🍻 cheers

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: vit-base-id-card
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: beans
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 1.0
+---
+
+<!-- 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-id-card
+
+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 beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0611
+- Accuracy: 1.0
+
+## 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.0610995814204216,
+    "eval_runtime": 1.8578,
+    "eval_samples_per_second": 14.533,
+    "eval_steps_per_second": 2.153,
+    "total_flos": 3.502669323615437e+16,
+    "train_loss": 0.25591564178466797,
+    "train_runtime": 40.8688,
+    "train_samples_per_second": 11.06,
+    "train_steps_per_second": 0.783
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_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": "form",
+    "1": "id_card_back",
+    "2": "id_card_front"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "form": "0",
+    "id_card_back": "1",
+    "id_card_front": "2"
+  },
+  "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": "4.38.2"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.0610995814204216,
+    "eval_runtime": 1.8578,
+    "eval_samples_per_second": 14.533,
+    "eval_steps_per_second": 2.153
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fddba4b9b119ad3ef2426885782d2b79033eb714640f3d62da164f57c27206
+size 343227052

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/Mar21_06-15-23_67fe17cc1743/events.out.tfevents.1711001733.67fe17cc1743.1153.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856414c6635da0875727bb8260519dca3bf213402ca0c0ab03cc9336bb8f1e1a
+size 5274

runs/Mar21_06-15-23_67fe17cc1743/events.out.tfevents.1711001845.67fe17cc1743.1153.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c28cb057839b237cb573a070efbc6fd81318f3333911f3b044e297db9247802d
+size 405

runs/Mar21_06-33-51_67fe17cc1743/events.out.tfevents.1711002832.67fe17cc1743.1153.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad2c6d34701c5f30d308a4fe2cd646fa2f13f5945c05839a76ef16bbfe7e5d4
+size 5588

runs/Mar21_06-33-51_67fe17cc1743/events.out.tfevents.1711002876.67fe17cc1743.1153.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f70f5bc8c65b9e398c551fc0c2b744ef4ed993592a9a9de0b02e344ead997ed
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.502669323615437e+16,
+    "train_loss": 0.25591564178466797,
+    "train_runtime": 40.8688,
+    "train_samples_per_second": 11.06,
+    "train_steps_per_second": 0.783
+}

trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 100,
+  "global_step": 32,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.040573000907898,
+      "learning_rate": 0.00014375,
+      "loss": 0.6083,
+      "step": 10
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.4061480462551117,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 0.1341,
+      "step": 20
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.30543988943099976,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.0648,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "step": 32,
+      "total_flos": 3.502669323615437e+16,
+      "train_loss": 0.25591564178466797,
+      "train_runtime": 40.8688,
+      "train_samples_per_second": 11.06,
+      "train_steps_per_second": 0.783
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 32,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "total_flos": 3.502669323615437e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef34432b313669942c77076b60d487bda6024f60f7696c7295a2118b4ca0d8b5
+size 4856