🍻 cheers

README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- generated_from_trainer
+model-index:
+- name: vit-ena24
+  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. -->
+
+# vit-ena24
+
+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:
+- eval_loss: 3.0866
+- eval_model_preparation_time: 0.0047
+- eval_accuracy: 0.0473
+- eval_runtime: 917.1232
+- eval_samples_per_second: 1.428
+- eval_steps_per_second: 0.179
+- step: 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.51.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.04732824427480916,
+    "eval_loss": 3.08662486076355,
+    "eval_model_preparation_time": 0.0047,
+    "eval_runtime": 917.1232,
+    "eval_samples_per_second": 1.428,
+    "eval_steps_per_second": 0.179
+}

config.json

@@ -0,0 +1,73 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "American Black Bear",
+    "1": "American Crow",
+    "10": "Eastern Fox Squirrel",
+    "11": "Eastern Gray Squirrel",
+    "12": "Grey Fox",
+    "13": "Horse",
+    "14": "Northern Raccoon",
+    "15": "Red Fox",
+    "16": "Striped Skunk",
+    "17": "Vehicle",
+    "18": "Virginia Opossum",
+    "19": "White_Tailed_Deer",
+    "2": "Bird",
+    "20": "Wild Turkey",
+    "21": "Woodchuck",
+    "3": "Bobcat",
+    "4": "Chicken",
+    "5": "Coyote",
+    "6": "Dog",
+    "7": "Domestic Cat",
+    "8": "Eastern Chipmunk",
+    "9": "Eastern Cottontail"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "American Black Bear": "0",
+    "American Crow": "1",
+    "Bird": "2",
+    "Bobcat": "3",
+    "Chicken": "4",
+    "Coyote": "5",
+    "Dog": "6",
+    "Domestic Cat": "7",
+    "Eastern Chipmunk": "8",
+    "Eastern Cottontail": "9",
+    "Eastern Fox Squirrel": "10",
+    "Eastern Gray Squirrel": "11",
+    "Grey Fox": "12",
+    "Horse": "13",
+    "Northern Raccoon": "14",
+    "Red Fox": "15",
+    "Striped Skunk": "16",
+    "Vehicle": "17",
+    "Virginia Opossum": "18",
+    "White_Tailed_Deer": "19",
+    "Wild Turkey": "20",
+    "Woodchuck": "21"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.04732824427480916,
+    "eval_loss": 3.08662486076355,
+    "eval_model_preparation_time": 0.0047,
+    "eval_runtime": 917.1232,
+    "eval_samples_per_second": 1.428,
+    "eval_steps_per_second": 0.179
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df275aaaa1509717b68f5cb779f769300ce9faf581adadb7179e8589b46fac4f
+size 343285496

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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/Apr14_17-08-40_f3935f1f5266/events.out.tfevents.1744651561.f3935f1f5266.1199.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d528eabcb3c4e870a8b3c0a599ab606f604e88eab556c5887f87139535e4c1
+size 409

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d78ea8cb4472688a53d74cae5dc602594965a09a43bf10b39982546ef1e0e5
+size 5304