Upload folder using huggingface_hub

checkpoint-1190/config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "Child 0-12",
+    "1": "Teenager 13-20",
+    "2": "Adult 21-44",
+    "3": "Middle Age 45-64",
+    "4": "Aged 65+"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Adult 21-44": 2,
+    "Aged 65+": 4,
+    "Child 0-12": 0,
+    "Middle Age 45-64": 3,
+    "Teenager 13-20": 1
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "4.57.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

checkpoint-1190/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07352e52a9d04b444234bc7fdce0937588d811fff4603c9cc18776c1853f67bf
+size 86695548

checkpoint-1190/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4875411e8c0d535b1fd85d0436643875ff02e1595ec14850e9ab405da8a0c943
+size 173507339

checkpoint-1190/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-1190/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0fea880db68c60449840e725448b65c06c7b8576a88e765d1284ec552448ac
+size 14645

checkpoint-1190/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f75c72ecb4036b4fce96fdb2ffc5536718b0f3642ed55affa47d7eef31d9fbb
+size 1465

checkpoint-1190/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_global_step": 1190,
+  "best_metric": 0.35589027404785156,
+  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-1190",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1190,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 36.58893585205078,
+      "learning_rate": 1.6929914529914532e-05,
+      "loss": 0.8451,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8110012620950778,
+      "eval_loss": 0.4803926944732666,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 184.4364,
+      "eval_samples_per_second": 103.103,
+      "eval_steps_per_second": 12.888,
+      "step": 595
+    },
+    {
+      "epoch": 1.680672268907563,
+      "grad_norm": 25.577220916748047,
+      "learning_rate": 1.3511111111111112e-05,
+      "loss": 0.5616,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8604859066049643,
+      "eval_loss": 0.35589027404785156,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 182.6442,
+      "eval_samples_per_second": 104.115,
+      "eval_steps_per_second": 13.014,
+      "step": 1190
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2975,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 7.416809333563392e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1190/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4ead4878e2e55fe3a4fe39438d2aaee6578e9b7eb9c1e0638d6c33b6fd4199
+size 5777

checkpoint-1785/config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "Child 0-12",
+    "1": "Teenager 13-20",
+    "2": "Adult 21-44",
+    "3": "Middle Age 45-64",
+    "4": "Aged 65+"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Adult 21-44": 2,
+    "Aged 65+": 4,
+    "Child 0-12": 0,
+    "Middle Age 45-64": 3,
+    "Teenager 13-20": 1
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "4.57.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

checkpoint-1785/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e46998bf31cf598ec9e64a99020bb32261f3c05c3f58218c2c4cd3866ef827
+size 86695548

checkpoint-1785/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f26a2d4a8b8002521d2986ed0cd612062f6e54b864a4a54c4c8780c42e154f
+size 173507339

checkpoint-1785/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-1785/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b99619fd48f4c73b844833968383dc2aa4ede042c19b949f9a572817307f66
+size 14645

checkpoint-1785/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0107ac088db75354f166f3d8151158e80817f1e001de3d620e5df182bb7aa957
+size 1465

checkpoint-1785/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_global_step": 1785,
+  "best_metric": 0.26440638303756714,
+  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-1785",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1785,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 36.58893585205078,
+      "learning_rate": 1.6929914529914532e-05,
+      "loss": 0.8451,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8110012620950778,
+      "eval_loss": 0.4803926944732666,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 184.4364,
+      "eval_samples_per_second": 103.103,
+      "eval_steps_per_second": 12.888,
+      "step": 595
+    },
+    {
+      "epoch": 1.680672268907563,
+      "grad_norm": 25.577220916748047,
+      "learning_rate": 1.3511111111111112e-05,
+      "loss": 0.5616,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8604859066049643,
+      "eval_loss": 0.35589027404785156,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 182.6442,
+      "eval_samples_per_second": 104.115,
+      "eval_steps_per_second": 13.014,
+      "step": 1190
+    },
+    {
+      "epoch": 2.5210084033613445,
+      "grad_norm": 22.501468658447266,
+      "learning_rate": 1.0092307692307693e-05,
+      "loss": 0.4402,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8958245687841817,
+      "eval_loss": 0.26440638303756714,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 185.7803,
+      "eval_samples_per_second": 102.357,
+      "eval_steps_per_second": 12.795,
+      "step": 1785
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2975,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.1125214000345088e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1785/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4ead4878e2e55fe3a4fe39438d2aaee6578e9b7eb9c1e0638d6c33b6fd4199
+size 5777

