Model save

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 6.0,
-    "eval_accuracy": 0.7,
-    "eval_loss": 0.7854475975036621,
-    "eval_runtime": 5.1812,
-    "eval_samples_per_second": 15.44,
-    "eval_steps_per_second": 1.93,
-    "total_flos": 3.7602497396736e+16,
-    "train_loss": 0.9928933892931256,
-    "train_runtime": 194.8808,
-    "train_samples_per_second": 12.315,
-    "train_steps_per_second": 0.216
+    "epoch": 5.0,
+    "eval_accuracy": 0.65,
+    "eval_loss": 0.8501228094100952,
+    "eval_runtime": 4.6045,
+    "eval_samples_per_second": 17.374,
+    "eval_steps_per_second": 2.172,
+    "total_flos": 3.133541449728e+16,
+    "train_loss": 1.137827001299177,
+    "train_runtime": 183.2231,
+    "train_samples_per_second": 10.916,
+    "train_steps_per_second": 0.191
 }

config.json

@@ -1,32 +1,13 @@
 {
-  "_name_or_path": "nvidia/mit-b0",
+  "_name_or_path": "tcvrishank/histo_train_vit",
   "architectures": [
-    "SegformerForImageClassification"
+    "ViTForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "classifier_dropout_prob": 0.1,
-  "decoder_hidden_size": 256,
-  "depths": [
-    2,
-    2,
-    2,
-    2
-  ],
-  "downsampling_rates": [
-    1,
-    4,
-    8,
-    16
-  ],
-  "drop_path_rate": 0.1,
+  "encoder_stride": 16,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_sizes": [
-    32,
-    64,
-    160,
-    256
-  ],
+  "hidden_size": 768,
   "id2label": {
     "0": "Benign",
     "1": "InSitu",
@@ -35,49 +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-06,
-  "mlp_ratios": [
-    4,
-    4,
-    4,
-    4
-  ],
-  "model_type": "segformer",
-  "num_attention_heads": [
-    1,
-    2,
-    5,
-    8
-  ],
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
   "num_channels": 3,
-  "num_encoder_blocks": 4,
-  "patch_sizes": [
-    7,
-    3,
-    3,
-    3
-  ],
+  "num_hidden_layers": 12,
+  "patch_size": 16,
   "problem_type": "single_label_classification",
-  "reshape_last_stage": true,
-  "semantic_loss_ignore_index": 255,
-  "sr_ratios": [
-    8,
-    4,
-    2,
-    1
-  ],
-  "strides": [
-    4,
-    2,
-    2,
-    2
-  ],
+  "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.26.1"
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 6.0,
-    "eval_accuracy": 0.7,
-    "eval_loss": 0.7854475975036621,
-    "eval_runtime": 5.1812,
-    "eval_samples_per_second": 15.44,
-    "eval_steps_per_second": 1.93
+    "epoch": 5.0,
+    "eval_accuracy": 0.65,
+    "eval_loss": 0.8501228094100952,
+    "eval_runtime": 4.6045,
+    "eval_samples_per_second": 17.374,
+    "eval_steps_per_second": 2.172
 }

preprocessor_config.json

@@ -1,23 +1,22 @@
 {
   "do_normalize": true,
-  "do_reduce_labels": false,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.485,
-    0.456,
-    0.406
+    0.5,
+    0.5,
+    0.5
   ],
-  "image_processor_type": "SegformerImageProcessor",
+  "image_processor_type": "ViTFeatureExtractor",
   "image_std": [
-    0.229,
-    0.224,
-    0.225
+    0.5,
+    0.5,
+    0.5
   ],
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "height": 512,
-    "width": 512
+    "height": 224,
+    "width": 224
   }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736e338ae6c175c9a1402bafd68eccc46490a4360a8608272c2f5c1ce16af6cd
-size 13348117
+oid sha256:52b81b9436f28f788ea36ab0eaab1e7c2e9cc6cd58230462018bb07f2cd552fc
+size 343274861

runs/Mar25_20-19-42_828e34389393/events.out.tfevents.1679775793.828e34389393.24.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b53d511d277e33b77011a080cd66205daacc4df39a897133853c3b6c5a562c
+size 357

runs/Mar25_20-23-45_828e34389393/1679775836.194679/events.out.tfevents.1679775836.828e34389393.24.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ea88d265ba380c7a2d534808d465ca2b80b0498182402c250acb2fc892453b
+size 5695

runs/Mar25_20-23-45_828e34389393/events.out.tfevents.1679775836.828e34389393.24.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81a546f1f9c906448e5755520b6567f3016f4dcf6ba6432a82e5270aad4a0ea
+size 5109

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 6.0,
-    "total_flos": 3.7602497396736e+16,
-    "train_loss": 0.9928933892931256,
-    "train_runtime": 194.8808,
-    "train_samples_per_second": 12.315,
-    "train_steps_per_second": 0.216
+    "epoch": 5.0,
+    "total_flos": 3.133541449728e+16,
+    "train_loss": 1.137827001299177,
+    "train_runtime": 183.2231,
+    "train_samples_per_second": 10.916,
+    "train_steps_per_second": 0.191
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f35b6227592223779cd4c7154aa2d14de68fb55568cdf87e7e82a09b893231
+oid sha256:51c784bcfe84093acfb329ab8cdd8aa46a6c4c20bd94e51587d2a6380e8a07ff
 size 3515