initial commit

config.json

@@ -0,0 +1,44 @@
+{
+  "_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": "anger",
+    "1": "contempt",
+    "2": "disgust",
+    "3": "fear",
+    "4": "happy",
+    "5": "neutral",
+    "6": "sad",
+    "7": "surprise"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": "0",
+    "contempt": "1",
+    "disgust": "2",
+    "fear": "3",
+    "happy": "4",
+    "neutral": "5",
+    "sad": "6",
+    "surprise": "7"
+  },
+  "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": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32fbdcb26859cf47e6ea7b10bff0558a9901edecc411773aba294da85ed7c3f
+size 343242432

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690808fee9d7eba792214b3c1022d0825bb7494c0f66db97f7c7985d9069025b
+size 686606219

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": "ViTImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e8435ae8c920caa0d57fec9edc0421965614c6ec6940211de3c5a3729f386e
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a0831807cfe3ccf0a632a824659c9e7bb8c5459ee8419abb6191bcc43df94a4
+size 1465

trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_metric": 0.53125,
+  "best_model_checkpoint": "C:\\Users\\stanl\\Documents\\Belajar AI Engineer\\Phase 1 - Core AI Foundation\\Project 0 - Visual Emotion Recognition\\model\\checkpoint-160",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.19375,
+      "eval_loss": 2.0662333965301514,
+      "eval_runtime": 13.2579,
+      "eval_samples_per_second": 12.068,
+      "eval_steps_per_second": 1.509,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.26875,
+      "eval_loss": 2.019904613494873,
+      "eval_runtime": 13.0513,
+      "eval_samples_per_second": 12.259,
+      "eval_steps_per_second": 1.532,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3125,
+      "eval_loss": 1.9013290405273438,
+      "eval_runtime": 13.5256,
+      "eval_samples_per_second": 11.829,
+      "eval_steps_per_second": 1.479,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3625,
+      "eval_loss": 1.6900867223739624,
+      "eval_runtime": 14.0497,
+      "eval_samples_per_second": 11.388,
+      "eval_steps_per_second": 1.424,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.45625,
+      "eval_loss": 1.5257279872894287,
+      "eval_runtime": 13.7295,
+      "eval_samples_per_second": 11.654,
+      "eval_steps_per_second": 1.457,
+      "step": 100
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.45625,
+      "eval_loss": 1.4562708139419556,
+      "eval_runtime": 13.9702,
+      "eval_samples_per_second": 11.453,
+      "eval_steps_per_second": 1.432,
+      "step": 120
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.49375,
+      "eval_loss": 1.3860729932785034,
+      "eval_runtime": 13.8523,
+      "eval_samples_per_second": 11.55,
+      "eval_steps_per_second": 1.444,
+      "step": 140
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.53125,
+      "eval_loss": 1.349557876586914,
+      "eval_runtime": 14.5066,
+      "eval_samples_per_second": 11.029,
+      "eval_steps_per_second": 1.379,
+      "step": 160
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 3.967803229785293e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453da15a202441a3c621c8beebe038ea7f52f1aa55c21c8b9970dcd06051fb9f
+size 5777