checkpoint-2380/config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "Child 0-12",
+    "1": "Teenager 13-20",
+    "2": "Adult 21-44",
+    "3": "Middle Age 45-64",
+    "4": "Aged 65+"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Adult 21-44": 2,
+    "Aged 65+": 4,
+    "Child 0-12": 0,
+    "Middle Age 45-64": 3,
+    "Teenager 13-20": 1
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "4.57.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

checkpoint-2380/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae7c9ede706184b084d89f9fe58b48d90f1520d35aa2ea83f086844db8dbf90
+size 86695548

checkpoint-2380/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c11a111f4b77c50309b584bb9d179e57794465003ddc8fed0e3ddf7ff59ca4
+size 173507339

checkpoint-2380/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-2380/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac69cff8b26e2632aa36cfe5c915c1da831540a43a12793fac26cffeffd7f018
+size 14645

checkpoint-2380/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9b29c1e14bde64c335f10467cf6285f0db73e33a154c94e6426b6cc6072b53
+size 1465

checkpoint-2380/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_global_step": 2380,
+  "best_metric": 0.15674497187137604,
+  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-2380",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 36.58893585205078,
+      "learning_rate": 1.6929914529914532e-05,
+      "loss": 0.8451,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8110012620950778,
+      "eval_loss": 0.4803926944732666,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 184.4364,
+      "eval_samples_per_second": 103.103,
+      "eval_steps_per_second": 12.888,
+      "step": 595
+    },
+    {
+      "epoch": 1.680672268907563,
+      "grad_norm": 25.577220916748047,
+      "learning_rate": 1.3511111111111112e-05,
+      "loss": 0.5616,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8604859066049643,
+      "eval_loss": 0.35589027404785156,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 182.6442,
+      "eval_samples_per_second": 104.115,
+      "eval_steps_per_second": 13.014,
+      "step": 1190
+    },
+    {
+      "epoch": 2.5210084033613445,
+      "grad_norm": 22.501468658447266,
+      "learning_rate": 1.0092307692307693e-05,
+      "loss": 0.4402,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8958245687841817,
+      "eval_loss": 0.26440638303756714,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 185.7803,
+      "eval_samples_per_second": 102.357,
+      "eval_steps_per_second": 12.795,
+      "step": 1785
+    },
+    {
+      "epoch": 3.361344537815126,
+      "grad_norm": 27.099328994750977,
+      "learning_rate": 6.673504273504275e-06,
+      "loss": 0.3172,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9453092132940681,
+      "eval_loss": 0.15674497187137604,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 181.8977,
+      "eval_samples_per_second": 104.542,
+      "eval_steps_per_second": 13.068,
+      "step": 2380
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2975,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.4833618667126784e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2380/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4ead4878e2e55fe3a4fe39438d2aaee6578e9b7eb9c1e0638d6c33b6fd4199
+size 5777

checkpoint-2975/config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "Child 0-12",
+    "1": "Teenager 13-20",
+    "2": "Adult 21-44",
+    "3": "Middle Age 45-64",
+    "4": "Aged 65+"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Adult 21-44": 2,
+    "Aged 65+": 4,
+    "Child 0-12": 0,
+    "Middle Age 45-64": 3,
+    "Teenager 13-20": 1
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "4.57.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

