SeyedAli/Arosal

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vit-Arousal
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# vit-Arousal
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the custom dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8522
+- Accuracy: 0.6294
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.9023        | 0.78  | 100  | 0.8522          | 0.6294   |
+| 0.5376        | 1.56  | 200  | 0.8592          | 0.6686   |
+| 0.2473        | 2.34  | 300  | 0.9559          | 0.6510   |
+| 0.0691        | 3.12  | 400  | 1.1399          | 0.6275   |
+| 0.0821        | 3.91  | 500  | 1.2060          | 0.6392   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.6294117647058823,
+    "eval_loss": 0.852151095867157,
+    "eval_runtime": 9.2884,
+    "eval_samples_per_second": 54.907,
+    "eval_steps_per_second": 6.89,
+    "total_flos": 6.311117323294802e+17,
+    "train_loss": 0.46213533167610876,
+    "train_runtime": 403.5009,
+    "train_samples_per_second": 20.183,
+    "train_steps_per_second": 1.269
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_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": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3",
+    "4": "4"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3",
+    "4": "4"
+  },
+  "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": "4.35.2"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.6294117647058823,
+    "eval_loss": 0.852151095867157,
+    "eval_runtime": 9.2884,
+    "eval_samples_per_second": 54.907,
+    "eval_steps_per_second": 6.89
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337d04c61d44afc1c5cd22cd1aeefc35bf2aa45bcb9bb68710a76c3718f4808d
+size 343233204

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
+  }
+}

runs/Feb12_08-33-02_3945894e4f8b/events.out.tfevents.1707726792.3945894e4f8b.938.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2501318335d20fa2c6225951b3e41a36efdba0e92452c1435fcf3c27dfa57394
+size 14191

runs/Feb12_08-33-02_3945894e4f8b/events.out.tfevents.1707727212.3945894e4f8b.938.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e33c0ceb13db6460fa3b20fe54ba1fcd1aabe16d908c841214c1a083818c8c6
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 6.311117323294802e+17,
+    "train_loss": 0.46213533167610876,
+    "train_runtime": 403.5009,
+    "train_samples_per_second": 20.183,
+    "train_steps_per_second": 1.269
+}

