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-5e-5
+  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: 0.8043478260869565
+---
+
+<!-- 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-5e-5
+
+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: 0.6236
+- Accuracy: 0.8043
+
+## 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: 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    | 1.3816          | 0.4565   |
+| No log        | 2.0   | 7    | 1.3504          | 0.4565   |
+| 1.3654        | 2.86  | 10   | 1.3075          | 0.4565   |
+| 1.3654        | 4.0   | 14   | 1.2444          | 0.4565   |
+| 1.3654        | 4.86  | 17   | 1.2089          | 0.4565   |
+| 1.2386        | 6.0   | 21   | 1.1711          | 0.4565   |
+| 1.2386        | 6.86  | 24   | 1.1492          | 0.4565   |
+| 1.2386        | 8.0   | 28   | 1.1050          | 0.4783   |
+| 1.132         | 8.86  | 31   | 1.0928          | 0.6522   |
+| 1.132         | 10.0  | 35   | 1.0230          | 0.6739   |
+| 1.132         | 10.86 | 38   | 0.9864          | 0.6522   |
+| 1.015         | 12.0  | 42   | 1.0060          | 0.6739   |
+| 1.015         | 12.86 | 45   | 0.8790          | 0.7174   |
+| 1.015         | 14.0  | 49   | 0.8533          | 0.6739   |
+| 0.9217        | 14.86 | 52   | 0.8203          | 0.6957   |
+| 0.9217        | 16.0  | 56   | 0.8152          | 0.6739   |
+| 0.9217        | 16.86 | 59   | 0.8598          | 0.6522   |
+| 0.7989        | 18.0  | 63   | 0.7979          | 0.6957   |
+| 0.7989        | 18.86 | 66   | 0.7555          | 0.6739   |
+| 0.7309        | 20.0  | 70   | 0.7019          | 0.7609   |
+| 0.7309        | 20.86 | 73   | 0.7254          | 0.7174   |
+| 0.7309        | 22.0  | 77   | 0.7268          | 0.6739   |
+| 0.6267        | 22.86 | 80   | 0.7096          | 0.6739   |
+| 0.6267        | 24.0  | 84   | 0.7568          | 0.6739   |
+| 0.6267        | 24.86 | 87   | 0.6565          | 0.7391   |
+| 0.564         | 26.0  | 91   | 0.7035          | 0.7391   |
+| 0.564         | 26.86 | 94   | 0.7081          | 0.7391   |
+| 0.564         | 28.0  | 98   | 0.6236          | 0.8043   |
+| 0.5625        | 28.86 | 101  | 0.6091          | 0.8043   |
+| 0.5625        | 30.0  | 105  | 0.6523          | 0.7609   |
+| 0.5625        | 30.86 | 108  | 0.6235          | 0.7826   |
+| 0.5185        | 32.0  | 112  | 0.5974          | 0.7826   |
+| 0.5185        | 32.86 | 115  | 0.5944          | 0.7826   |
+| 0.5185        | 34.0  | 119  | 0.6005          | 0.7826   |
+| 0.5005        | 34.29 | 120  | 0.6005          | 0.7826   |
+
+
+### 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": 0.8043478260869565,
+    "eval_loss": 0.6235552430152893,
+    "eval_runtime": 1.0772,
+    "eval_samples_per_second": 42.702,
+    "eval_steps_per_second": 2.785,
+    "train_loss": 0.8312262058258056,
+    "train_runtime": 279.5249,
+    "train_samples_per_second": 30.48,
+    "train_steps_per_second": 0.429
+}

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": 0.8043478260869565,
+    "eval_loss": 0.6235552430152893,
+    "eval_runtime": 1.0772,
+    "eval_samples_per_second": 42.702,
+    "eval_steps_per_second": 2.785
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7311d1c16ff34db12353e03bf06fda66ffaf1b9e775540ca835ba296ebfaa3db
+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_11-06-31_DESKTOP-SKBE9FB/events.out.tfevents.1733072793.DESKTOP-SKBE9FB.18448.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f0380a53f752d78947a93a721d02e76649707506e79e4fd50d9e08e7c8d22f
+size 18615

runs/Dec01_11-06-31_DESKTOP-SKBE9FB/events.out.tfevents.1733073074.DESKTOP-SKBE9FB.18448.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c55c4ffb5ed8de475c7b4690474cb8152e283baf48066e9917a02afea29500
+size 405

