End of training

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+base_model: microsoft/swinv2-tiny-patch4-window8-256
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: swinv2-tiny-patch4-window8-256-finetuned-gardner-exp-max
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7953020134228188
+---
+
+<!-- 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. -->
+
+# swinv2-tiny-patch4-window8-256-finetuned-gardner-exp-max
+
+This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5942
+- Accuracy: 0.7953
+
+## 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.6004        | 0.97  | 14   | 1.4012          | 0.5463   |
+| 1.4099        | 2.0   | 29   | 1.0249          | 0.5463   |
+| 1.1043        | 2.97  | 43   | 0.9695          | 0.6732   |
+| 1.0028        | 4.0   | 58   | 0.8659          | 0.6585   |
+| 0.8915        | 4.97  | 72   | 0.7728          | 0.7317   |
+| 0.8824        | 6.0   | 87   | 0.7238          | 0.7220   |
+| 0.8286        | 6.97  | 101  | 0.7220          | 0.7220   |
+| 0.8274        | 8.0   | 116  | 0.7376          | 0.6976   |
+| 0.7765        | 8.97  | 130  | 0.7117          | 0.7366   |
+| 0.7633        | 9.66  | 140  | 0.7079          | 0.7366   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2
+- Datasets 2.16.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 9.66,
+    "eval_accuracy": 0.7953020134228188,
+    "eval_loss": 0.5942178964614868,
+    "eval_runtime": 12.097,
+    "eval_samples_per_second": 24.634,
+    "eval_steps_per_second": 0.827,
+    "train_loss": 0.9881165368216378,
+    "train_runtime": 1025.6442,
+    "train_samples_per_second": 17.93,
+    "train_steps_per_second": 0.136
+}

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
+  "architectures": [
+    "Swinv2ForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    6,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 96,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3",
+    "4": "4"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swinv2",
+  "num_channels": 3,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "patch_size": 4,
+  "path_norm": true,
+  "pretrained_window_sizes": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_absolute_embeddings": false,
+  "window_size": 8
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.66,
+    "eval_accuracy": 0.7953020134228188,
+    "eval_loss": 0.5942178964614868,
+    "eval_runtime": 12.097,
+    "eval_samples_per_second": 24.634,
+    "eval_steps_per_second": 0.827
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84f52166f9698bfa19378546856697dc85b2c450c8f3451dc214fc69bf72d4b
+size 110359372

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 256,
+    "width": 256
+  }
+}

runs/Dec26_19-25-49_MacBook-Pro-de-Max-2.local/events.out.tfevents.1703615160.MacBook-Pro-de-Max-2.local.25840.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea35f690e9d8a65739b2ec2f06d9d1898ca906532c44cd3083b720314f301ff6
+size 10529

runs/Dec26_19-25-49_MacBook-Pro-de-Max-2.local/events.out.tfevents.1703616189.MacBook-Pro-de-Max-2.local.25840.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5220613e8db8f4fa85f3dec90d22c7e6c66e3aa4f59f117f0fa797c8ab321a97
+size 734

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 9.66,
+    "train_loss": 0.9881165368216378,
+    "train_runtime": 1025.6442,
+    "train_samples_per_second": 17.93,
+    "train_steps_per_second": 0.136
+}

trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": 0.7365853658536585,
+  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-gardner-exp-max/checkpoint-130",
+  "epoch": 9.655172413793103,
+  "eval_steps": 500,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.6004,
+      "step": 10
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.5463414634146342,
+      "eval_loss": 1.401221752166748,
+      "eval_runtime": 10.6657,
+      "eval_samples_per_second": 19.22,
+      "eval_steps_per_second": 0.656,
+      "step": 14
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.4099,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5463414634146342,
+      "eval_loss": 1.024906039237976,
+      "eval_runtime": 3.9358,
+      "eval_samples_per_second": 52.086,
+      "eval_steps_per_second": 1.779,
+      "step": 29
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 1.1287,
+      "step": 30
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 1.1043,
+      "step": 40
+    },
+    {
+      "epoch": 2.97,
+      "eval_accuracy": 0.6731707317073171,
+      "eval_loss": 0.9695160388946533,
+      "eval_runtime": 4.1803,
+      "eval_samples_per_second": 49.039,
+      "eval_steps_per_second": 1.675,
+      "step": 43
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.0028,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6585365853658537,
+      "eval_loss": 0.8658934235572815,
+      "eval_runtime": 4.0107,
+      "eval_samples_per_second": 51.114,
+      "eval_steps_per_second": 1.745,
+      "step": 58
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 0.9609,
+      "step": 60
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.8915,
+      "step": 70
+    },
+    {
+      "epoch": 4.97,
+      "eval_accuracy": 0.7317073170731707,
+      "eval_loss": 0.7727790474891663,
+      "eval_runtime": 4.0395,
+      "eval_samples_per_second": 50.748,
+      "eval_steps_per_second": 1.733,
+      "step": 72
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.8824,
+      "step": 80
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7219512195121951,
+      "eval_loss": 0.7237768173217773,
+      "eval_runtime": 3.9086,
+      "eval_samples_per_second": 52.449,
+      "eval_steps_per_second": 1.791,
+      "step": 87
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 0.8629,
+      "step": 90
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 0.8286,
+      "step": 100
+    },
+    {
+      "epoch": 6.97,
+      "eval_accuracy": 0.7219512195121951,
+      "eval_loss": 0.7219818830490112,
+      "eval_runtime": 3.9131,
+      "eval_samples_per_second": 52.389,
+      "eval_steps_per_second": 1.789,
+      "step": 101
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.8274,
+      "step": 110
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.697560975609756,
+      "eval_loss": 0.7375687956809998,
+      "eval_runtime": 3.8911,
+      "eval_samples_per_second": 52.685,
+      "eval_steps_per_second": 1.799,
+      "step": 116
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 0.794,
+      "step": 120
+    },
+    {
+      "epoch": 8.97,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 0.7765,
+      "step": 130
+    },
+    {
+      "epoch": 8.97,
+      "eval_accuracy": 0.7365853658536585,
+      "eval_loss": 0.7116620540618896,
+      "eval_runtime": 3.9546,
+      "eval_samples_per_second": 51.839,
+      "eval_steps_per_second": 1.77,
+      "step": 130
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 0.0,
+      "loss": 0.7633,
+      "step": 140
+    },
+    {
+      "epoch": 9.66,
+      "eval_accuracy": 0.7365853658536585,
+      "eval_loss": 0.7078527212142944,
+      "eval_runtime": 4.1225,
+      "eval_samples_per_second": 49.727,
+      "eval_steps_per_second": 1.698,
+      "step": 140
+    },
+    {
+      "epoch": 9.66,
+      "step": 140,
+      "total_flos": 5.78085766574506e+17,
+      "train_loss": 0.9881165368216378,
+      "train_runtime": 1025.6442,
+      "train_samples_per_second": 17.93,
+      "train_steps_per_second": 0.136
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5.78085766574506e+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 sha256:78c8073d0ca296061eeb2c1f9efe2310da5f052d3bfc061bd3372b205f4693f1
+size 4792