Upload folder using huggingface_hub

checkpoint-471/config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "high resolution image",
+    "1": "low resolution image"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "high resolution image": 0,
+    "low resolution image": 1
+  },
+  "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.dev0",
+  "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-471/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e235193822f56e34ce8aef2f0799d17e903024f5574753109da1351de72dcd0c
+size 371567992

checkpoint-471/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c7ae4ae30a583f9d5abc2319eaf6de15c0d05610fd6e5d1b46a8555b3be08c
+size 686555770

checkpoint-471/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-471/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1635d34d7ef35cbcadef0d515cae13c0a24a81b57addc13278b81727e336ff10
+size 14244

checkpoint-471/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4459bcc2da2716c88601bb32e5f1e8f8dca943aa67548f8c7351bacc5e19f965
+size 1064

checkpoint-471/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_global_step": 471,
+  "best_metric": 0.4816523790359497,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-471",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 471,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7139154704944178,
+      "eval_loss": 0.5481679439544678,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.3671,
+      "eval_samples_per_second": 40.332,
+      "eval_steps_per_second": 5.042,
+      "step": 157
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7567783094098883,
+      "eval_loss": 0.48407095670700073,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.5024,
+      "eval_samples_per_second": 40.288,
+      "eval_steps_per_second": 5.036,
+      "step": 314
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.733652312599681,
+      "eval_loss": 0.4816523790359497,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 122.2853,
+      "eval_samples_per_second": 41.019,
+      "eval_steps_per_second": 5.127,
+      "step": 471
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 942,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 1.260352701119103e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-471/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257ee6518ff12f4a25db68491a875c1516136684318f2995c2f0fbe07ac7602e
+size 5304

checkpoint-628/config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "high resolution image",
+    "1": "low resolution image"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "high resolution image": 0,
+    "low resolution image": 1
+  },
+  "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.dev0",
+  "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-628/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60cfb3df637122c8c193b75ce7064bef315bbe0c420b955001578c25b2322916
+size 371567992

checkpoint-628/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5afa2f1883e4fd354819f6601bbb612137384bb9cbf3c67f4a8554fedd6919
+size 686555770

checkpoint-628/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-628/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c16939bc58992c20820c994ac01515b985e62daedce71acc0a71c5741e5bb3
+size 14244

checkpoint-628/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3123e68ca59c4165bc4f9042ca2c5c37afca6b63bf9d651c86be544a2a1cedac
+size 1064

checkpoint-628/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_global_step": 628,
+  "best_metric": 0.4302399456501007,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-628",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 628,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7139154704944178,
+      "eval_loss": 0.5481679439544678,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.3671,
+      "eval_samples_per_second": 40.332,
+      "eval_steps_per_second": 5.042,
+      "step": 157
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7567783094098883,
+      "eval_loss": 0.48407095670700073,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.5024,
+      "eval_samples_per_second": 40.288,
+      "eval_steps_per_second": 5.036,
+      "step": 314
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.733652312599681,
+      "eval_loss": 0.4816523790359497,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 122.2853,
+      "eval_samples_per_second": 41.019,
+      "eval_steps_per_second": 5.127,
+      "step": 471
+    },
+    {
+      "epoch": 3.1847133757961785,
+      "grad_norm": 33.35067367553711,
+      "learning_rate": 2.477578475336323e-06,
+      "loss": 0.5312,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7651515151515151,
+      "eval_loss": 0.4302399456501007,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 123.8512,
+      "eval_samples_per_second": 40.5,
+      "eval_steps_per_second": 5.063,
+      "step": 628
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 942,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 1.680470268158804e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-628/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257ee6518ff12f4a25db68491a875c1516136684318f2995c2f0fbe07ac7602e
+size 5304

checkpoint-785/config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "high resolution image",
+    "1": "low resolution image"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "high resolution image": 0,
+    "low resolution image": 1
+  },
+  "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.dev0",
+  "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-785/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13454eaa7d6b7c66341c299a4be323868edd5f99fa4afc70e11d4c210c4a58bb
+size 371567992

checkpoint-785/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8350daa589ebe1c4158aa85ff8ba272563833842544565013f12084a722b6d5e
+size 686555770

checkpoint-785/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-785/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1f353c22c2572e290982ee469c524213e7115a6af1ec437f4e4f101d2e4630d
+size 14244

checkpoint-785/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3ad598951542bd8f1b74c73d2ae7c632c752afc052cd1e1f7b5549e4b2777b
+size 1064

