End of training

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: Accomodation_room_classification
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.875
+---
+
+<!-- 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. -->
+
+# Accomodation_room_classification
+
+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: 0.3910
+- Accuracy: 0.875
+
+## 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: 7
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 5    | 0.6710          | 0.8182   |
+| 0.5771        | 2.0   | 10   | 0.5322          | 0.8523   |
+| 0.5771        | 3.0   | 15   | 0.4599          | 0.8580   |
+| 0.3947        | 4.0   | 20   | 0.4182          | 0.8636   |
+| 0.3947        | 5.0   | 25   | 0.3910          | 0.875    |
+| 0.3635        | 6.0   | 30   | 0.3867          | 0.875    |
+| 0.3635        | 7.0   | 35   | 0.3858          | 0.8580   |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.3910140097141266,
+    "eval_runtime": 4.9449,
+    "eval_samples_per_second": 35.592,
+    "eval_steps_per_second": 1.213,
+    "total_flos": 3.412155785301688e+17,
+    "train_loss": 0.42741406985691616,
+    "train_runtime": 323.3094,
+    "train_samples_per_second": 13.619,
+    "train_steps_per_second": 0.108
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_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": "amenities",
+    "1": "bathroom",
+    "2": "bedroom",
+    "3": "exterior",
+    "4": "floor_plan",
+    "5": "kitchen",
+    "6": "living_room",
+    "7": "others"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "amenities": 0,
+    "bathroom": 1,
+    "bedroom": 2,
+    "exterior": 3,
+    "floor_plan": 4,
+    "kitchen": 5,
+    "living_room": 6,
+    "others": 7
+  },
+  "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": "4.40.0"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.3910140097141266,
+    "eval_runtime": 4.9449,
+    "eval_samples_per_second": 35.592,
+    "eval_steps_per_second": 1.213
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7eff9d81dca60dc599bc43c868acf7790dd9c4dd43424cfdbd67c52d541346
+size 343242432

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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/Apr27_12-31-05_37cc8a3686bb/events.out.tfevents.1714221066.37cc8a3686bb.2342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb281e7c5eb782ac3696b6bb3428382281db0f88cc18bf0fbdde5838489c4b3
+size 4976

runs/Apr27_12-33-11_37cc8a3686bb/events.out.tfevents.1714221204.37cc8a3686bb.2342.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090d8e487fff6a8ef0b711386a267c81b4a58593c2eacf08b6acd172a1fe0cd9
+size 7323

runs/Apr27_12-33-11_37cc8a3686bb/events.out.tfevents.1714221455.37cc8a3686bb.2342.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5bcc6815cea79c5cd99e1ac1c43a37591832bb81459d00bc704866004804542
+size 722

runs/Apr27_12-39-16_37cc8a3686bb/events.out.tfevents.1714221573.37cc8a3686bb.2342.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2331d8bee942eb5943218e79d64f1a68b461eeff5c8e69fbf9c334b07bfbf6bd
+size 8241

runs/Apr27_12-39-16_37cc8a3686bb/events.out.tfevents.1714221910.37cc8a3686bb.2342.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19e944b63c3a5dff842bc6421a0af43c154e7a98d92344fa85f86155b56e861
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 3.412155785301688e+17,
+    "train_loss": 0.42741406985691616,
+    "train_runtime": 323.3094,
+    "train_samples_per_second": 13.619,
+    "train_steps_per_second": 0.108
+}

trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": 0.875,
+  "best_model_checkpoint": "Accomodation_room_classification/checkpoint-25",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 35,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8181818181818182,
+      "eval_loss": 0.6709501147270203,
+      "eval_runtime": 4.9691,
+      "eval_samples_per_second": 35.419,
+      "eval_steps_per_second": 1.207,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9039503335952759,
+      "learning_rate": 4.032258064516129e-05,
+      "loss": 0.5771,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8522727272727273,
+      "eval_loss": 0.5321911573410034,
+      "eval_runtime": 5.4706,
+      "eval_samples_per_second": 32.172,
+      "eval_steps_per_second": 1.097,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8579545454545454,
+      "eval_loss": 0.459867924451828,
+      "eval_runtime": 5.2619,
+      "eval_samples_per_second": 33.448,
+      "eval_steps_per_second": 1.14,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.7084476947784424,
+      "learning_rate": 2.4193548387096777e-05,
+      "loss": 0.3947,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8636363636363636,
+      "eval_loss": 0.4181961715221405,
+      "eval_runtime": 5.1139,
+      "eval_samples_per_second": 34.416,
+      "eval_steps_per_second": 1.173,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.3910140097141266,
+      "eval_runtime": 5.509,
+      "eval_samples_per_second": 31.947,
+      "eval_steps_per_second": 1.089,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.146559238433838,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 0.3635,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.3867148458957672,
+      "eval_runtime": 5.0182,
+      "eval_samples_per_second": 35.072,
+      "eval_steps_per_second": 1.196,
+      "step": 30
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8579545454545454,
+      "eval_loss": 0.38580694794654846,
+      "eval_runtime": 5.5963,
+      "eval_samples_per_second": 31.449,
+      "eval_steps_per_second": 1.072,
+      "step": 35
+    },
+    {
+      "epoch": 7.0,
+      "step": 35,
+      "total_flos": 3.412155785301688e+17,
+      "train_loss": 0.42741406985691616,
+      "train_runtime": 323.3094,
+      "train_samples_per_second": 13.619,
+      "train_steps_per_second": 0.108
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 35,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 3.412155785301688e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7deaf974521a2d932fa22fa953ad9729032ba310b2815c726e723c60658187
+size 5048