trainer_state.json

@@ -0,0 +1,379 @@
+{
+  "best_metric": 0.852151095867157,
+  "best_model_checkpoint": "./vit-Arousal/checkpoint-100",
+  "epoch": 4.0,
+  "eval_steps": 100,
+  "global_step": 512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019609375,
+      "loss": 1.3074,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001921875,
+      "loss": 1.0019,
+      "step": 20
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018828125,
+      "loss": 0.9923,
+      "step": 30
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000184375,
+      "loss": 0.8658,
+      "step": 40
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00018046875000000002,
+      "loss": 0.9941,
+      "step": 50
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00017656250000000002,
+      "loss": 1.0082,
+      "step": 60
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00017265625,
+      "loss": 0.949,
+      "step": 70
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00016875,
+      "loss": 0.9459,
+      "step": 80
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00016484375,
+      "loss": 0.8496,
+      "step": 90
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001609375,
+      "loss": 0.9023,
+      "step": 100
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.6294117647058823,
+      "eval_loss": 0.852151095867157,
+      "eval_runtime": 9.2104,
+      "eval_samples_per_second": 55.372,
+      "eval_steps_per_second": 6.949,
+      "step": 100
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00015703125,
+      "loss": 0.8067,
+      "step": 110
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.000153125,
+      "loss": 0.8751,
+      "step": 120
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00014921875000000002,
+      "loss": 0.7552,
+      "step": 130
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00014531250000000002,
+      "loss": 0.5661,
+      "step": 140
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00014140625,
+      "loss": 0.549,
+      "step": 150
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0001375,
+      "loss": 0.6449,
+      "step": 160
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013359375,
+      "loss": 0.5941,
+      "step": 170
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001296875,
+      "loss": 0.5656,
+      "step": 180
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00012578125,
+      "loss": 0.542,
+      "step": 190
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00012187500000000001,
+      "loss": 0.5376,
+      "step": 200
+    },
+    {
+      "epoch": 1.56,
+      "eval_accuracy": 0.6686274509803921,
+      "eval_loss": 0.8591523766517639,
+      "eval_runtime": 8.6666,
+      "eval_samples_per_second": 58.846,
+      "eval_steps_per_second": 7.385,
+      "step": 200
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00011796875,
+      "loss": 0.6298,
+      "step": 210
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0001140625,
+      "loss": 0.5563,
+      "step": 220
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00011015625000000001,
+      "loss": 0.6173,
+      "step": 230
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00010625000000000001,
+      "loss": 0.6663,
+      "step": 240
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00010234375,
+      "loss": 0.5781,
+      "step": 250
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.84375e-05,
+      "loss": 0.528,
+      "step": 260
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.453125000000001e-05,
+      "loss": 0.2836,
+      "step": 270
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 9.062500000000001e-05,
+      "loss": 0.2782,
+      "step": 280
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.671875e-05,
+      "loss": 0.2749,
+      "step": 290
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.28125e-05,
+      "loss": 0.2473,
+      "step": 300
+    },
+    {
+      "epoch": 2.34,
+      "eval_accuracy": 0.6509803921568628,
+      "eval_loss": 0.9559371471405029,
+      "eval_runtime": 9.3899,
+      "eval_samples_per_second": 54.314,
+      "eval_steps_per_second": 6.816,
+      "step": 300
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.890625000000001e-05,
+      "loss": 0.1479,
+      "step": 310
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.3088,
+      "step": 320
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.109375e-05,
+      "loss": 0.242,
+      "step": 330
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.71875e-05,
+      "loss": 0.2083,
+      "step": 340
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.328125e-05,
+      "loss": 0.2094,
+      "step": 350
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 5.9375e-05,
+      "loss": 0.1957,
+      "step": 360
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.546875e-05,
+      "loss": 0.1911,
+      "step": 370
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.15625e-05,
+      "loss": 0.2174,
+      "step": 380
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 4.765625e-05,
+      "loss": 0.1176,
+      "step": 390
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 4.375e-05,
+      "loss": 0.0691,
+      "step": 400
+    },
+    {
+      "epoch": 3.12,
+      "eval_accuracy": 0.6274509803921569,
+      "eval_loss": 1.1399476528167725,
+      "eval_runtime": 8.471,
+      "eval_samples_per_second": 60.206,
+      "eval_steps_per_second": 7.555,
+      "step": 400
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 3.984375e-05,
+      "loss": 0.0712,
+      "step": 410
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.59375e-05,
+      "loss": 0.0492,
+      "step": 420
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 3.203125e-05,
+      "loss": 0.0818,
+      "step": 430
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 2.8125000000000003e-05,
+      "loss": 0.0854,
+      "step": 440
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 2.4218750000000003e-05,
+      "loss": 0.1115,
+      "step": 450
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 2.0312500000000002e-05,
+      "loss": 0.1219,
+      "step": 460
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.6406250000000002e-05,
+      "loss": 0.0581,
+      "step": 470
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0745,
+      "step": 480
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 8.59375e-06,
+      "loss": 0.039,
+      "step": 490
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 0.0821,
+      "step": 500
+    },
+    {
+      "epoch": 3.91,
+      "eval_accuracy": 0.6392156862745098,
+      "eval_loss": 1.20601224899292,
+      "eval_runtime": 9.3464,
+      "eval_samples_per_second": 54.566,
+      "eval_steps_per_second": 6.848,
+      "step": 500
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 7.8125e-07,
+      "loss": 0.06,
+      "step": 510
+    },
+    {
+      "epoch": 4.0,
+      "step": 512,
+      "total_flos": 6.311117323294802e+17,
+      "train_loss": 0.46213533167610876,
+      "train_runtime": 403.5009,
+      "train_samples_per_second": 20.183,
+      "train_steps_per_second": 1.269
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 512,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "total_flos": 6.311117323294802e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7147cb9f0a2c061dbeef39df08546ccde78f25f11b207762c14a3862e9617d9e
+size 4536