Upload folder using huggingface_hub

checkpoint-1816/config.json

@@ -0,0 +1,40 @@
+{
+  "_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": "Ahegao",
+    "1": "Angry",
+    "2": "Happy",
+    "3": "Neutral",
+    "4": "Sad",
+    "5": "Surprise"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Ahegao": 0,
+    "Angry": 1,
+    "Happy": 2,
+    "Neutral": 3,
+    "Sad": 4,
+    "Surprise": 5
+  },
+  "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": "4.41.2"
+}

checkpoint-1816/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94525fb26dba2d214bc94ca26f08595eb2cb0772870f101c7ce17ee73312940
+size 343236280

checkpoint-1816/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7c964f62aacf0f73ddab077040453aebf1b486255eebf32da96d7ca3e177ba
+size 686593029

checkpoint-1816/preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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-1816/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731ece137e5aa3227cb68c27fb95f4d3f48a5cdbc3a8f9775ac89791b5acdfe1
+size 14575

checkpoint-1816/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323965c452bc07ceb4fe6e8ee76e3f88e944c0d346b0ae79ac0c9d429433262d
+size 627

checkpoint-1816/trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 1.747721552848816,
+  "best_model_checkpoint": "face_emotions_image_detection/checkpoint-1816",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1816,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.20258665287118469,
+      "eval_loss": 1.7820897102355957,
+      "eval_runtime": 182.1671,
+      "eval_samples_per_second": 53.056,
+      "eval_steps_per_second": 1.663,
+      "step": 227
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2313502327987584,
+      "eval_loss": 1.7733079195022583,
+      "eval_runtime": 139.8617,
+      "eval_samples_per_second": 69.104,
+      "eval_steps_per_second": 2.166,
+      "step": 454
+    },
+    {
+      "epoch": 2.202643171806167,
+      "grad_norm": 0.9193387031555176,
+      "learning_rate": 1.4903737259343148e-07,
+      "loss": 1.7844,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.26083807553026384,
+      "eval_loss": 1.7658255100250244,
+      "eval_runtime": 138.2124,
+      "eval_samples_per_second": 69.929,
+      "eval_steps_per_second": 2.192,
+      "step": 681
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.28701500258665286,
+      "eval_loss": 1.759501338005066,
+      "eval_runtime": 137.9413,
+      "eval_samples_per_second": 70.066,
+      "eval_steps_per_second": 2.197,
+      "step": 908
+    },
+    {
+      "epoch": 4.405286343612334,
+      "grad_norm": 0.9177930355072021,
+      "learning_rate": 9.241223103057757e-08,
+      "loss": 1.7598,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3092602172788412,
+      "eval_loss": 1.7544183731079102,
+      "eval_runtime": 139.1755,
+      "eval_samples_per_second": 69.445,
+      "eval_steps_per_second": 2.177,
+      "step": 1135
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.32177961717537507,
+      "eval_loss": 1.750722885131836,
+      "eval_runtime": 138.002,
+      "eval_samples_per_second": 70.035,
+      "eval_steps_per_second": 2.196,
+      "step": 1362
+    },
+    {
+      "epoch": 6.607929515418502,
+      "grad_norm": 0.8425195813179016,
+      "learning_rate": 3.5787089467723666e-08,
+      "loss": 1.7423,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.33005690636316604,
+      "eval_loss": 1.7484561204910278,
+      "eval_runtime": 138.5918,
+      "eval_samples_per_second": 69.737,
+      "eval_steps_per_second": 2.186,
+      "step": 1589
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.3322296947749612,
+      "eval_loss": 1.747721552848816,
+      "eval_runtime": 138.6669,
+      "eval_samples_per_second": 69.699,
+      "eval_steps_per_second": 2.185,
+      "step": 1816
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1816,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 8.987533185659535e+18,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1816/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26ce6d664479197fb0fb66d81ef5614be50cf3e7dcc39e6b656d601985f500c
+size 4603

config.json

@@ -0,0 +1,40 @@
+{
+  "_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": "Ahegao",
+    "1": "Angry",
+    "2": "Happy",
+    "3": "Neutral",
+    "4": "Sad",
+    "5": "Surprise"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Ahegao": 0,
+    "Angry": 1,
+    "Happy": 2,
+    "Neutral": 3,
+    "Sad": 4,
+    "Surprise": 5
+  },
+  "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": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94525fb26dba2d214bc94ca26f08595eb2cb0772870f101c7ce17ee73312940
+size 343236280

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26ce6d664479197fb0fb66d81ef5614be50cf3e7dcc39e6b656d601985f500c
+size 4603