itsLeen/swin-large-ai-or-not

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: itsLeen/vit-large-ai-or-not
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: swin-large-ai-or-not
+  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. -->
+
+# swin-large-ai-or-not
+
+This model is a fine-tuned version of [itsLeen/vit-large-ai-or-not](https://huggingface.co/itsLeen/vit-large-ai-or-not) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3914
+- Accuracy: 0.9048
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 31   | 0.2801          | 0.9206   |
+| No log        | 2.0   | 62   | 0.3914          | 0.9048   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 3.885939559150387e+16,
+    "train_loss": 0.41833576079337825,
+    "train_runtime": 107.6715,
+    "train_samples_per_second": 4.607,
+    "train_steps_per_second": 0.576
+}

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "itsLeen/vit-large-ai-or-not",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754f96ad02322143802ffd4fc750c5c62c4ac05718f770cd4364b23e83db7f8c
+size 347498816

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 3.885939559150387e+16,
+    "train_loss": 0.41833576079337825,
+    "train_runtime": 107.6715,
+    "train_samples_per_second": 4.607,
+    "train_steps_per_second": 0.576
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35cf376809255214d244822c67f698816e0928ba8445e0fe54d8826755b1216
+size 5176