checkpoint-785/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_global_step": 785,
+  "best_metric": 0.4116573631763458,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-785",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 785,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7139154704944178,
+      "eval_loss": 0.5481679439544678,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.3671,
+      "eval_samples_per_second": 40.332,
+      "eval_steps_per_second": 5.042,
+      "step": 157
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7567783094098883,
+      "eval_loss": 0.48407095670700073,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.5024,
+      "eval_samples_per_second": 40.288,
+      "eval_steps_per_second": 5.036,
+      "step": 314
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.733652312599681,
+      "eval_loss": 0.4816523790359497,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 122.2853,
+      "eval_samples_per_second": 41.019,
+      "eval_steps_per_second": 5.127,
+      "step": 471
+    },
+    {
+      "epoch": 3.1847133757961785,
+      "grad_norm": 33.35067367553711,
+      "learning_rate": 2.477578475336323e-06,
+      "loss": 0.5312,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7651515151515151,
+      "eval_loss": 0.4302399456501007,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 123.8512,
+      "eval_samples_per_second": 40.5,
+      "eval_steps_per_second": 5.063,
+      "step": 628
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7811004784688995,
+      "eval_loss": 0.4116573631763458,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.6627,
+      "eval_samples_per_second": 40.237,
+      "eval_steps_per_second": 5.03,
+      "step": 785
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 942,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 2.100587835198505e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-785/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257ee6518ff12f4a25db68491a875c1516136684318f2995c2f0fbe07ac7602e
+size 5304

checkpoint-942/config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "high resolution image",
+    "1": "low resolution image"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "high resolution image": 0,
+    "low resolution image": 1
+  },
+  "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.dev0",
+  "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-942/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c717d0f12db50f92ad27eeb50bc6febd5a8134018157e62fd31c78e2de71f459
+size 371567992

checkpoint-942/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438a5e38cf2cfaf269a8475691006e4eda70a34de9f1e8ded4a422d2ae9e38e5
+size 686555770

checkpoint-942/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-942/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e8b8c83d1b0671dddb8be40aa997b0cbcd73cd86030a0e76f225d442ae2ff7
+size 14244

checkpoint-942/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c9b94afe22fd897665b1527971a0a237e746c84f95701f77b94ddf7f03ae00
+size 1064

checkpoint-942/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_global_step": 942,
+  "best_metric": 0.40608102083206177,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-942",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 942,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7139154704944178,
+      "eval_loss": 0.5481679439544678,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.3671,
+      "eval_samples_per_second": 40.332,
+      "eval_steps_per_second": 5.042,
+      "step": 157
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7567783094098883,
+      "eval_loss": 0.48407095670700073,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.5024,
+      "eval_samples_per_second": 40.288,
+      "eval_steps_per_second": 5.036,
+      "step": 314
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.733652312599681,
+      "eval_loss": 0.4816523790359497,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 122.2853,
+      "eval_samples_per_second": 41.019,
+      "eval_steps_per_second": 5.127,
+      "step": 471
+    },
+    {
+      "epoch": 3.1847133757961785,
+      "grad_norm": 33.35067367553711,
+      "learning_rate": 2.477578475336323e-06,
+      "loss": 0.5312,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7651515151515151,
+      "eval_loss": 0.4302399456501007,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 123.8512,
+      "eval_samples_per_second": 40.5,
+      "eval_steps_per_second": 5.063,
+      "step": 628
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7811004784688995,
+      "eval_loss": 0.4116573631763458,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 124.6627,
+      "eval_samples_per_second": 40.237,
+      "eval_steps_per_second": 5.03,
+      "step": 785
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7830940988835726,
+      "eval_loss": 0.40608102083206177,
+      "eval_model_preparation_time": 0.0027,
+      "eval_runtime": 126.8136,
+      "eval_samples_per_second": 39.554,
+      "eval_steps_per_second": 4.944,
+      "step": 942
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 942,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 2.520705402238206e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-942/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257ee6518ff12f4a25db68491a875c1516136684318f2995c2f0fbe07ac7602e
+size 5304

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "high resolution image",
+    "1": "low resolution image"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "high resolution image": 0,
+    "low resolution image": 1
+  },
+  "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.dev0",
+  "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:c717d0f12db50f92ad27eeb50bc6febd5a8134018157e62fd31c78e2de71f459
+size 371567992

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 sha256:257ee6518ff12f4a25db68491a875c1516136684318f2995c2f0fbe07ac7602e
+size 5304