Training in progress, epoch 0

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: microsoft/swin-tiny-patch4-window7-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: swin-tiny-patch4-window7-224-finetuned-student_six_classes
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7751572327044025
+---
+
+<!-- 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. -->
+
+# swin-tiny-patch4-window7-224-finetuned-student_six_classes
+
+This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4916
+- Accuracy: 0.7752
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.4387        | 0.94  | 11   | 0.9083          | 0.6368   |
+| 0.7445        | 1.96  | 23   | 0.5326          | 0.8553   |
+| 0.4879        | 2.81  | 33   | 0.4916          | 0.7752   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.81,
+    "total_flos": 1.0400908167453082e+17,
+    "train_loss": 0.8560382669622247,
+    "train_runtime": 123.6615,
+    "train_samples_per_second": 36.001,
+    "train_steps_per_second": 0.267
+}

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    6,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 96,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Looking Away",
+    "1": "bored",
+    "2": "confused",
+    "3": "drowsy",
+    "4": "engaged",
+    "5": "frustrated"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Looking Away": 0,
+    "bored": 1,
+    "confused": 2,
+    "drowsy": 3,
+    "engaged": 4,
+    "frustrated": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f29aa4be255c19a5bcb2791d7e70701e7702d0014087ee593787a7c6bcf0f77d
+size 110355136

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Apr15_01-15-18_076be6699dc0/events.out.tfevents.1713143742.076be6699dc0.466.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7901b969ea54268ccca6998dc7ef3978d5f5b82182a00c9fb778edbe806934ae
+size 7152

runs/Apr15_01-18-49_076be6699dc0/events.out.tfevents.1713143937.076be6699dc0.466.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8418e0d1de9edc23dafba5db8e39ace1823a405139ae044ee9fd9d4c3836ddc
+size 7061

runs/Apr15_01-21-15_076be6699dc0/events.out.tfevents.1713144081.076be6699dc0.466.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e34b8baaf0a81915dc81bf6a41bde79c508a04f19ce813d4c850483fa78d35c
+size 7536

runs/Apr15_01-25-06_076be6699dc0/events.out.tfevents.1713144313.076be6699dc0.466.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7101de40e04769bba5d61d2e15d30634671d1a618de52af4a6a8551c0db31902
+size 5757

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.81,
+    "total_flos": 1.0400908167453082e+17,
+    "train_loss": 0.8560382669622247,
+    "train_runtime": 123.6615,
+    "train_samples_per_second": 36.001,
+    "train_steps_per_second": 0.267
+}

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.8553459119496856,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-student_six_classes/checkpoint-23",
+  "epoch": 2.8085106382978724,
+  "eval_steps": 500,
+  "global_step": 33,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.85,
+      "grad_norm": 5.6343159675598145,
+      "learning_rate": 3.965517241379311e-05,
+      "loss": 1.4387,
+      "step": 10
+    },
+    {
+      "epoch": 0.94,
+      "eval_accuracy": 0.6367924528301887,
+      "eval_loss": 0.9083201885223389,
+      "eval_runtime": 8.5969,
+      "eval_samples_per_second": 73.98,
+      "eval_steps_per_second": 2.326,
+      "step": 11
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 9.409465789794922,
+      "learning_rate": 2.2413793103448276e-05,
+      "loss": 0.7445,
+      "step": 20
+    },
+    {
+      "epoch": 1.96,
+      "eval_accuracy": 0.8553459119496856,
+      "eval_loss": 0.532645583152771,
+      "eval_runtime": 10.5737,
+      "eval_samples_per_second": 60.149,
+      "eval_steps_per_second": 1.891,
+      "step": 23
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 7.701065540313721,
+      "learning_rate": 5.172413793103448e-06,
+      "loss": 0.4879,
+      "step": 30
+    },
+    {
+      "epoch": 2.81,
+      "eval_accuracy": 0.7751572327044025,
+      "eval_loss": 0.4916297495365143,
+      "eval_runtime": 7.7495,
+      "eval_samples_per_second": 82.07,
+      "eval_steps_per_second": 2.581,
+      "step": 33
+    },
+    {
+      "epoch": 2.81,
+      "step": 33,
+      "total_flos": 1.0400908167453082e+17,
+      "train_loss": 0.8560382669622247,
+      "train_runtime": 123.6615,
+      "train_samples_per_second": 36.001,
+      "train_steps_per_second": 0.267
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 33,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.0400908167453082e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4cd09b88621b4b40848428a2f1450dad31a4091f716ffb1dc04ede78b3a6dc8
+size 4984