Training in progress, step 420

README.md

@@ -1,90 +1,90 @@
----
-library_name: transformers
-license: apache-2.0
-base_model: google/vit-base-patch16-224-in21k
-tags:
-- generated_from_trainer
-datasets:
-- imagefolder
-metrics:
-- accuracy
-- f1
-model-index:
-- name: got-model
-  results:
-  - task:
-      name: Image Classification
-      type: image-classification
-    dataset:
-      name: imagefolder
-      type: imagefolder
-      config: default
-      split: test
-      args: default
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.9428571428571428
-    - name: F1
-      type: f1
-      value: 0.9442260195944405
----
-
-<!-- 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. -->
-
-# got-model
-
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.1971
-- Accuracy: 0.9429
-- F1: 0.9442
-
-## 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: 16
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 10
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.073         | 1.0   | 42   | 0.2416          | 0.9238   | 0.9250 |
-| 0.061         | 2.0   | 84   | 0.2160          | 0.9333   | 0.9345 |
-| 0.0543        | 3.0   | 126  | 0.2114          | 0.9429   | 0.9432 |
-| 0.0497        | 4.0   | 168  | 0.2028          | 0.9429   | 0.9442 |
-| 0.046         | 5.0   | 210  | 0.1985          | 0.9429   | 0.9442 |
-| 0.0435        | 6.0   | 252  | 0.2009          | 0.9429   | 0.9442 |
-| 0.0414        | 7.0   | 294  | 0.1976          | 0.9429   | 0.9442 |
-| 0.0402        | 8.0   | 336  | 0.1978          | 0.9429   | 0.9442 |
-| 0.0391        | 9.0   | 378  | 0.1967          | 0.9429   | 0.9442 |
-| 0.0385        | 10.0  | 420  | 0.1971          | 0.9429   | 0.9442 |
-
-
-### Framework versions
-
-- Transformers 4.45.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
-- Tokenizers 0.20.0
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+- f1
+model-index:
+- name: got-model
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: test
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9428571428571428
+    - name: F1
+      type: f1
+      value: 0.9442260195944405
+---
+
+<!-- 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. -->
+
+# got-model
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1971
+- Accuracy: 0.9429
+- F1: 0.9442
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 0.073         | 1.0   | 42   | 0.2416          | 0.9238   | 0.9250 |
+| 0.061         | 2.0   | 84   | 0.2160          | 0.9333   | 0.9345 |
+| 0.0543        | 3.0   | 126  | 0.2114          | 0.9429   | 0.9432 |
+| 0.0497        | 4.0   | 168  | 0.2028          | 0.9429   | 0.9442 |
+| 0.046         | 5.0   | 210  | 0.1985          | 0.9429   | 0.9442 |
+| 0.0435        | 6.0   | 252  | 0.2009          | 0.9429   | 0.9442 |
+| 0.0414        | 7.0   | 294  | 0.1976          | 0.9429   | 0.9442 |
+| 0.0402        | 8.0   | 336  | 0.1978          | 0.9429   | 0.9442 |
+| 0.0391        | 9.0   | 378  | 0.1967          | 0.9429   | 0.9442 |
+| 0.0385        | 10.0  | 420  | 0.1971          | 0.9429   | 0.9442 |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.0

all_results.json

@@ -1,8 +1,14 @@
-{
-    "epoch": 10.0,
-    "total_flos": 5.130291560557363e+17,
-    "train_loss": 0.04840113861220224,
-    "train_runtime": 1424.2891,
-    "train_samples_per_second": 4.648,
-    "train_steps_per_second": 0.295
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.09523809523809523,
+    "eval_f1": 0.016563146997929608,
+    "eval_loss": NaN,
+    "eval_runtime": 2.8277,
+    "eval_samples_per_second": 37.133,
+    "eval_steps_per_second": 4.951,
+    "total_flos": 5.130291560557363e+17,
+    "train_loss": 0.0,
+    "train_runtime": 548.693,
+    "train_samples_per_second": 12.065,
+    "train_steps_per_second": 1.513
 }

config.json

@@ -1,46 +1,46 @@
-{
-  "_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": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8"
-  },
-  "image_size": 224,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6,
-    "LABEL_7": 7,
-    "LABEL_8": 8
-  },
-  "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": "4.45.2"
-}
+{
+  "_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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": "4.46.2"
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.09523809523809523,
+    "eval_f1": 0.016563146997929608,
+    "eval_loss": NaN,
+    "eval_runtime": 2.8277,
+    "eval_samples_per_second": 37.133,
+    "eval_steps_per_second": 4.951
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e4f49d00358cdf718d9df6a65cdd1d1655c075ab6ffe21445ad635be350a8a
+oid sha256:faea4fd9bce54a0a8ac21d7a2f02bfb00b0583239a931c498b5f6a552ec027ec
 size 343245508

preprocessor_config.json

@@ -1,22 +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
-  }
-}
+{
+  "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
+  }
+}

train_results.json

@@ -1,8 +1,8 @@
-{
-    "epoch": 10.0,
-    "total_flos": 5.130291560557363e+17,
-    "train_loss": 0.04840113861220224,
-    "train_runtime": 1424.2891,
-    "train_samples_per_second": 4.648,
-    "train_steps_per_second": 0.295
+{
+    "epoch": 10.0,
+    "total_flos": 5.130291560557363e+17,
+    "train_loss": 0.0,
+    "train_runtime": 548.693,
+    "train_samples_per_second": 12.065,
+    "train_steps_per_second": 1.513
 }

trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 830,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4939759036144578,
+      "grad_norm": NaN,
+      "learning_rate": 1.9012048192771087e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.9879518072289156,
+      "grad_norm": NaN,
+      "learning_rate": 1.802409638554217e-05,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8332,
+      "eval_samples_per_second": 37.061,
+      "eval_steps_per_second": 4.941,
+      "step": 83
+    },
+    {
+      "epoch": 1.4819277108433735,
+      "grad_norm": NaN,
+      "learning_rate": 1.7036144578313254e-05,
+      "loss": 0.0,
+      "step": 123
+    },
+    {
+      "epoch": 1.9759036144578315,
+      "grad_norm": NaN,
+      "learning_rate": 1.604819277108434e-05,
+      "loss": 0.0,
+      "step": 164
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8629,
+      "eval_samples_per_second": 36.676,
+      "eval_steps_per_second": 4.89,
+      "step": 166
+    },
+    {
+      "epoch": 2.4698795180722892,
+      "grad_norm": NaN,
+      "learning_rate": 1.5060240963855424e-05,
+      "loss": 0.0,
+      "step": 205
+    },
+    {
+      "epoch": 2.963855421686747,
+      "grad_norm": NaN,
+      "learning_rate": 1.4072289156626506e-05,
+      "loss": 0.0,
+      "step": 246
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8905,
+      "eval_samples_per_second": 36.326,
+      "eval_steps_per_second": 4.843,
+      "step": 249
+    },
+    {
+      "epoch": 3.4578313253012047,
+      "grad_norm": NaN,
+      "learning_rate": 1.3084337349397591e-05,
+      "loss": 0.0,
+      "step": 287
+    },
+    {
+      "epoch": 3.9518072289156625,
+      "grad_norm": NaN,
+      "learning_rate": 1.2096385542168677e-05,
+      "loss": 0.0,
+      "step": 328
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8626,
+      "eval_samples_per_second": 36.68,
+      "eval_steps_per_second": 4.891,
+      "step": 332
+    },
+    {
+      "epoch": 4.445783132530121,
+      "grad_norm": NaN,
+      "learning_rate": 1.110843373493976e-05,
+      "loss": 0.0,
+      "step": 369
+    },
+    {
+      "epoch": 4.9397590361445785,
+      "grad_norm": NaN,
+      "learning_rate": 1.0120481927710844e-05,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8494,
+      "eval_samples_per_second": 36.849,
+      "eval_steps_per_second": 4.913,
+      "step": 415
+    },
+    {
+      "epoch": 5.433734939759036,
+      "grad_norm": NaN,
+      "learning_rate": 9.132530120481929e-06,
+      "loss": 0.0,
+      "step": 451
+    },
+    {
+      "epoch": 5.927710843373494,
+      "grad_norm": NaN,
+      "learning_rate": 8.144578313253012e-06,
+      "loss": 0.0,
+      "step": 492
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8675,
+      "eval_samples_per_second": 36.617,
+      "eval_steps_per_second": 4.882,
+      "step": 498
+    },
+    {
+      "epoch": 6.421686746987952,
+      "grad_norm": NaN,
+      "learning_rate": 7.156626506024097e-06,
+      "loss": 0.0,
+      "step": 533
+    },
+    {
+      "epoch": 6.9156626506024095,
+      "grad_norm": NaN,
+      "learning_rate": 6.168674698795182e-06,
+      "loss": 0.0,
+      "step": 574
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8441,
+      "eval_samples_per_second": 36.919,
+      "eval_steps_per_second": 4.922,
+      "step": 581
+    },
+    {
+      "epoch": 7.409638554216867,
+      "grad_norm": NaN,
+      "learning_rate": 5.180722891566266e-06,
+      "loss": 0.0,
+      "step": 615
+    },
+    {
+      "epoch": 7.903614457831325,
+      "grad_norm": NaN,
+      "learning_rate": 4.19277108433735e-06,
+      "loss": 0.0,
+      "step": 656
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8258,
+      "eval_samples_per_second": 37.157,
+      "eval_steps_per_second": 4.954,
+      "step": 664
+    },
+    {
+      "epoch": 8.397590361445783,
+      "grad_norm": NaN,
+      "learning_rate": 3.204819277108434e-06,
+      "loss": 0.0,
+      "step": 697
+    },
+    {
+      "epoch": 8.891566265060241,
+      "grad_norm": NaN,
+      "learning_rate": 2.2168674698795183e-06,
+      "loss": 0.0,
+      "step": 738
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8829,
+      "eval_samples_per_second": 36.422,
+      "eval_steps_per_second": 4.856,
+      "step": 747
+    },
+    {
+      "epoch": 9.385542168674698,
+      "grad_norm": NaN,
+      "learning_rate": 1.2289156626506025e-06,
+      "loss": 0.0,
+      "step": 779
+    },
+    {
+      "epoch": 9.879518072289157,
+      "grad_norm": NaN,
+      "learning_rate": 2.409638554216868e-07,
+      "loss": 0.0,
+      "step": 820
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.09523809523809523,
+      "eval_f1": 0.016563146997929608,
+      "eval_loss": NaN,
+      "eval_runtime": 2.8484,
+      "eval_samples_per_second": 36.863,
+      "eval_steps_per_second": 4.915,
+      "step": 830
+    },
+    {
+      "epoch": 10.0,
+      "step": 830,
+      "total_flos": 5.130291560557363e+17,
+      "train_loss": 0.0,
+      "train_runtime": 548.693,
+      "train_samples_per_second": 12.065,
+      "train_steps_per_second": 1.513
+    }
+  ],
+  "logging_steps": 41,
+  "max_steps": 830,
+  "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": 5.130291560557363e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b217f60eca579a79f17be2ca050edd9d4ae9009327acb05ae2ede5375fd5835d
-size 5176
+oid sha256:0700128b977dcfbe9aadb63bb0ff124cbe09812beff12427b460eda1058c382a
+size 5240