End of training

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: finetuned-blurr-nonblur
+  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. -->
+
+# finetuned-blurr-nonblur
+
+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: 0.2435
+- Accuracy: 0.9241
+
+## 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: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6486        | 1.0   | 14   | 0.6255          | 0.6646   |
+| 0.552         | 2.0   | 28   | 0.5737          | 0.6772   |
+| 0.4207        | 3.0   | 42   | 0.5175          | 0.7975   |
+| 0.3545        | 4.0   | 56   | 0.4484          | 0.8861   |
+| 0.2082        | 5.0   | 70   | 0.3621          | 0.8861   |
+| 0.167         | 6.0   | 84   | 0.2930          | 0.9051   |
+| 0.176         | 7.0   | 98   | 0.3003          | 0.8861   |
+| 0.1275        | 8.0   | 112  | 0.2435          | 0.9241   |
+| 0.11          | 9.0   | 126  | 0.2581          | 0.9051   |
+| 0.1009        | 10.0  | 140  | 0.2474          | 0.9114   |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9240506329113924,
+    "eval_loss": 0.2435225546360016,
+    "eval_runtime": 8.0346,
+    "eval_samples_per_second": 19.665,
+    "eval_steps_per_second": 0.373,
+    "total_flos": 6.912285473621606e+17,
+    "train_loss": 0.2789982352937971,
+    "train_runtime": 718.4172,
+    "train_samples_per_second": 12.416,
+    "train_steps_per_second": 0.195
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_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": "Blurr",
+    "1": "Non Blurr"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Blurr": 0,
+    "Non Blurr": 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": "4.38.1"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9240506329113924,
+    "eval_loss": 0.2435225546360016,
+    "eval_runtime": 8.0346,
+    "eval_samples_per_second": 19.665,
+    "eval_steps_per_second": 0.373
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c24745fe885a08f73d3732c9c092f1c76788526ba582e2b5084569defff55cae
+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": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/May31_11-09-09_6c18d3c55927/events.out.tfevents.1717153750.6c18d3c55927.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ede4dda5b342f99aac9c3e675bc1f708a33d83e0f344b7b3f84c5035691c29f
+size 11025

runs/May31_11-09-09_6c18d3c55927/events.out.tfevents.1717154483.6c18d3c55927.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c89d9acd1fffb51efe3bc4cf5d88da7e6e1930b71d9c4227eb99938ac7a9466
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 6.912285473621606e+17,
+    "train_loss": 0.2789982352937971,
+    "train_runtime": 718.4172,
+    "train_samples_per_second": 12.416,
+    "train_steps_per_second": 0.195
+}

trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.2435225546360016,
+  "best_model_checkpoint": "finetuned-blurr-nonblur/checkpoint-112",
+  "epoch": 10.0,
+  "eval_steps": 100,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.71,
+      "grad_norm": 54505.6171875,
+      "learning_rate": 1.8571428571428575e-05,
+      "loss": 0.6486,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6645569620253164,
+      "eval_loss": 0.625545084476471,
+      "eval_runtime": 7.9446,
+      "eval_samples_per_second": 19.888,
+      "eval_steps_per_second": 0.378,
+      "step": 14
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 57206.48828125,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.552,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6772151898734177,
+      "eval_loss": 0.5736974477767944,
+      "eval_runtime": 7.72,
+      "eval_samples_per_second": 20.466,
+      "eval_steps_per_second": 0.389,
+      "step": 28
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 53612.984375,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 0.5206,
+      "step": 30
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 51806.32421875,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.4207,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7974683544303798,
+      "eval_loss": 0.5174736380577087,
+      "eval_runtime": 7.726,
+      "eval_samples_per_second": 20.45,
+      "eval_steps_per_second": 0.388,
+      "step": 42
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 56256.515625,
+      "learning_rate": 1.2857142857142859e-05,
+      "loss": 0.3545,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8860759493670886,
+      "eval_loss": 0.44835516810417175,
+      "eval_runtime": 7.7183,
+      "eval_samples_per_second": 20.471,
+      "eval_steps_per_second": 0.389,
+      "step": 56
+    },
+    {
+      "epoch": 4.29,
+      "grad_norm": 70625.890625,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.286,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 57182.4140625,
+      "learning_rate": 1e-05,
+      "loss": 0.2082,
+      "step": 70
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8860759493670886,
+      "eval_loss": 0.3621000051498413,
+      "eval_runtime": 7.8704,
+      "eval_samples_per_second": 20.075,
+      "eval_steps_per_second": 0.381,
+      "step": 70
+    },
+    {
+      "epoch": 5.71,
+      "grad_norm": 41587.15625,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.167,
+      "step": 80
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9050632911392406,
+      "eval_loss": 0.2930063307285309,
+      "eval_runtime": 7.906,
+      "eval_samples_per_second": 19.985,
+      "eval_steps_per_second": 0.379,
+      "step": 84
+    },
+    {
+      "epoch": 6.43,
+      "grad_norm": 89662.453125,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.176,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8860759493670886,
+      "eval_loss": 0.3003353178501129,
+      "eval_runtime": 7.7836,
+      "eval_samples_per_second": 20.299,
+      "eval_steps_per_second": 0.385,
+      "step": 98
+    },
+    {
+      "epoch": 7.14,
+      "grad_norm": 105894.6796875,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.1271,
+      "step": 100
+    },
+    {
+      "epoch": 7.86,
+      "grad_norm": 73103.46875,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.1275,
+      "step": 110
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9240506329113924,
+      "eval_loss": 0.2435225546360016,
+      "eval_runtime": 7.7728,
+      "eval_samples_per_second": 20.327,
+      "eval_steps_per_second": 0.386,
+      "step": 112
+    },
+    {
+      "epoch": 8.57,
+      "grad_norm": 65041.953125,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.11,
+      "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9050632911392406,
+      "eval_loss": 0.25813814997673035,
+      "eval_runtime": 7.8334,
+      "eval_samples_per_second": 20.17,
+      "eval_steps_per_second": 0.383,
+      "step": 126
+    },
+    {
+      "epoch": 9.29,
+      "grad_norm": 42873.71484375,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.107,
+      "step": 130
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 64285.99609375,
+      "learning_rate": 0.0,
+      "loss": 0.1009,
+      "step": 140
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9113924050632911,
+      "eval_loss": 0.24741442501544952,
+      "eval_runtime": 7.9653,
+      "eval_samples_per_second": 19.836,
+      "eval_steps_per_second": 0.377,
+      "step": 140
+    },
+    {
+      "epoch": 10.0,
+      "step": 140,
+      "total_flos": 6.912285473621606e+17,
+      "train_loss": 0.2789982352937971,
+      "train_runtime": 718.4172,
+      "train_samples_per_second": 12.416,
+      "train_steps_per_second": 0.195
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 6.912285473621606e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48fb5f8242b3a0aedc2a8f87542b09847512f1fd792dc2f4c02d7b52e0826c7
+size 4920