checkpoint-2975/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8636d6e9ceb085bddd789514fd5d76530eca6981e91ec63c07e9e9c0a3f1c6
+size 86695548

checkpoint-2975/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9ed98480bfcae67203f6be416f9657396e05e2674bcf5ea3d66c5c80dc3404
+size 173507339

checkpoint-2975/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-2975/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73068c589ce4d6fd20a35518dde8f3d307e57b652e65f960e80544ca67a4bf93
+size 14645

checkpoint-2975/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4dc6c6efc1e511bd1933b9a99504a13b1009dcfe1068d8dec69ec4ace54d08
+size 1465

checkpoint-2975/trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_global_step": 2975,
+  "best_metric": 0.12348528951406479,
+  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-2975",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2975,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 36.58893585205078,
+      "learning_rate": 1.6929914529914532e-05,
+      "loss": 0.8451,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8110012620950778,
+      "eval_loss": 0.4803926944732666,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 184.4364,
+      "eval_samples_per_second": 103.103,
+      "eval_steps_per_second": 12.888,
+      "step": 595
+    },
+    {
+      "epoch": 1.680672268907563,
+      "grad_norm": 25.577220916748047,
+      "learning_rate": 1.3511111111111112e-05,
+      "loss": 0.5616,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8604859066049643,
+      "eval_loss": 0.35589027404785156,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 182.6442,
+      "eval_samples_per_second": 104.115,
+      "eval_steps_per_second": 13.014,
+      "step": 1190
+    },
+    {
+      "epoch": 2.5210084033613445,
+      "grad_norm": 22.501468658447266,
+      "learning_rate": 1.0092307692307693e-05,
+      "loss": 0.4402,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8958245687841817,
+      "eval_loss": 0.26440638303756714,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 185.7803,
+      "eval_samples_per_second": 102.357,
+      "eval_steps_per_second": 12.795,
+      "step": 1785
+    },
+    {
+      "epoch": 3.361344537815126,
+      "grad_norm": 27.099328994750977,
+      "learning_rate": 6.673504273504275e-06,
+      "loss": 0.3172,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9453092132940681,
+      "eval_loss": 0.15674497187137604,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 181.8977,
+      "eval_samples_per_second": 104.542,
+      "eval_steps_per_second": 13.068,
+      "step": 2380
+    },
+    {
+      "epoch": 4.201680672268908,
+      "grad_norm": 28.719318389892578,
+      "learning_rate": 3.2547008547008553e-06,
+      "loss": 0.2164,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9559318468657972,
+      "eval_loss": 0.12348528951406479,
+      "eval_model_preparation_time": 0.0159,
+      "eval_runtime": 186.47,
+      "eval_samples_per_second": 101.979,
+      "eval_steps_per_second": 12.747,
+      "step": 2975
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2975,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.854202333390848e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2975/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4ead4878e2e55fe3a4fe39438d2aaee6578e9b7eb9c1e0638d6c33b6fd4199
+size 5777

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "MetaClip2ForImageClassification"
+  ],
+  "dtype": "float32",
+  "id2label": {
+    "0": "Child 0-12",
+    "1": "Teenager 13-20",
+    "2": "Adult 21-44",
+    "3": "Middle Age 45-64",
+    "4": "Aged 65+"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Adult 21-44": 2,
+    "Aged 65+": 4,
+    "Child 0-12": 0,
+    "Middle Age 45-64": 3,
+    "Teenager 13-20": 1
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "problem_type": "single_label_classification",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "projection_dim": 384,
+    "vocab_size": 901629
+  },
+  "transformers_version": "4.57.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8636d6e9ceb085bddd789514fd5d76530eca6981e91ec63c07e9e9c0a3f1c6
+size 86695548

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "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:ce4ead4878e2e55fe3a4fe39438d2aaee6578e9b7eb9c1e0638d6c33b6fd4199
+size 5777