cats_vs_dogs

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- generated_from_trainer
+datasets:
+- cats_vs_dogs
+metrics:
+- accuracy
+model-index:
+- name: vit-base-catsVSdogs-demo-v5
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: cats_vs_dogs
+      type: cats_vs_dogs
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.98
+---
+
+<!-- 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-base-catsVSdogs-demo-v5
+
+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 cats_vs_dogs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0523
+- Accuracy: 0.98
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0337        | 2.0   | 100  | 0.0523          | 0.98     |
+| 0.0038        | 4.0   | 200  | 0.0591          | 0.985    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.98,
+    "eval_loss": 0.05225329101085663,
+    "eval_runtime": 175.9654,
+    "eval_samples_per_second": 1.137,
+    "eval_steps_per_second": 0.142,
+    "total_flos": 2.479743667666944e+17,
+    "train_loss": 0.06029550410807133,
+    "train_runtime": 7671.8377,
+    "train_samples_per_second": 0.417,
+    "train_steps_per_second": 0.026
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_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": "cat",
+    "1": "dog"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "cat": "0",
+    "dog": "1"
+  },
+  "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": 0.98,
+    "eval_loss": 0.05225329101085663,
+    "eval_runtime": 175.9654,
+    "eval_samples_per_second": 1.137,
+    "eval_steps_per_second": 0.142
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fdc26c6330a5962da28f0a8a0fbe978eb1b1522e09485599f832257fe48b6da
+size 343223968

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

runs/Dec01_00-23-32_3e969321df64/events.out.tfevents.1701390262.3e969321df64.329.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18e38e0467a82a193a9c2dd97d97fb8fc08d47f42a0e44890239b2ed6b00c85
+size 8327

runs/Dec01_00-23-32_3e969321df64/events.out.tfevents.1701398140.3e969321df64.329.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dcc2d31a9e4ef0a5d4f26b35f681ec32669d72f5115fbc669c0483b656ad7b3
+size 411

runs/Nov30_20-18-04_3e969321df64/events.out.tfevents.1701375911.3e969321df64.329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860d27fb56f61b3fcf5559c0b423e18a1ff0af63f2cec6ea922250ca73f875d1
+size 5307

runs/Nov30_21-13-42_3e969321df64/events.out.tfevents.1701378842.3e969321df64.329.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7758e9e26de4e558b941bc5be5728f654c86134da04ecc06bf6a70c7e131b3d
+size 13307

runs/Nov30_21-13-42_3e969321df64/events.out.tfevents.1701389962.3e969321df64.329.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f78060d617d933b44d1698371a93c015ac2892e1acb961a53f9833a4624a9b
+size 4323

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 2.479743667666944e+17,
+    "train_loss": 0.06029550410807133,
+    "train_runtime": 7671.8377,
+    "train_samples_per_second": 0.417,
+    "train_steps_per_second": 0.026
+}

trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": 0.05225329101085663,
+  "best_model_checkpoint": "./vit-base-catsVSdogs-demo-v5/checkpoint-100",
+  "epoch": 4.0,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019,
+      "loss": 0.4108,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00018,
+      "loss": 0.1022,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00017,
+      "loss": 0.2383,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016,
+      "loss": 0.1444,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0812,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00014,
+      "loss": 0.0268,
+      "step": 60
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.0375,
+      "step": 70
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00012,
+      "loss": 0.0088,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.0227,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0337,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.98,
+      "eval_loss": 0.05225329101085663,
+      "eval_runtime": 164.0992,
+      "eval_samples_per_second": 1.219,
+      "eval_steps_per_second": 0.152,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9e-05,
+      "loss": 0.0065,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8e-05,
+      "loss": 0.0055,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7e-05,
+      "loss": 0.0179,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 6e-05,
+      "loss": 0.016,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5e-05,
+      "loss": 0.0314,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 4e-05,
+      "loss": 0.0067,
+      "step": 160
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 3e-05,
+      "loss": 0.004,
+      "step": 170
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 2e-05,
+      "loss": 0.0041,
+      "step": 180
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1e-05,
+      "loss": 0.0039,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.0038,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.985,
+      "eval_loss": 0.059128113090991974,
+      "eval_runtime": 162.5287,
+      "eval_samples_per_second": 1.231,
+      "eval_steps_per_second": 0.154,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "step": 200,
+      "total_flos": 2.479743667666944e+17,
+      "train_loss": 0.06029550410807133,
+      "train_runtime": 7671.8377,
+      "train_samples_per_second": 0.417,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "total_flos": 2.479743667666944e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0068cdc49051a47482a2c72986ff01979c70ff51c0addb896801168db347bb7d
+size 4600