Model save

all_results.json

@@ -1,8 +1,13 @@
 {
-    "epoch": 10.0,
-    "total_flos": 9.942951223296e+16,
-    "train_loss": 0.5497611045837403,
-    "train_runtime": 245.3761,
-    "train_samples_per_second": 16.302,
-    "train_steps_per_second": 0.285
+    "epoch": 8.0,
+    "eval_accuracy": 0.8625,
+    "eval_loss": 0.3848486542701721,
+    "eval_runtime": 3.7207,
+    "eval_samples_per_second": 21.501,
+    "eval_steps_per_second": 2.688,
+    "total_flos": 7.9543609786368e+16,
+    "train_loss": 0.7504995593002864,
+    "train_runtime": 163.9569,
+    "train_samples_per_second": 19.517,
+    "train_steps_per_second": 0.342
 }

config.json

@@ -1,18 +1,10 @@
 {
-  "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
+  "_name_or_path": "tcvrishank/histo_train_vit",
   "architectures": [
-    "SwinForImageClassification"
+    "ViTForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "depths": [
-    2,
-    2,
-    6,
-    2
-  ],
-  "drop_path_rate": 0.1,
-  "embed_dim": 96,
-  "encoder_stride": 32,
+  "encoder_stride": 16,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
@@ -24,37 +16,21 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "Benign": "0",
     "InSitu": "1",
     "Invasive": "2",
     "Normal": "3"
   },
-  "layer_norm_eps": 1e-05,
-  "mlp_ratio": 4.0,
-  "model_type": "swin",
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
   "num_channels": 3,
-  "num_heads": [
-    3,
-    6,
-    12,
-    24
-  ],
-  "num_layers": 4,
-  "out_features": null,
-  "patch_size": 4,
-  "path_norm": true,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4"
-  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
-  "use_absolute_embeddings": false,
-  "window_size": 7
+  "transformers_version": "4.26.1"
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8625,
+    "eval_loss": 0.3848486542701721,
+    "eval_runtime": 3.7207,
+    "eval_samples_per_second": 21.501,
+    "eval_steps_per_second": 2.688
+}

preprocessor_config.json

@@ -3,17 +3,17 @@
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.485,
-    0.456,
-    0.406
+    0.5,
+    0.5,
+    0.5
   ],
-  "image_processor_type": "ViTImageProcessor",
+  "image_processor_type": "ViTFeatureExtractor",
   "image_std": [
-    0.229,
-    0.224,
-    0.225
+    0.5,
+    0.5,
+    0.5
   ],
-  "resample": 3,
+  "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
     "height": 224,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1760ab87d9fc61e87305174b8418a0b5a986c2b6fd39ac873df7328c1c3a870
-size 110401009
+oid sha256:c471f3f0989e3f578bcdbec37e997713a27ef8b2398efc93d21a3f256940abb6
+size 343274861

runs/Mar25_20-32-20_828e34389393/events.out.tfevents.1679776575.828e34389393.24.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40883f21a16b023bed69602ebee2f9bd87c0bd55a6675db96d4c25429f61c600
+size 674

runs/Mar25_20-37-05_828e34389393/1679776639.1080477/events.out.tfevents.1679776639.828e34389393.24.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9a205860d0bdbd776f7b54791f419b88b0f67a91b05b5fd00d32940133e4e2
+size 5680

runs/Mar25_20-37-05_828e34389393/events.out.tfevents.1679776639.828e34389393.24.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f9471cc02c83df7466bd867cf79622312fc155925c0e46c0c1eb445234a44f
+size 5248

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "total_flos": 9.942951223296e+16,
-    "train_loss": 0.5497611045837403,
-    "train_runtime": 245.3761,
-    "train_samples_per_second": 16.302,
-    "train_steps_per_second": 0.285
+    "epoch": 8.0,
+    "total_flos": 7.9543609786368e+16,
+    "train_loss": 0.7504995593002864,
+    "train_runtime": 163.9569,
+    "train_samples_per_second": 19.517,
+    "train_steps_per_second": 0.342
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be429cf83c4a1330a71546e58700666e2294f97073b6f173aa763fc1f9513c0b
+oid sha256:f2e6a475e03a3774b76603130b3a9e691e03326e6f09b5b70955df834acfb80a
 size 3515