End of training

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: microsoft/swin-tiny-patch4-window7-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: swin-tiny-patch4-window7-224-finetuned-swin-pre_evaluation
+  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. -->
+
+# swin-tiny-patch4-window7-224-finetuned-swin-pre_evaluation
+
+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 None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5048
+- Accuracy: 0.3193
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.5873        | 0.93  | 10   | 1.5200          | 0.2844   |
+| 1.5036        | 1.95  | 21   | 1.5082          | 0.3124   |
+| 1.4965        | 2.79  | 30   | 1.5048          | 0.3193   |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.79,
+    "eval_accuracy": 0.31934731934731936,
+    "eval_loss": 1.5047541856765747,
+    "eval_runtime": 4.54,
+    "eval_samples_per_second": 94.493,
+    "eval_steps_per_second": 3.084,
+    "total_flos": 9.465954043959706e+16,
+    "train_loss": 1.5291136741638183,
+    "train_runtime": 93.8451,
+    "train_samples_per_second": 43.476,
+    "train_steps_per_second": 0.32
+}

config.json

@@ -0,0 +1,67 @@
+{
+  "_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": "0_Soft",
+    "1": "1_Semi_Medium",
+    "2": "2_Medium",
+    "3": "3_Semi_Hard",
+    "4": "4_Hard"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "0_Soft": 0,
+    "1_Semi_Medium": 1,
+    "2_Medium": 2,
+    "3_Semi_Hard": 3,
+    "4_Hard": 4
+  },
+  "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": "4.32.1",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.79,
+    "eval_accuracy": 0.31934731934731936,
+    "eval_loss": 1.5047541856765747,
+    "eval_runtime": 4.54,
+    "eval_samples_per_second": 94.493,
+    "eval_steps_per_second": 3.084
+}

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
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d27209503a04b8d0d31463cd7c916e978c6764b3398a9e23a9d5d4c6988367
+size 110404081

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.79,
+    "total_flos": 9.465954043959706e+16,
+    "train_loss": 1.5291136741638183,
+    "train_runtime": 93.8451,
+    "train_samples_per_second": 43.476,
+    "train_steps_per_second": 0.32
+}

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": 0.31934731934731936,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-swin-pre_evaluation/checkpoint-30",
+  "epoch": 2.7906976744186047,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 1.5873,
+      "step": 10
+    },
+    {
+      "epoch": 0.93,
+      "eval_accuracy": 0.28438228438228436,
+      "eval_loss": 1.5200079679489136,
+      "eval_runtime": 4.9667,
+      "eval_samples_per_second": 86.375,
+      "eval_steps_per_second": 2.819,
+      "step": 10
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 1.5036,
+      "step": 20
+    },
+    {
+      "epoch": 1.95,
+      "eval_accuracy": 0.3123543123543124,
+      "eval_loss": 1.5081508159637451,
+      "eval_runtime": 4.3738,
+      "eval_samples_per_second": 98.084,
+      "eval_steps_per_second": 3.201,
+      "step": 21
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 0.0,
+      "loss": 1.4965,
+      "step": 30
+    },
+    {
+      "epoch": 2.79,
+      "eval_accuracy": 0.31934731934731936,
+      "eval_loss": 1.5047541856765747,
+      "eval_runtime": 4.8256,
+      "eval_samples_per_second": 88.9,
+      "eval_steps_per_second": 2.901,
+      "step": 30
+    },
+    {
+      "epoch": 2.79,
+      "step": 30,
+      "total_flos": 9.465954043959706e+16,
+      "train_loss": 1.5291136741638183,
+      "train_runtime": 93.8451,
+      "train_samples_per_second": 43.476,
+      "train_steps_per_second": 0.32
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 30,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 9.465954043959706e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8855c697739f2aa202ec46f580781c52c2d41aada49671f762ef8acd3976b602
+size 4155