X-ray-ai-detection_v2

README.md

@@ -1,4 +1,5 @@
 ---
+license: cc-by-4.0
 base_model: umm-maybe/AI-image-detector
 tags:
 - generated_from_trainer
@@ -12,21 +13,19 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [umm-maybe/AI-image-detector](https://huggingface.co/umm-maybe/AI-image-detector) 
-on synthetic-pggan-chest-xrays dataset for AI-generated data, chest-xray-pneumonia for real data.
+This model is a fine-tuned version of [umm-maybe/AI-image-detector](https://huggingface.co/umm-maybe/AI-image-detector) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0554
-- eval_accuracy: 0.9842
-- eval_runtime: 88.2511
-- eval_samples_per_second: 25.065
-- eval_steps_per_second: 3.139
-- epoch: 0.09
-- step: 100
+- eval_loss: 0.1365
+- eval_accuracy: 0.9612
+- eval_runtime: 35.5742
+- eval_samples_per_second: 16.669
+- eval_steps_per_second: 2.108
+- epoch: 1.86
+- step: 550
 
 ## Model description
 
-A model is a practical part of my master's thesis. 
-The model is solving the problem of detection AI-generated images (CT, MRI, X-ray scans in medical domain)
+More information needed
 
 ## Intended uses & limitations
 
@@ -52,6 +51,6 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu118
-- Tokenizers 0.15.0
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Tokenizers 0.15.2

config.json

@@ -57,7 +57,7 @@
     "stage4"
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.37.2",
   "use_absolute_embeddings": false,
   "window_size": 7
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:309765249ddaf9a0be789c5d4f0124b026fa3a767608890595ba403ffa796956
+oid sha256:a95c39b87e8143adce646d3318a20dec81aeb4218f24d70fcc2302e0f0cb3c3d
 size 347498816

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49424b10287be137405df23bf4458f99754543aa611f8d41259833b619e43964
-size 4536
+oid sha256:b2e18d112bea1dd86f58cc9314cfeea5bf4bfc436fb7f99fe9c69d90179e4420
+size 4664