32health/non-ada-classification

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: facebook/dinov2-large
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: output_dinov2_large
+  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. -->
+
+# output_dinov2_large
+
+This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0294
+- Precision: 0.9810
+- Recall: 0.9748
+- F1: 0.9779
+
+## 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-06
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 145  | 0.0585          | 0.9332    | 0.9538 | 0.9434 |
+| No log        | 2.0   | 290  | 0.0367          | 0.9527    | 0.9727 | 0.9626 |
+| No log        | 3.0   | 435  | 0.0338          | 0.9776    | 0.9622 | 0.9698 |
+| 1.3658        | 4.0   | 580  | 0.0265          | 0.9718    | 0.9769 | 0.9743 |
+| 1.3658        | 5.0   | 725  | 0.0250          | 0.9708    | 0.9790 | 0.9749 |
+| 1.3658        | 6.0   | 870  | 0.0323          | 0.9809    | 0.9695 | 0.9752 |
+| 0.0959        | 7.0   | 1015 | 0.0285          | 0.9749    | 0.9800 | 0.9775 |
+| 0.0959        | 8.0   | 1160 | 0.0319          | 0.9820    | 0.9727 | 0.9773 |
+| 0.0959        | 9.0   | 1305 | 0.0313          | 0.9810    | 0.9737 | 0.9773 |
+| 0.0959        | 10.0  | 1450 | 0.0294          | 0.9810    | 0.9748 | 0.9779 |
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.5.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,82 @@
+{
+  "apply_layernorm": true,
+  "architectures": [
+    "Dinov2ForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "drop_path_rate": 0.0,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Pano",
+    "1": "FMX",
+    "2": "BW",
+    "3": "PA",
+    "4": "PC",
+    "5": "IOP",
+    "6": "Photo",
+    "7": "NA"
+  },
+  "image_size": 518,
+  "initializer_range": 0.02,
+  "label2id": {
+    "BW": 2,
+    "FMX": 1,
+    "IOP": 5,
+    "NA": 7,
+    "PA": 3,
+    "PC": 4,
+    "Pano": 0,
+    "Photo": 6
+  },
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "out_features": [
+    "stage24"
+  ],
+  "out_indices": [
+    24
+  ],
+  "patch_size": 14,
+  "problem_type": "multi_label_classification",
+  "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12",
+    "stage13",
+    "stage14",
+    "stage15",
+    "stage16",
+    "stage17",
+    "stage18",
+    "stage19",
+    "stage20",
+    "stage21",
+    "stage22",
+    "stage23",
+    "stage24"
+  ],
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "use_mask_token": true,
+  "use_swiglu_ffn": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4df401f0ea555eea8a699cdc5a42ab2bcfbce5d3e87a3cae058fc9f954a748
+size 1217591688

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "data_format": "channels_first",
+  "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": "BitImageProcessorFast",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baab5a65c7796696f889c100871960b3db63b5f99eda718fef4b90ba83c15843
+size 5201