End of training

README.md

@@ -0,0 +1,79 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: etsy-room-classifier
+  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. -->
+
+# etsy-room-classifier
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0884
+- Accuracy: 0.75
+
+## 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: 2025
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- 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
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.7984        | 1.0   | 12   | 1.7703          | 0.2      |
+| 1.7678        | 2.0   | 24   | 1.7096          | 0.45     |
+| 1.6943        | 3.0   | 36   | 1.6088          | 0.525    |
+| 1.6284        | 4.0   | 48   | 1.5027          | 0.575    |
+| 1.4732        | 5.0   | 60   | 1.4243          | 0.55     |
+| 1.4102        | 6.0   | 72   | 1.3879          | 0.55     |
+| 1.3583        | 7.0   | 84   | 1.3096          | 0.625    |
+| 1.2844        | 8.0   | 96   | 1.2460          | 0.675    |
+| 1.2383        | 9.0   | 108  | 1.1915          | 0.7      |
+| 1.1613        | 10.0  | 120  | 1.1863          | 0.65     |
+| 1.1508        | 11.0  | 132  | 1.1619          | 0.775    |
+| 1.0836        | 12.0  | 144  | 1.1397          | 0.8      |
+| 1.115         | 13.0  | 156  | 1.1122          | 0.75     |
+| 1.0829        | 14.0  | 168  | 1.0820          | 0.8      |
+| 1.0483        | 15.0  | 180  | 1.0884          | 0.75     |
+
+
+### Framework versions
+
+- Transformers 4.54.1
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "bathroom",
+    "1": "bedroom",
+    "2": "hallway",
+    "3": "kitchen",
+    "4": "other",
+    "5": "toilet"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bathroom": "0",
+    "bedroom": "1",
+    "hallway": "2",
+    "kitchen": "3",
+    "other": "4",
+    "toilet": "5"
+  },
+  "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": "4.54.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba395b79bb410c637491727cabc8eb819f21df4d1356eebd5d05cca7a85b4c3f
+size 343236280

preprocessor_config.json

@@ -0,0 +1,31 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Jul31_13-59-33_0508-124547-7g8b340j-172-16-88-57/events.out.tfevents.1753970383.0508-124547-7g8b340j-172-16-88-57.3407.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d797f2b6170f7c9e53fd0610d45d1ae6287b0c9f2e4191e9c9c5888ab32fbe
+size 11216

runs/Jul31_14-02-38_0508-124547-7g8b340j-172-16-88-57/events.out.tfevents.1753970561.0508-124547-7g8b340j-172-16-88-57.3407.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bb491b7c5baa4055e8ddc5141751540474e30d6c027c2201b7ecbcad507076
+size 11216

runs/Jul31_14-05-48_0508-124547-7g8b340j-172-16-88-57/events.out.tfevents.1753970749.0508-124547-7g8b340j-172-16-88-57.3407.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b46bbb9d85b24d2244133916ad7d5b32ec28f9bac1b1f1c62ab894584221241
+size 11285

runs/Jul31_14-08-56_0508-124547-7g8b340j-172-16-88-57/events.out.tfevents.1753970937.0508-124547-7g8b340j-172-16-88-57.3407.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e46593f0bfd0d8956f30e1bac6f2475031f99a4cb89ee8699b38204ce2944c
+size 9889

runs/Jul31_14-11-40_0508-124547-7g8b340j-172-16-88-57/events.out.tfevents.1753971101.0508-124547-7g8b340j-172-16-88-57.3407.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152e690e8fde94de3f59043def83983e59a826095352fb46e76d6c2e3f64c5c6
+size 14111

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86c71806b3b8572fc69cda1304b8914092e666407dc2b626a831741e69ca134
+size 5432