End of training

README.md

@@ -0,0 +1,112 @@
+---
+license: apache-2.0
+base_model: microsoft/beit-base-patch16-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: beit-base-patch16-224-DMAE
+  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: 0.7608695652173914
+---
+
+<!-- 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. -->
+
+# beit-base-patch16-224-DMAE
+
+This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6703
+- Accuracy: 0.7609
+
+## 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: 0.00015
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 40
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 0.86  | 3    | 1.3117          | 0.4565   |
+| No log        | 2.0   | 7    | 1.2539          | 0.4565   |
+| 1.2875        | 2.86  | 10   | 1.2355          | 0.4565   |
+| 1.2875        | 4.0   | 14   | 1.1827          | 0.4783   |
+| 1.2875        | 4.86  | 17   | 1.0758          | 0.6522   |
+| 1.1369        | 6.0   | 21   | 1.0942          | 0.5      |
+| 1.1369        | 6.86  | 24   | 1.1312          | 0.5217   |
+| 1.1369        | 8.0   | 28   | 1.0906          | 0.5217   |
+| 1.1009        | 8.86  | 31   | 0.8704          | 0.6957   |
+| 1.1009        | 10.0  | 35   | 1.0023          | 0.5870   |
+| 1.1009        | 10.86 | 38   | 1.0288          | 0.5870   |
+| 0.9152        | 12.0  | 42   | 0.7874          | 0.7174   |
+| 0.9152        | 12.86 | 45   | 0.7166          | 0.7174   |
+| 0.9152        | 14.0  | 49   | 0.7269          | 0.6957   |
+| 0.8444        | 14.86 | 52   | 0.8481          | 0.6957   |
+| 0.8444        | 16.0  | 56   | 0.7589          | 0.6304   |
+| 0.8444        | 16.86 | 59   | 0.7590          | 0.6304   |
+| 0.8085        | 18.0  | 63   | 0.8320          | 0.6304   |
+| 0.8085        | 18.86 | 66   | 0.7469          | 0.7391   |
+| 0.6941        | 20.0  | 70   | 0.8337          | 0.6304   |
+| 0.6941        | 20.86 | 73   | 0.7928          | 0.7174   |
+| 0.6941        | 22.0  | 77   | 0.8765          | 0.6522   |
+| 0.5822        | 22.86 | 80   | 0.7139          | 0.7174   |
+| 0.5822        | 24.0  | 84   | 0.7477          | 0.6957   |
+| 0.5822        | 24.86 | 87   | 0.6987          | 0.7174   |
+| 0.5174        | 26.0  | 91   | 0.6815          | 0.7391   |
+| 0.5174        | 26.86 | 94   | 0.7332          | 0.7174   |
+| 0.5174        | 28.0  | 98   | 0.6582          | 0.7391   |
+| 0.48          | 28.86 | 101  | 0.7273          | 0.7391   |
+| 0.48          | 30.0  | 105  | 0.7595          | 0.6957   |
+| 0.48          | 30.86 | 108  | 0.7136          | 0.7391   |
+| 0.4159        | 32.0  | 112  | 0.6703          | 0.7609   |
+| 0.4159        | 32.86 | 115  | 0.6736          | 0.7609   |
+| 0.4159        | 34.0  | 119  | 0.6866          | 0.7609   |
+| 0.3472        | 34.29 | 120  | 0.6873          | 0.7609   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 34.29,
+    "eval_accuracy": 0.7608695652173914,
+    "eval_loss": 0.6703464388847351,
+    "eval_runtime": 0.9412,
+    "eval_samples_per_second": 48.873,
+    "eval_steps_per_second": 3.187,
+    "train_loss": 0.7608571231365204,
+    "train_runtime": 273.4381,
+    "train_samples_per_second": 31.159,
+    "train_steps_per_second": 0.439
+}

