itsLeen/swin-large-ai-or-nott

README.md

@@ -4,11 +4,26 @@ license: apache-2.0
 base_model: itsLeen/swin-large-ai-or-not
 tags:
 - generated_from_trainer
+datasets:
+- imagefolder
 metrics:
 - accuracy
 model-index:
 - name: swin-large-ai-or-not
-  results: []
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train[:2000]
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9625
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # swin-large-ai-or-not
 
-This model is a fine-tuned version of [itsLeen/swin-large-ai-or-not](https://huggingface.co/itsLeen/swin-large-ai-or-not) on an unknown dataset.
+This model is a fine-tuned version of [itsLeen/swin-large-ai-or-not](https://huggingface.co/itsLeen/swin-large-ai-or-not) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3141
-- Accuracy: 0.95
+- Loss: 0.2540
+- Accuracy: 0.9625
 
 ## Model description
 
@@ -38,14 +53,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 16
+- learning_rate: 3e-05
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
+- lr_scheduler_type: cosine
 - num_epochs: 20
 - mixed_precision_training: Native AMP
 
@@ -53,18 +68,19 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3817        | 2.0   | 50   | 0.2489          | 0.92     |
-| 0.0787        | 4.0   | 100  | 0.3381          | 0.92     |
-| 0.0361        | 6.0   | 150  | 0.3256          | 0.93     |
-| 0.012         | 8.0   | 200  | 0.3192          | 0.94     |
-| 0.0062        | 10.0  | 250  | 0.2874          | 0.955    |
-| 0.0026        | 12.0  | 300  | 0.3379          | 0.95     |
-| 0.003         | 14.0  | 350  | 0.3620          | 0.945    |
-| 0.003         | 16.0  | 400  | 0.3141          | 0.95     |
+| 0.1485        | 1.0   | 100  | 0.2140          | 0.93     |
+| 0.0185        | 2.0   | 200  | 0.1999          | 0.9625   |
+| 0.0122        | 3.0   | 300  | 0.1703          | 0.9575   |
+| 0.0044        | 4.0   | 400  | 0.1952          | 0.9575   |
+| 0.0           | 5.0   | 500  | 0.2642          | 0.965    |
+| 0.0           | 6.0   | 600  | 0.2600          | 0.965    |
+| 0.0           | 7.0   | 700  | 0.3664          | 0.9625   |
+| 0.0           | 8.0   | 800  | 0.2540          | 0.9625   |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
 - Pytorch 2.5.0+cu121
+- Datasets 3.1.0
 - Tokenizers 0.19.1

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 16.0,
+    "epoch": 8.0,
     "total_flos": 1.0028231120388096e+18,
-    "train_loss": 0.06541787043213844,
-    "train_runtime": 1788.9812,
-    "train_samples_per_second": 8.944,
-    "train_steps_per_second": 0.279
+    "train_loss": 0.03964285453781485,
+    "train_runtime": 2016.2985,
+    "train_samples_per_second": 15.871,
+    "train_steps_per_second": 0.992
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8616bc58b4fa8d256f08240e9a9e71c41273c61bd6a76d09081522507a72d6b3
+oid sha256:c49b17008b5fa8e6fe35e45d2bff15f60ac98f912bb0cd32bde3187b637ef6b2
 size 347498816

runs/Nov05_19-59-26_dbf8ab450a93/events.out.tfevents.1730836768.dbf8ab450a93.798.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d4c2dd4f5e469757d1c472fea6aced9ae2ff7307a1fa1c141dd18cc306cfb2
+size 11967

runs/Nov05_20-33-53_dbf8ab450a93/events.out.tfevents.1730838835.dbf8ab450a93.798.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7df323e5c2eb31860f903da7f548af6db988bd46f50655346d6978e0cf0857e
+size 11968

runs/Nov05_21-09-20_dbf8ab450a93/events.out.tfevents.1730840969.dbf8ab450a93.798.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2709b64d7144afff4b7cd813b91e41b6891f3cd23e9644216a58c4bf106f639
+size 14892

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 16.0,
+    "epoch": 8.0,
     "total_flos": 1.0028231120388096e+18,
-    "train_loss": 0.06541787043213844,
-    "train_runtime": 1788.9812,
-    "train_samples_per_second": 8.944,
-    "train_steps_per_second": 0.279
+    "train_loss": 0.03964285453781485,
+    "train_runtime": 2016.2985,
+    "train_samples_per_second": 15.871,
+    "train_steps_per_second": 0.992
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a04433f297c998d5da5994ba9e737e1c5111cddbedd621134203217302a8966
+oid sha256:7f71648cc0aa416296e2b8c942150816176f175ccd7e9d3c4e9dda8976c83f8d
 size 5176