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 34.29,
+    "train_loss": 0.8312262058258056,
+    "train_runtime": 279.5249,
+    "train_samples_per_second": 30.48,
+    "train_steps_per_second": 0.429
+}

trainer_state.json

@@ -0,0 +1,417 @@
+{
+  "best_metric": 0.8043478260869565,
+  "best_model_checkpoint": "beit-base-patch16-224-DMAE-5e-5\\checkpoint-98",
+  "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": 1.381615161895752,
+      "eval_runtime": 0.7932,
+      "eval_samples_per_second": 57.995,
+      "eval_steps_per_second": 3.782,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.3503844738006592,
+      "eval_runtime": 0.8112,
+      "eval_samples_per_second": 56.707,
+      "eval_steps_per_second": 3.698,
+      "step": 7
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.3654,
+      "step": 10
+    },
+    {
+      "epoch": 2.86,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.307466745376587,
+      "eval_runtime": 0.7822,
+      "eval_samples_per_second": 58.809,
+      "eval_steps_per_second": 3.835,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.244441032409668,
+      "eval_runtime": 0.7842,
+      "eval_samples_per_second": 58.66,
+      "eval_steps_per_second": 3.826,
+      "step": 14
+    },
+    {
+      "epoch": 4.86,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.2088861465454102,
+      "eval_runtime": 0.7852,
+      "eval_samples_per_second": 58.586,
+      "eval_steps_per_second": 3.821,
+      "step": 17
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 1.2386,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.1710909605026245,
+      "eval_runtime": 0.7777,
+      "eval_samples_per_second": 59.15,
+      "eval_steps_per_second": 3.858,
+      "step": 21
+    },
+    {
+      "epoch": 6.86,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.14915132522583,
+      "eval_runtime": 0.8062,
+      "eval_samples_per_second": 57.059,
+      "eval_steps_per_second": 3.721,
+      "step": 24
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4782608695652174,
+      "eval_loss": 1.1050454378128052,
+      "eval_runtime": 0.7812,
+      "eval_samples_per_second": 58.886,
+      "eval_steps_per_second": 3.84,
+      "step": 28
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.132,
+      "step": 30
+    },
+    {
+      "epoch": 8.86,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 1.0928192138671875,
+      "eval_runtime": 0.7982,
+      "eval_samples_per_second": 57.631,
+      "eval_steps_per_second": 3.759,
+      "step": 31
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 1.0229545831680298,
+      "eval_runtime": 0.8342,
+      "eval_samples_per_second": 55.144,
+      "eval_steps_per_second": 3.596,
+      "step": 35
+    },
+    {
+      "epoch": 10.86,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 0.9864158034324646,
+      "eval_runtime": 0.7922,
+      "eval_samples_per_second": 58.067,
+      "eval_steps_per_second": 3.787,
+      "step": 38
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 1.015,
+      "step": 40
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 1.005975604057312,
+      "eval_runtime": 0.7792,
+      "eval_samples_per_second": 59.037,
+      "eval_steps_per_second": 3.85,
+      "step": 42
+    },
+    {
+      "epoch": 12.86,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.8789530396461487,
+      "eval_runtime": 1.0307,
+      "eval_samples_per_second": 44.628,
+      "eval_steps_per_second": 2.911,
+      "step": 45
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.853344738483429,
+      "eval_runtime": 0.9702,
+      "eval_samples_per_second": 47.412,
+      "eval_steps_per_second": 3.092,
+      "step": 49
+    },
+    {
+      "epoch": 14.29,
+      "learning_rate": 3.240740740740741e-05,
+      "loss": 0.9217,
+      "step": 50
+    },
+    {
+      "epoch": 14.86,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.8203216791152954,
+      "eval_runtime": 0.8002,
+      "eval_samples_per_second": 57.487,
+      "eval_steps_per_second": 3.749,
+      "step": 52
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.8151666522026062,
+      "eval_runtime": 0.8012,
+      "eval_samples_per_second": 57.414,
+      "eval_steps_per_second": 3.744,
+      "step": 56
+    },
+    {
+      "epoch": 16.86,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 0.8598169088363647,
+      "eval_runtime": 0.7827,
+      "eval_samples_per_second": 58.772,
+      "eval_steps_per_second": 3.833,
+      "step": 59
+    },
+    {
+      "epoch": 17.14,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.7989,
+      "step": 60
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.7979407906532288,
+      "eval_runtime": 0.7862,
+      "eval_samples_per_second": 58.511,
+      "eval_steps_per_second": 3.816,
+      "step": 63
+    },
+    {
+      "epoch": 18.86,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.7554780840873718,
+      "eval_runtime": 0.7872,
