End of training

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: facebook/dinov2-base
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: dinov2-base-finetuned-har
+  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: 0.8683473389355743
+---
+
+<!-- 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. -->
+
+# dinov2-base-finetuned-har
+
+This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4009
+- Accuracy: 0.8683
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.9308        | 0.9801 | 37   | 0.5692          | 0.8301   |
+| 0.7052        | 1.9868 | 75   | 0.4806          | 0.8469   |
+| 0.5414        | 2.9404 | 111  | 0.4009          | 0.8683   |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.4.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.9403973509933774,
+    "eval_accuracy": 0.8683473389355743,
+    "eval_loss": 0.4009244740009308,
+    "eval_runtime": 16.7576,
+    "eval_samples_per_second": 63.911,
+    "eval_steps_per_second": 1.014,
+    "total_flos": 2.897918409348219e+18,
+    "train_loss": 0.8824126113642443,
+    "train_runtime": 1162.7997,
+    "train_samples_per_second": 24.868,
+    "train_steps_per_second": 0.095
+}

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "facebook/dinov2-base",
+  "apply_layernorm": true,
+  "architectures": [
+    "Dinov2ForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "drop_path_rate": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "calling",
+    "1": "clapping",
+    "2": "cycling",
+    "3": "dancing",
+    "4": "drinking",
+    "5": "eating",
+    "6": "fighting",
+    "7": "hugging",
+    "8": "laughing",
+    "9": "listening_to_music",
+    "10": "running",
+    "11": "sitting",
+    "12": "sleeping",
+    "13": "texting",
+    "14": "using_laptop"
+  },
+  "image_size": 518,
+  "initializer_range": 0.02,
+  "label2id": {
+    "calling": 0,
+    "clapping": 1,
+    "cycling": 2,
+    "dancing": 3,
+    "drinking": 4,
+    "eating": 5,
+    "fighting": 6,
+    "hugging": 7,
+    "laughing": 8,
+    "listening_to_music": 9,
+    "running": 10,
+    "sitting": 11,
+    "sleeping": 12,
+    "texting": 13,
+    "using_laptop": 14
+  },
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "out_features": [
+    "stage12"
+  ],
+  "out_indices": [
+    12
+  ],
+  "patch_size": 14,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "use_swiglu_ffn": false
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9403973509933774,
+    "eval_accuracy": 0.8683473389355743,
+    "eval_loss": 0.4009244740009308,
+    "eval_runtime": 16.7576,
+    "eval_samples_per_second": 63.911,
+    "eval_steps_per_second": 1.014
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871810da26e66871898b38e81fdea72726776b07bc4c63245e0a7c107e40906c
+size 346439852

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "BitImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}

runs/Sep06_16-54-48_85a93488dee6/events.out.tfevents.1725641801.85a93488dee6.36.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f53b9efabcba354c4c95aca8a50808c5b2b4321635fbe5fda5720677738482
+size 9512

runs/Sep06_16-54-48_85a93488dee6/events.out.tfevents.1725643284.85a93488dee6.36.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d888bf75523fd36c4df7e8f2a14a7f7089b5c2f9c81eaaafcaa6add5010046
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9403973509933774,
+    "total_flos": 2.897918409348219e+18,
+    "train_loss": 0.8824126113642443,
+    "train_runtime": 1162.7997,
+    "train_samples_per_second": 24.868,
+    "train_steps_per_second": 0.095
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": 0.8683473389355743,
+  "best_model_checkpoint": "/kaggle/working/dinov2-base-finetuned-har/checkpoint-111",
+  "epoch": 2.9403973509933774,
+  "eval_steps": 500,
+  "global_step": 111,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26490066225165565,
+      "grad_norm": 80.4668197631836,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 2.2896,
+      "step": 10
+    },
+    {
+      "epoch": 0.5298013245033113,
+      "grad_norm": 28.893081665039062,
+      "learning_rate": 4.595959595959596e-05,
+      "loss": 1.1524,
+      "step": 20
+    },
+    {
+      "epoch": 0.7947019867549668,
+      "grad_norm": 21.720983505249023,
+      "learning_rate": 4.0909090909090915e-05,
+      "loss": 0.9308,
+      "step": 30
+    },
+    {
+      "epoch": 0.9801324503311258,
+      "eval_accuracy": 0.8300653594771242,
+      "eval_loss": 0.5691878795623779,
+      "eval_runtime": 22.1989,
+      "eval_samples_per_second": 48.246,
+      "eval_steps_per_second": 0.766,
+      "step": 37
+    },
+    {
+      "epoch": 1.0596026490066226,
+      "grad_norm": 22.94610023498535,
+      "learning_rate": 3.5858585858585855e-05,
+      "loss": 0.863,
+      "step": 40
+    },
+    {
+      "epoch": 1.3245033112582782,
+      "grad_norm": 24.597158432006836,
+      "learning_rate": 3.080808080808081e-05,
+      "loss": 0.7744,
+      "step": 50
+    },
+    {
+      "epoch": 1.589403973509934,
+      "grad_norm": 16.806970596313477,
+      "learning_rate": 2.575757575757576e-05,
+      "loss": 0.7287,
+      "step": 60
+    },
+    {
+      "epoch": 1.8543046357615895,
+      "grad_norm": 16.49362564086914,
+      "learning_rate": 2.070707070707071e-05,
+      "loss": 0.7052,
+      "step": 70
+    },
+    {
+      "epoch": 1.9867549668874172,
+      "eval_accuracy": 0.8468720821661998,
+      "eval_loss": 0.4805677831172943,
+      "eval_runtime": 15.9267,
+      "eval_samples_per_second": 67.246,
+      "eval_steps_per_second": 1.067,
+      "step": 75
+    },
+    {
+      "epoch": 2.119205298013245,
+      "grad_norm": 22.60504722595215,
+      "learning_rate": 1.565656565656566e-05,
+      "loss": 0.6016,
+      "step": 80
+    },
+    {
+      "epoch": 2.384105960264901,
+      "grad_norm": 15.832114219665527,
+      "learning_rate": 1.0606060606060607e-05,
+      "loss": 0.5896,
+      "step": 90
+    },
+    {
+      "epoch": 2.6490066225165565,
+      "grad_norm": 12.651689529418945,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.5613,
+      "step": 100
+    },
+    {
+      "epoch": 2.9139072847682117,
+      "grad_norm": 17.284223556518555,
+      "learning_rate": 5.050505050505052e-07,
+      "loss": 0.5414,
+      "step": 110
+    },
+    {
+      "epoch": 2.9403973509933774,
+      "eval_accuracy": 0.8683473389355743,
+      "eval_loss": 0.4009244740009308,
+      "eval_runtime": 15.8918,
+      "eval_samples_per_second": 67.393,
+      "eval_steps_per_second": 1.07,
+      "step": 111
+    },
+    {
+      "epoch": 2.9403973509933774,
+      "step": 111,
+      "total_flos": 2.897918409348219e+18,
+      "train_loss": 0.8824126113642443,
+      "train_runtime": 1162.7997,
+      "train_samples_per_second": 24.868,
+      "train_steps_per_second": 0.095
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 111,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.897918409348219e+18,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0466811c297431f27147c596df290edba625fff6c1885fc8e974ee18b87a00
+size 5240