End of training

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: vit-base-patch16-224-finetuned-cedar
+  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: 0.7882830626450116
+---
+
+<!-- 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-patch16-224-finetuned-cedar
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4667
+- Accuracy: 0.7883
+
+## 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: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.5419        | 1.0   | 54   | 0.5085          | 0.7657   |
+| 0.4541        | 2.0   | 108  | 0.4667          | 0.7883   |
+| 0.3847        | 3.0   | 162  | 0.5603          | 0.7320   |
+| 0.3669        | 4.0   | 216  | 0.4869          | 0.7749   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.7882830626450116,
+    "eval_loss": 0.46672987937927246,
+    "eval_runtime": 28.0348,
+    "eval_samples_per_second": 61.495,
+    "eval_steps_per_second": 1.926,
+    "total_flos": 2.1362991696950723e+18,
+    "train_loss": 0.4688039951854282,
+    "train_runtime": 1140.3926,
+    "train_samples_per_second": 24.174,
+    "train_steps_per_second": 0.189
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "full_forg",
+    "1": "full_org"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "full_forg": 0,
+    "full_org": 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": 0.7882830626450116,
+    "eval_loss": 0.46672987937927246,
+    "eval_runtime": 28.0348,
+    "eval_samples_per_second": 61.495,
+    "eval_steps_per_second": 1.926
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbc2b11eb066b415099616c5eb05f5d680a9d969b9296fdc6fbfcdd70a67174
+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": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Dec29_17-00-52_9d7cae9b6491/events.out.tfevents.1703869272.9d7cae9b6491.1030.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e019b29205d44231aea74a87a73990974420133fcac5e6778be698426a98a719
+size 9181

runs/Dec29_17-00-52_9d7cae9b6491/events.out.tfevents.1703870457.9d7cae9b6491.1030.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a168abb6985a9f2904c7506507f0bfc7941620423a9984963bb9f4ab4ac142a7
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 2.1362991696950723e+18,
+    "train_loss": 0.4688039951854282,
+    "train_runtime": 1140.3926,
+    "train_samples_per_second": 24.174,
+    "train_steps_per_second": 0.189
+}

trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_metric": 0.7882830626450116,
+  "best_model_checkpoint": "vit-base-patch16-224-finetuned-cedar/checkpoint-108",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 216,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 0.7007,
+      "step": 10
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.6193,
+      "step": 20
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.793814432989691e-05,
+      "loss": 0.5897,
+      "step": 30
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.536082474226804e-05,
+      "loss": 0.5124,
+      "step": 40
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.2783505154639175e-05,
+      "loss": 0.5419,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.765661252900232,
+      "eval_loss": 0.5085464119911194,
+      "eval_runtime": 27.8034,
+      "eval_samples_per_second": 62.007,
+      "eval_steps_per_second": 1.942,
+      "step": 54
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.020618556701031e-05,
+      "loss": 0.4913,
+      "step": 60
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.7628865979381445e-05,
+      "loss": 0.4795,
+      "step": 70
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.5051546391752576e-05,
+      "loss": 0.4856,
+      "step": 80
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.2474226804123714e-05,
+      "loss": 0.4715,
+      "step": 90
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.9896907216494846e-05,
+      "loss": 0.4541,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7882830626450116,
+      "eval_loss": 0.46672987937927246,
+      "eval_runtime": 27.8433,
+      "eval_samples_per_second": 61.918,
+      "eval_steps_per_second": 1.939,
+      "step": 108
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 2.7319587628865977e-05,
+      "loss": 0.4464,
+      "step": 110
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.4742268041237116e-05,
+      "loss": 0.4412,
+      "step": 120
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.2164948453608247e-05,
+      "loss": 0.4327,
+      "step": 130
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.9587628865979382e-05,
+      "loss": 0.4301,
+      "step": 140
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.7010309278350517e-05,
+      "loss": 0.4184,
+      "step": 150
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.4432989690721649e-05,
+      "loss": 0.3847,
+      "step": 160
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7320185614849188,
+      "eval_loss": 0.5602948069572449,
+      "eval_runtime": 27.4724,
+      "eval_samples_per_second": 62.754,
+      "eval_steps_per_second": 1.966,
+      "step": 162
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 1.1855670103092783e-05,
+      "loss": 0.4003,
+      "step": 170
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 9.278350515463918e-06,
+      "loss": 0.4209,
+      "step": 180
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 6.701030927835052e-06,
+      "loss": 0.405,
+      "step": 190
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 4.123711340206186e-06,
+      "loss": 0.4026,
+      "step": 200
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.5463917525773197e-06,
+      "loss": 0.3669,
+      "step": 210
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7749419953596288,
+      "eval_loss": 0.4869101941585541,
+      "eval_runtime": 27.2972,
+      "eval_samples_per_second": 63.157,
+      "eval_steps_per_second": 1.978,
+      "step": 216
+    },
+    {
+      "epoch": 4.0,
+      "step": 216,
+      "total_flos": 2.1362991696950723e+18,
+      "train_loss": 0.4688039951854282,
+      "train_runtime": 1140.3926,
+      "train_samples_per_second": 24.174,
+      "train_steps_per_second": 0.189
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 216,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 2.1362991696950723e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854519fb4c4284fa2c3d12a55bd101f08476a8fbb772abe88e4ac5d80f05e9db
+size 4600