+      "eval_samples_per_second": 58.437,
+      "eval_steps_per_second": 3.811,
+      "step": 66
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 2.314814814814815e-05,
+      "loss": 0.7309,
+      "step": 70
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.7608695652173914,
+      "eval_loss": 0.7019062042236328,
+      "eval_runtime": 0.8452,
+      "eval_samples_per_second": 54.425,
+      "eval_steps_per_second": 3.549,
+      "step": 70
+    },
+    {
+      "epoch": 20.86,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.7253907322883606,
+      "eval_runtime": 0.8162,
+      "eval_samples_per_second": 56.359,
+      "eval_steps_per_second": 3.676,
+      "step": 73
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.7267776131629944,
+      "eval_runtime": 0.7792,
+      "eval_samples_per_second": 59.037,
+      "eval_steps_per_second": 3.85,
+      "step": 77
+    },
+    {
+      "epoch": 22.86,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.6267,
+      "step": 80
+    },
+    {
+      "epoch": 22.86,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.7095625400543213,
+      "eval_runtime": 0.7832,
+      "eval_samples_per_second": 58.735,
+      "eval_steps_per_second": 3.831,
+      "step": 80
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.7568075060844421,
+      "eval_runtime": 0.7902,
+      "eval_samples_per_second": 58.215,
+      "eval_steps_per_second": 3.797,
+      "step": 84
+    },
+    {
+      "epoch": 24.86,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.6565390825271606,
+      "eval_runtime": 0.7832,
+      "eval_samples_per_second": 58.735,
+      "eval_steps_per_second": 3.831,
+      "step": 87
+    },
+    {
+      "epoch": 25.71,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.564,
+      "step": 90
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.703463077545166,
+      "eval_runtime": 0.8392,
+      "eval_samples_per_second": 54.815,
+      "eval_steps_per_second": 3.575,
+      "step": 91
+    },
+    {
+      "epoch": 26.86,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.7081196904182434,
+      "eval_runtime": 0.7792,
+      "eval_samples_per_second": 59.037,
+      "eval_steps_per_second": 3.85,
+      "step": 94
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.8043478260869565,
+      "eval_loss": 0.6235552430152893,
+      "eval_runtime": 0.7842,
+      "eval_samples_per_second": 58.66,
+      "eval_steps_per_second": 3.826,
+      "step": 98
+    },
+    {
+      "epoch": 28.57,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.5625,
+      "step": 100
+    },
+    {
+      "epoch": 28.86,
+      "eval_accuracy": 0.8043478260869565,
+      "eval_loss": 0.6090804934501648,
+      "eval_runtime": 0.7902,
+      "eval_samples_per_second": 58.214,
+      "eval_steps_per_second": 3.797,
+      "step": 101
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.7608695652173914,
+      "eval_loss": 0.652334988117218,
+      "eval_runtime": 0.7812,
+      "eval_samples_per_second": 58.886,
+      "eval_steps_per_second": 3.84,
+      "step": 105
+    },
+    {
+      "epoch": 30.86,
+      "eval_accuracy": 0.782608695652174,
+      "eval_loss": 0.6235449910163879,
+      "eval_runtime": 0.7912,
+      "eval_samples_per_second": 58.141,
+      "eval_steps_per_second": 3.792,
+      "step": 108
+    },
+    {
+      "epoch": 31.43,
+      "learning_rate": 4.6296296296296296e-06,
+      "loss": 0.5185,
+      "step": 110
+    },
+    {
+      "epoch": 32.0,
+      "eval_accuracy": 0.782608695652174,
+      "eval_loss": 0.5974029898643494,
+      "eval_runtime": 0.7762,
+      "eval_samples_per_second": 59.265,
+      "eval_steps_per_second": 3.865,
+      "step": 112
+    },
+    {
+      "epoch": 32.86,
+      "eval_accuracy": 0.782608695652174,
+      "eval_loss": 0.5943583846092224,
+      "eval_runtime": 0.7887,
+      "eval_samples_per_second": 58.324,
+      "eval_steps_per_second": 3.804,
+      "step": 115
+    },
+    {
+      "epoch": 34.0,
+      "eval_accuracy": 0.782608695652174,
+      "eval_loss": 0.6004733443260193,
+      "eval_runtime": 0.7862,
+      "eval_samples_per_second": 58.511,
+      "eval_steps_per_second": 3.816,
+      "step": 119
+    },
+    {
+      "epoch": 34.29,
+      "learning_rate": 0.0,
+      "loss": 0.5005,
+      "step": 120
+    },
+    {
+      "epoch": 34.29,
+      "eval_accuracy": 0.782608695652174,
+      "eval_loss": 0.6005403399467468,
+      "eval_runtime": 0.7812,
+      "eval_samples_per_second": 58.886,
+      "eval_steps_per_second": 3.84,
+      "step": 120
+    },
+    {
+      "epoch": 34.29,
+      "step": 120,
+      "total_flos": 5.659246428298445e+17,
+      "train_loss": 0.8312262058258056,
+      "train_runtime": 279.5249,
+      "train_samples_per_second": 30.48,
+      "train_steps_per_second": 0.429
+    }
+  ],
+  "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:b0de54185baab8e67f0286e2eca28c11dabac9f823a8bc875881b2a63086c94f
+size 4728