Upload folder using huggingface_hub

checkpoint-3750/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Female",
+    "1": "Male"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Female": 0,
+    "Male": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3"
+}

checkpoint-3750/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:311bf7c7de91b9dcde135c4788a634cae812240543afd5bff1c905440ec219cb
+size 343223968

checkpoint-3750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7baf75beccb50d8ac94eb0f3989b73e2a57473ea0312b17b9e18ae3232dafdc
+size 686568890

checkpoint-3750/preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-3750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
+size 14244

checkpoint-3750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6b3456c57b8d97ed05bd1eb762c0f01179b387dafb386256f7065ee85b5026
+size 1064

checkpoint-3750/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.18133555352687836,
+  "best_model_checkpoint": "fairface_gender_image_detection/checkpoint-3750",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 3.194249391555786,
+      "learning_rate": 8.273542600896861e-06,
+      "loss": 0.3452,
+      "step": 500
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.3906941413879395,
+      "learning_rate": 7.4663677130044845e-06,
+      "loss": 0.1955,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.958942174911499,
+      "learning_rate": 6.6591928251121084e-06,
+      "loss": 0.1709,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.915,
+      "eval_loss": 0.21168974041938782,
+      "eval_model_preparation_time": 0.0041,
+      "eval_runtime": 890.2454,
+      "eval_samples_per_second": 11.233,
+      "eval_steps_per_second": 1.404,
+      "step": 1875
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 6.014321804046631,
+      "learning_rate": 5.852017937219731e-06,
+      "loss": 0.154,
+      "step": 2000
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 10.029616355895996,
+      "learning_rate": 5.044843049327354e-06,
+      "loss": 0.1161,
+      "step": 2500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.819401979446411,
+      "learning_rate": 4.237668161434978e-06,
+      "loss": 0.1218,
+      "step": 3000
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.9613158702850342,
+      "learning_rate": 3.430493273542601e-06,
+      "loss": 0.1212,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9342,
+      "eval_loss": 0.18133555352687836,
+      "eval_model_preparation_time": 0.0041,
+      "eval_runtime": 894.9262,
+      "eval_samples_per_second": 11.174,
+      "eval_steps_per_second": 1.397,
+      "step": 3750
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 9.29903875375104e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aea97385d32c3a92090bc68995c820f81da587261b707dea4cb30f2b69c8f60
+size 5240

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa9be212b0ea1274957c7fedf7ba5d526e963f71de623a9c4f53413760047cc
+oid sha256:311bf7c7de91b9dcde135c4788a634cae812240543afd5bff1c905440ec219cb
 size 343223968

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4259b780c969be6dcb2cd47d0fe7da7c8b92e370d789469f7190c16cf2f18673
+oid sha256:5aea97385d32c3a92090bc68995c820f81da587261b707dea4cb30f2b69c8f60
 size 5240