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "microsoft/beit-base-patch16-224",
+  "add_fpn": false,
+  "architectures": [
+    "BeitForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auxiliary_channels": 256,
+  "auxiliary_concat_input": false,
+  "auxiliary_loss_weight": 0.4,
+  "auxiliary_num_convs": 1,
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "avanzada",
+    "1": "leve",
+    "2": "moderada",
+    "3": "no dmae"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "avanzada": 0,
+    "leve": 1,
+    "moderada": 2,
+    "no dmae": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "out_features": [
+    "stage12"
+  ],
+  "out_indices": [
+    12
+  ],
+  "patch_size": 16,
+  "pool_scales": [
+    1,
+    2,
+    3,
+    6
+  ],
+  "problem_type": "single_label_classification",
+  "reshape_hidden_states": true,
+  "semantic_loss_ignore_index": 255,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_absolute_position_embeddings": false,
+  "use_auxiliary_head": true,
+  "use_mask_token": false,
+  "use_mean_pooling": true,
+  "use_relative_position_bias": true,
+  "use_shared_relative_position_bias": false,
+  "vocab_size": 8192
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 34.29,
+    "eval_accuracy": 0.7608695652173914,
+    "eval_loss": 0.6703464388847351,
+    "eval_runtime": 0.9412,
+    "eval_samples_per_second": 48.873,
+    "eval_steps_per_second": 3.187
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a016a111b6eaf4f931d12977149905f4d7d88631870443437645b1933a97216
+size 343086480

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "BeitImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Dec01_10-53-02_DESKTOP-SKBE9FB/events.out.tfevents.1733071983.DESKTOP-SKBE9FB.2928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a95f8f664233edfeb0630eef4c7dd6cd5331bdb36fcebb2fa96b784bfce7f080
+size 18602

runs/Dec01_10-53-02_DESKTOP-SKBE9FB/events.out.tfevents.1733072258.DESKTOP-SKBE9FB.2928.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2821bb3fb209cc81b3d5038676a6cea56d78f76dd70961ec316e9bbd1d09bfde
+size 405

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 34.29,
+    "train_loss": 0.7608571231365204,
+    "train_runtime": 273.4381,
+    "train_samples_per_second": 31.159,
+    "train_steps_per_second": 0.439
+}

