End of training

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-base-patch16_fold1
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: test
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6692913385826772
+---
+
+<!-- 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. -->
+
+# Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-base-patch16_fold1
+
+This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6421
+- Accuracy: 0.6693
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.0907        | 1.0   | 924  | 1.0851          | 0.6296   |
+| 0.945         | 2.0   | 1848 | 1.0698          | 0.6340   |
+| 0.7725        | 3.0   | 2772 | 0.9959          | 0.6687   |
+| 0.4807        | 4.0   | 3696 | 1.0700          | 0.6677   |
+| 0.5152        | 5.0   | 4620 | 1.1856          | 0.6579   |
+| 0.264         | 6.0   | 5544 | 1.2952          | 0.6647   |
+| 0.1403        | 7.0   | 6468 | 1.4304          | 0.6655   |
+| 0.1127        | 8.0   | 7392 | 1.5557          | 0.6679   |
+| 0.1072        | 9.0   | 8316 | 1.6120          | 0.6685   |
+| 0.1138        | 10.0  | 9240 | 1.6421          | 0.6693   |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,88 @@
+{
+  "_name_or_path": "microsoft/beit-base-patch16-224-pt22k-ft22k",
+  "architectures": [
+    "BeitForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auxiliary_channels": 256,
+  "auxiliary_concat_input": false,
+  "auxiliary_loss_weight": 0.4,
+  "auxiliary_num_convs": 1,
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "AmorfHead",
+    "1": "AsymmetricNeck",
+    "10": "RoundHead",
+    "11": "ShortTail",
+    "12": "TaperedHead",
+    "13": "ThickNeck",
+    "14": "ThinNeck",
+    "15": "TwistedNeck",
+    "16": "TwistedTail",
+    "17": "VacuolatedHead",
+    "2": "CurlyTail",
+    "3": "DoubleHead",
+    "4": "DoubleTail",
+    "5": "LongTail",
+    "6": "NarrowAcrosome",
+    "7": "Normal",
+    "8": "PinHead",
+    "9": "PyriformHead"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AmorfHead": "0",
+    "AsymmetricNeck": "1",
+    "CurlyTail": "2",
+    "DoubleHead": "3",
+    "DoubleTail": "4",
+    "LongTail": "5",
+    "NarrowAcrosome": "6",
+    "Normal": "7",
+    "PinHead": "8",
+    "PyriformHead": "9",
+    "RoundHead": "10",
+    "ShortTail": "11",
+    "TaperedHead": "12",
+    "ThickNeck": "13",
+    "ThinNeck": "14",
+    "TwistedNeck": "15",
+    "TwistedTail": "16",
+    "VacuolatedHead": "17"
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "out_indices": [
+    3,
+    5,
+    7,
+    11
+  ],
+  "patch_size": 16,
+  "pool_scales": [
+    1,
+    2,
+    3,
+    6
+  ],
+  "problem_type": "single_label_classification",
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_absolute_position_embeddings": false,
+  "use_auxiliary_head": true,
+  "use_mask_token": false,
+  "use_mean_pooling": true,
+  "use_relative_position_bias": true,
+  "use_shared_relative_position_bias": false,
+  "vocab_size": 8192
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c64cca68c8fe48ab7bf203aad1a2e384786b8da9cb34a6a52c7417cdad88aa
+size 343129544

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "BeitImageProcessor",
+  "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 sha256:8a22b617296dee1b6eb4886e7a0a0e1984d2f915d0ddd6fcbb7c46b40489c5d6
+size 4704