/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_global_step": 506,
+  "best_metric": 0.9519435167312622,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-506",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 506,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9881422924901185,
+      "grad_norm": 7.464842796325684,
+      "learning_rate": 0.0002661122661122661,
+      "loss": 1.5544,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6886938245657415,
+      "eval_loss": 0.9519435167312622,
+      "eval_model_preparation_time": 0.0026,
+      "eval_runtime": 216.1541,
+      "eval_samples_per_second": 74.84,
+      "eval_steps_per_second": 9.359,
+      "step": 506
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1012,
+  "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": 1.3552160147247698e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-506/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c09778d5590b0474b689b82857e5d45343043143dcc53e05f5cce8ccfc8a9d
+size 5304

config.json

@@ -0,0 +1,100 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "\u090b",
+    "1": "\u0915",
+    "2": "\u0916",
+    "3": "\u0917",
+    "4": "\u0918",
+    "5": "\u0919",
+    "6": "\u091a",
+    "7": "\u091b",
+    "8": "\u091c",
+    "9": "\u091d",
+    "10": "\u091f",
+    "11": "\u0920",
+    "12": "\u0922",
+    "13": "\u0923",
+    "14": "\u0924",
+    "15": "\u0925",
+    "16": "\u0926",
+    "17": "\u0928",
+    "18": "\u092a",
+    "19": "\u092b",
+    "20": "\u092c",
+    "21": "\u092d",
+    "22": "\u092e",
+    "23": "\u092f",
+    "24": "\u0930",
+    "25": "\u0932",
+    "26": "\u0935",
+    "27": "\u0938",
+    "28": "\u0939"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "\u090b": 0,
+    "\u0915": 1,
+    "\u0916": 2,
+    "\u0917": 3,
+    "\u0918": 4,
+    "\u0919": 5,
+    "\u091a": 6,
+    "\u091b": 7,
+    "\u091c": 8,
+    "\u091d": 9,
+    "\u091f": 10,
+    "\u0920": 11,
+    "\u0922": 12,
+    "\u0923": 13,
+    "\u0924": 14,
+    "\u0925": 15,
+    "\u0926": 16,
+    "\u0928": 17,
+    "\u092a": 18,
+    "\u092b": 19,
+    "\u092c": 20,
+    "\u092d": 21,
+    "\u092e": 22,
+    "\u092f": 23,
+    "\u0930": 24,
+    "\u0932": 25,
+    "\u0935": 26,
+    "\u0938": 27,
+    "\u0939": 28
+  },
+  "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 sha256:4eeed8acb82365002266bf98361ceebe19f9b74d7c885c5c8854bb58082b85b5
+size 371651052

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 sha256:13c09778d5590b0474b689b82857e5d45343043143dcc53e05f5cce8ccfc8a9d
+size 5304