trainer_state.json

@@ -0,0 +1,417 @@
+{
+  "best_metric": 0.7608695652173914,
+  "best_model_checkpoint": "beit-base-patch16-224-DMAE\\checkpoint-112",
+  "epoch": 34.285714285714285,
+  "eval_steps": 500,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.86,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.3116604089736938,
+      "eval_runtime": 0.8082,
+      "eval_samples_per_second": 56.918,
+      "eval_steps_per_second": 3.712,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.253861665725708,
+      "eval_runtime": 0.7892,
+      "eval_samples_per_second": 58.289,
+      "eval_steps_per_second": 3.801,
+      "step": 7
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.000125,
+      "loss": 1.2875,
+      "step": 10
+    },
+    {
+      "epoch": 2.86,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.2354518175125122,
+      "eval_runtime": 0.8662,
+      "eval_samples_per_second": 53.106,
+      "eval_steps_per_second": 3.463,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4782608695652174,
+      "eval_loss": 1.1826977729797363,
+      "eval_runtime": 0.8117,
+      "eval_samples_per_second": 56.672,
+      "eval_steps_per_second": 3.696,
+      "step": 14
+    },
+    {
+      "epoch": 4.86,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 1.0757725238800049,
+      "eval_runtime": 0.8062,
+      "eval_samples_per_second": 57.059,
+      "eval_steps_per_second": 3.721,
+      "step": 17
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 1.1369,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.094215750694275,
+      "eval_runtime": 0.8172,
+      "eval_samples_per_second": 56.29,
+      "eval_steps_per_second": 3.671,
+      "step": 21
+    },
+    {
+      "epoch": 6.86,
+      "eval_accuracy": 0.5217391304347826,
+      "eval_loss": 1.1311554908752441,
+      "eval_runtime": 0.8022,
+      "eval_samples_per_second": 57.344,
+      "eval_steps_per_second": 3.74,
+      "step": 24
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5217391304347826,
+      "eval_loss": 1.0906236171722412,
+      "eval_runtime": 0.7872,
+      "eval_samples_per_second": 58.437,
+      "eval_steps_per_second": 3.811,
+      "step": 28
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 0.000125,
+      "loss": 1.1009,
+      "step": 30
+    },
+    {
+      "epoch": 8.86,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.8703853487968445,
+      "eval_runtime": 0.8317,
+      "eval_samples_per_second": 55.309,
+      "eval_steps_per_second": 3.607,
+      "step": 31
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5869565217391305,
+      "eval_loss": 1.0023223161697388,
+      "eval_runtime": 0.7942,
+      "eval_samples_per_second": 57.922,
+      "eval_steps_per_second": 3.777,
+      "step": 35
+    },
+    {
+      "epoch": 10.86,
+      "eval_accuracy": 0.5869565217391305,
+      "eval_loss": 1.028790831565857,
+      "eval_runtime": 0.7872,
+      "eval_samples_per_second": 58.437,
+      "eval_steps_per_second": 3.811,
+      "step": 38
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 0.9152,
+      "step": 40
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.7874318957328796,
+      "eval_runtime": 0.8082,
+      "eval_samples_per_second": 56.918,
+      "eval_steps_per_second": 3.712,
+      "step": 42
+    },
+    {
+      "epoch": 12.86,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.7165546417236328,
+      "eval_runtime": 0.7942,
+      "eval_samples_per_second": 57.922,
+      "eval_steps_per_second": 3.777,
+      "step": 45
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.7269295454025269,
+      "eval_runtime": 0.7872,
+      "eval_samples_per_second": 58.436,
+      "eval_steps_per_second": 3.811,
+      "step": 49
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 9.722222222222222e-05,
+      "loss": 0.8444,
+      "step": 50
+    },
+    {
+      "epoch": 14.86,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.8481345176696777,
+      "eval_runtime": 0.8212,
+      "eval_samples_per_second": 56.017,
+      "eval_steps_per_second": 3.653,
+      "step": 52
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.6304347826086957,
+      "eval_loss": 0.7588916420936584,
+      "eval_runtime": 0.7842,
+      "eval_samples_per_second": 58.66,
+      "eval_steps_per_second": 3.826,
+      "step": 56
+    },
+    {
+      "epoch": 16.86,
+      "eval_accuracy": 0.6304347826086957,
+      "eval_loss": 0.7590357065200806,
+      "eval_runtime": 0.7922,
+      "eval_samples_per_second": 58.068,
+      "eval_steps_per_second": 3.787,
+      "step": 59
+    },
+    {
+      "epoch": 17.14,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 0.8085,
+      "step": 60
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.6304347826086957,
+      "eval_loss": 0.8319522738456726,
+      "eval_runtime": 0.8282,
+      "eval_samples_per_second": 55.543,
+      "eval_steps_per_second": 3.622,
+      "step": 63
+    },
+    {
+      "epoch": 18.86,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.7469342350959778,
