End of training

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: microsoft/swinv2-base-patch4-window8-256
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: swinv2-base-patch4-window8-256-isic217
+  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. -->
+
+# swinv2-base-patch4-window8-256-isic217
+
+This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1588
+- Accuracy: 0.65
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.1681        | 0.9888 | 22   | 2.0018          | 0.25     |
+| 1.9254        | 1.9775 | 44   | 1.7653          | 0.35     |
+| 1.6706        | 2.9663 | 66   | 1.6649          | 0.6      |
+| 1.2834        | 4.0    | 89   | 1.5579          | 0.5      |
+| 1.2039        | 4.9888 | 111  | 1.4087          | 0.55     |
+| 0.9395        | 5.9775 | 133  | 1.3115          | 0.5      |
+| 0.7532        | 6.9663 | 155  | 1.3599          | 0.6      |
+| 0.6573        | 8.0    | 178  | 1.1588          | 0.65     |
+| 0.6663        | 8.9888 | 200  | 1.2074          | 0.6      |
+| 0.4686        | 9.8876 | 220  | 1.2285          | 0.6      |
+
+
+### Framework versions
+
+- Transformers 4.42.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 9.887640449438202,
+    "eval_accuracy": 0.65,
+    "eval_loss": 1.158837914466858,
+    "eval_runtime": 3.034,
+    "eval_samples_per_second": 6.592,
+    "eval_steps_per_second": 3.296,
+    "total_flos": 1.8042639737683968e+17,
+    "train_loss": 1.1781822247938676,
+    "train_runtime": 376.1356,
+    "train_samples_per_second": 4.732,
+    "train_steps_per_second": 0.585
+}

config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "microsoft/swinv2-base-patch4-window8-256",
+  "architectures": [
+    "Swinv2ForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "dots",
+    "1": "globules-clods",
+    "2": "lines",
+    "3": "network",
+    "4": "pattern",
+    "5": "regression structures",
+    "6": "shiny white structures",
+    "7": "structureless",
+    "8": "vessels"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "dots": 0,
+    "globules-clods": 1,
+    "lines": 2,
+    "network": 3,
+    "pattern": 4,
+    "regression structures": 5,
+    "shiny white structures": 6,
+    "structureless": 7,
+    "vessels": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swinv2",
+  "num_channels": 3,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "pretrained_window_sizes": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_absolute_embeddings": false,
+  "window_size": 8
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.887640449438202,
+    "eval_accuracy": 0.65,
+    "eval_loss": 1.158837914466858,
+    "eval_runtime": 3.034,
+    "eval_samples_per_second": 6.592,
+    "eval_steps_per_second": 3.296
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adf0d8d16113b190dfe9742394d7cf923e690849dbaf77e9d7ce19dd028fd66
+size 347674196

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": [
+    0.485,
+    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/Jun03_14-52-50_ip-10-110-161-167.ap-southeast-2.compute.internal/events.out.tfevents.1717426372.ip-10-110-161-167.ap-southeast-2.compute.internal.5893.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2470602f052ed1b3f7e1df68fdcf619e573ab2b831afb4aa7fe49d01b52d95
+size 11350

runs/Jun03_14-52-50_ip-10-110-161-167.ap-southeast-2.compute.internal/events.out.tfevents.1717426752.ip-10-110-161-167.ap-southeast-2.compute.internal.5893.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6707fee8e2fa3b024dd891ac0aed3ed8fa51f0a7df573674c943bfc704dcf1
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.887640449438202,
+    "total_flos": 1.8042639737683968e+17,
+    "train_loss": 1.1781822247938676,
+    "train_runtime": 376.1356,
+    "train_samples_per_second": 4.732,
+    "train_steps_per_second": 0.585
+}

trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_metric": 0.65,
+  "best_model_checkpoint": "swinv2-base-patch4-window8-256-isic217/checkpoint-178",
+  "epoch": 9.887640449438202,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9887640449438202,
+      "grad_norm": 12.935554504394531,
+      "learning_rate": 5e-05,
+      "loss": 2.1681,
+      "step": 22
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "eval_accuracy": 0.25,
+      "eval_loss": 2.0018374919891357,
+      "eval_runtime": 2.9002,
+      "eval_samples_per_second": 6.896,
+      "eval_steps_per_second": 3.448,
+      "step": 22
+    },
+    {
+      "epoch": 1.9775280898876404,
+      "grad_norm": 12.57723331451416,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.9254,
+      "step": 44
+    },
+    {
+      "epoch": 1.9775280898876404,
+      "eval_accuracy": 0.35,
+      "eval_loss": 1.765319585800171,
+      "eval_runtime": 2.8633,
+      "eval_samples_per_second": 6.985,
+      "eval_steps_per_second": 3.493,
+      "step": 44
+    },
+    {
+      "epoch": 2.966292134831461,
+      "grad_norm": 18.157392501831055,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 1.6706,
+      "step": 66
+    },
+    {
+      "epoch": 2.966292134831461,
+      "eval_accuracy": 0.6,
+      "eval_loss": 1.664868712425232,
+      "eval_runtime": 2.8974,
+      "eval_samples_per_second": 6.903,
+      "eval_steps_per_second": 3.451,
+      "step": 66
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 22.54041290283203,
+      "learning_rate": 3.308080808080809e-05,
+      "loss": 1.2834,
+      "step": 89
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.557893991470337,
+      "eval_runtime": 2.9133,
+      "eval_samples_per_second": 6.865,
+      "eval_steps_per_second": 3.432,
+      "step": 89
+    },
+    {
+      "epoch": 4.98876404494382,
+      "grad_norm": 24.279077529907227,
+      "learning_rate": 2.7525252525252528e-05,
+      "loss": 1.2039,
+      "step": 111
+    },
+    {
+      "epoch": 4.98876404494382,
+      "eval_accuracy": 0.55,
+      "eval_loss": 1.4086878299713135,
+      "eval_runtime": 2.9062,
+      "eval_samples_per_second": 6.882,
+      "eval_steps_per_second": 3.441,
+      "step": 111
+    },
+    {
+      "epoch": 5.97752808988764,
+      "grad_norm": 26.200206756591797,
+      "learning_rate": 2.1969696969696972e-05,
+      "loss": 0.9395,
+      "step": 133
+    },
+    {
+      "epoch": 5.97752808988764,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.3115328550338745,
+      "eval_runtime": 2.9002,
+      "eval_samples_per_second": 6.896,
+      "eval_steps_per_second": 3.448,
+      "step": 133
+    },
+    {
+      "epoch": 6.966292134831461,
+      "grad_norm": 24.642183303833008,
+      "learning_rate": 1.6414141414141416e-05,
+      "loss": 0.7532,
+      "step": 155
+    },
+    {
+      "epoch": 6.966292134831461,
+      "eval_accuracy": 0.6,
+      "eval_loss": 1.3599040508270264,
+      "eval_runtime": 2.9052,
+      "eval_samples_per_second": 6.884,
+      "eval_steps_per_second": 3.442,
+      "step": 155
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 20.47603416442871,
+      "learning_rate": 1.0606060606060607e-05,
+      "loss": 0.6573,
+      "step": 178
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.65,
+      "eval_loss": 1.158837914466858,
+      "eval_runtime": 2.8838,
+      "eval_samples_per_second": 6.935,
+      "eval_steps_per_second": 3.468,
+      "step": 178
+    },
+    {
+      "epoch": 8.98876404494382,
+      "grad_norm": 29.59978485107422,
+      "learning_rate": 5.050505050505051e-06,
+      "loss": 0.6663,
+      "step": 200
+    },
+    {
+      "epoch": 8.98876404494382,
+      "eval_accuracy": 0.6,
+      "eval_loss": 1.207406759262085,
+      "eval_runtime": 2.8796,
+      "eval_samples_per_second": 6.945,
+      "eval_steps_per_second": 3.473,
+      "step": 200
+    },
+    {
+      "epoch": 9.887640449438202,
+      "grad_norm": 12.570259094238281,
+      "learning_rate": 0.0,
+      "loss": 0.4686,
+      "step": 220
+    },
+    {
+      "epoch": 9.887640449438202,
+      "eval_accuracy": 0.6,
+      "eval_loss": 1.228463888168335,
+      "eval_runtime": 2.9115,
+      "eval_samples_per_second": 6.869,
+      "eval_steps_per_second": 3.435,
+      "step": 220
+    },
+    {
+      "epoch": 9.887640449438202,
+      "step": 220,
+      "total_flos": 1.8042639737683968e+17,
+      "train_loss": 1.1781822247938676,
+      "train_runtime": 376.1356,
+      "train_samples_per_second": 4.732,
+      "train_steps_per_second": 0.585
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8042639737683968e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddfabc3f7d512045d6f1323f6ea3e68e3707a8ef28ec3752046496e5ba3eb42a
+size 5176