+      "eval_runtime": 0.7967,
+      "eval_samples_per_second": 57.739,
+      "eval_steps_per_second": 3.766,
+      "step": 66
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 6.944444444444444e-05,
+      "loss": 0.6941,
+      "step": 70
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.6304347826086957,
+      "eval_loss": 0.8336846828460693,
+      "eval_runtime": 0.7982,
+      "eval_samples_per_second": 57.631,
+      "eval_steps_per_second": 3.759,
+      "step": 70
+    },
+    {
+      "epoch": 20.86,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.7927964925765991,
+      "eval_runtime": 0.7992,
+      "eval_samples_per_second": 57.559,
+      "eval_steps_per_second": 3.754,
+      "step": 73
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 0.87651526927948,
+      "eval_runtime": 0.8002,
+      "eval_samples_per_second": 57.486,
+      "eval_steps_per_second": 3.749,
+      "step": 77
+    },
+    {
+      "epoch": 22.86,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 0.5822,
+      "step": 80
+    },
+    {
+      "epoch": 22.86,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.7139173746109009,
+      "eval_runtime": 0.9727,
+      "eval_samples_per_second": 47.29,
+      "eval_steps_per_second": 3.084,
+      "step": 80
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.7476540207862854,
+      "eval_runtime": 0.7992,
+      "eval_samples_per_second": 57.559,
+      "eval_steps_per_second": 3.754,
+      "step": 84
+    },
+    {
+      "epoch": 24.86,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.6986671686172485,
+      "eval_runtime": 0.7972,
+      "eval_samples_per_second": 57.703,
+      "eval_steps_per_second": 3.763,
+      "step": 87
+    },
+    {
+      "epoch": 25.71,
+      "learning_rate": 4.1666666666666665e-05,
+      "loss": 0.5174,
+      "step": 90
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.6814792156219482,
+      "eval_runtime": 0.8162,
+      "eval_samples_per_second": 56.36,
+      "eval_steps_per_second": 3.676,
+      "step": 91
+    },
+    {
+      "epoch": 26.86,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.7331640720367432,
+      "eval_runtime": 0.7922,
+      "eval_samples_per_second": 58.068,
+      "eval_steps_per_second": 3.787,
+      "step": 94
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.6581622958183289,
+      "eval_runtime": 0.8077,
+      "eval_samples_per_second": 56.953,
+      "eval_steps_per_second": 3.714,
+      "step": 98
+    },
+    {
+      "epoch": 28.57,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 0.48,
+      "step": 100
+    },
+    {
+      "epoch": 28.86,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.7272840738296509,
+      "eval_runtime": 0.8112,
+      "eval_samples_per_second": 56.707,
+      "eval_steps_per_second": 3.698,
+      "step": 101
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.7594702243804932,
+      "eval_runtime": 0.8242,
+      "eval_samples_per_second": 55.813,
+      "eval_steps_per_second": 3.64,
+      "step": 105
+    },
+    {
+      "epoch": 30.86,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.7136482000350952,
+      "eval_runtime": 0.8099,
+      "eval_samples_per_second": 56.795,
+      "eval_steps_per_second": 3.704,
+      "step": 108
+    },
+    {
+      "epoch": 31.43,
+      "learning_rate": 1.3888888888888886e-05,
+      "loss": 0.4159,
+      "step": 110
+    },
+    {
+      "epoch": 32.0,
+      "eval_accuracy": 0.7608695652173914,
+      "eval_loss": 0.6703464388847351,
+      "eval_runtime": 0.8182,
+      "eval_samples_per_second": 56.222,
+      "eval_steps_per_second": 3.667,
+      "step": 112
+    },
+    {
+      "epoch": 32.86,
+      "eval_accuracy": 0.7608695652173914,
+      "eval_loss": 0.6735560894012451,
+      "eval_runtime": 0.7952,
+      "eval_samples_per_second": 57.849,
+      "eval_steps_per_second": 3.773,
+      "step": 115
+    },
+    {
+      "epoch": 34.0,
+      "eval_accuracy": 0.7608695652173914,
+      "eval_loss": 0.6866115927696228,
+      "eval_runtime": 0.7867,
+      "eval_samples_per_second": 58.473,
+      "eval_steps_per_second": 3.813,
+      "step": 119
+    },
+    {
+      "epoch": 34.29,
+      "learning_rate": 0.0,
+      "loss": 0.3472,
+      "step": 120
+    },
+    {
+      "epoch": 34.29,
+      "eval_accuracy": 0.7608695652173914,
+      "eval_loss": 0.6872942447662354,
+      "eval_runtime": 0.8602,
+      "eval_samples_per_second": 53.476,
+      "eval_steps_per_second": 3.488,
+      "step": 120
+    },
+    {
+      "epoch": 34.29,
+      "step": 120,
+      "total_flos": 5.659246428298445e+17,
+      "train_loss": 0.7608571231365204,
+      "train_runtime": 273.4381,
+      "train_samples_per_second": 31.159,
+      "train_steps_per_second": 0.439
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 5.659246428298445e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5b80051ba40bdb8d5e85da409fd883b761f4e021e6200334caaf99a96dae02
+size 4728