Training Completed!

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9176470588235294
+      value: 0.8941176470588236
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3352
-- Accuracy: 0.9176
+- Loss: 0.4515
+- Accuracy: 0.8941
 
 ## Model description
 
@@ -58,10 +58,13 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.0236        | 5.5556 | 100  | 0.4515          | 0.8941   |
 
 
 ### Framework versions

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.9176470588235294,
-    "eval_loss": 0.33524250984191895,
-    "eval_runtime": 2.2283,
-    "eval_samples_per_second": 38.145,
-    "eval_steps_per_second": 4.936,
-    "total_flos": 1.104270749148672e+17,
-    "train_loss": 0.3459944127334489,
-    "train_runtime": 65.8041,
-    "train_samples_per_second": 21.655,
-    "train_steps_per_second": 1.368
+    "epoch": 10.0,
+    "eval_accuracy": 0.8941176470588236,
+    "eval_loss": 0.4515226483345032,
+    "eval_runtime": 1.8149,
+    "eval_samples_per_second": 46.836,
+    "eval_steps_per_second": 6.061,
+    "total_flos": 2.208541498297344e+17,
+    "train_loss": 0.17066083699982199,
+    "train_runtime": 133.3595,
+    "train_samples_per_second": 21.371,
+    "train_steps_per_second": 1.35
 }

config.json

@@ -9,17 +9,17 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "normal",
-    "1": "Cancer",
-    "2": "Benign"
+    "0": "bengin",
+    "1": "cancer",
+    "2": "normal"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "Benign": 2,
-    "Cancer": 1,
-    "normal": 0
+    "bengin": 0,
+    "cancer": 1,
+    "normal": 2
   },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.9176470588235294,
-    "eval_loss": 0.33524250984191895,
-    "eval_runtime": 2.2283,
-    "eval_samples_per_second": 38.145,
-    "eval_steps_per_second": 4.936
+    "epoch": 10.0,
+    "eval_accuracy": 0.8941176470588236,
+    "eval_loss": 0.4515226483345032,
+    "eval_runtime": 1.8149,
+    "eval_samples_per_second": 46.836,
+    "eval_steps_per_second": 6.061
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7763f5afe02e29f88388f4d07a5b5b5bd4cd5110f49ff485033ddd04a27b9c18
+oid sha256:abb8cd2dafb6e3adda18265ed82f7d65d75ead47ddecbc89d2abdbbb4e78d1fb
 size 343227052

runs/May10_19-31-52_b9d6e8b22a3b/events.out.tfevents.1715369517.b9d6e8b22a3b.3702.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba02c8a3d3c8f9cc1584242152a43062f5fe2cdb0332340c5c69c438fcc7df46
+size 7833

runs/May10_19-31-52_b9d6e8b22a3b/events.out.tfevents.1715369631.b9d6e8b22a3b.3702.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47039229f259fd0b954f3be9b198b8af011516e2c45b2cc31486d865b489aaf6
+size 405

runs/May10_19-34-04_b9d6e8b22a3b/events.out.tfevents.1715369648.b9d6e8b22a3b.3702.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09146dcb9bed8c9e93652e304fe9b1c01660b8954ef25753575a7afba0a64194
+size 13627

runs/May10_19-34-04_b9d6e8b22a3b/events.out.tfevents.1715369921.b9d6e8b22a3b.3702.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d53451e5f353d6f08925bd8ddb6bccf77b42434c1126089e2b1c1f3bf63697d1
+size 411

runs/May10_19-53-24_b9d6e8b22a3b/events.out.tfevents.1715370809.b9d6e8b22a3b.3702.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a013409bff29a7946cf28334961aec0027213ae8ed1c081d83a67b9e18e03a
+size 9106

runs/May10_19-53-24_b9d6e8b22a3b/events.out.tfevents.1715371068.b9d6e8b22a3b.3702.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374ed9c830b4fcc1f41e08d757239be6c80426e2dbb10edcbca07628498dd4bf
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "total_flos": 1.104270749148672e+17,
-    "train_loss": 0.3459944127334489,
-    "train_runtime": 65.8041,
-    "train_samples_per_second": 21.655,
-    "train_steps_per_second": 1.368
+    "epoch": 10.0,
+    "total_flos": 2.208541498297344e+17,
+    "train_loss": 0.17066083699982199,
+    "train_runtime": 133.3595,
+    "train_samples_per_second": 21.371,
+    "train_steps_per_second": 1.35
 }

trainer_state.json

@@ -1,92 +1,164 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "best_metric": 0.4515226483345032,
+  "best_model_checkpoint": "./MRI_vit/checkpoint-100",
+  "epoch": 10.0,
   "eval_steps": 100,
-  "global_step": 90,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.5555555555555556,
-      "grad_norm": 10.430541038513184,
-      "learning_rate": 0.00017777777777777779,
-      "loss": 1.1321,
+      "grad_norm": 7.522036552429199,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 0.974,
       "step": 10
     },
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 3.6575100421905518,
-      "learning_rate": 0.00015555555555555556,
-      "loss": 0.6351,
+      "grad_norm": 2.3464157581329346,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.6625,
       "step": 20
     },
     {
       "epoch": 1.6666666666666665,
-      "grad_norm": 4.778464317321777,
-      "learning_rate": 0.00013333333333333334,
-      "loss": 0.4087,
+      "grad_norm": 9.9130220413208,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.4228,
       "step": 30
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 7.901824951171875,
-      "learning_rate": 0.00011111111111111112,
-      "loss": 0.3833,
+      "grad_norm": 9.101266860961914,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.4918,
       "step": 40
     },
     {
       "epoch": 2.7777777777777777,
-      "grad_norm": 1.8277825117111206,
-      "learning_rate": 8.888888888888889e-05,
-      "loss": 0.2095,
+      "grad_norm": 7.912335395812988,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 0.1294,
       "step": 50
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 6.244271755218506,
-      "learning_rate": 6.666666666666667e-05,
-      "loss": 0.2673,
+      "grad_norm": 1.002270221710205,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.1837,
       "step": 60
     },
     {
       "epoch": 3.888888888888889,
-      "grad_norm": 3.88458251953125,
-      "learning_rate": 4.4444444444444447e-05,
-      "loss": 0.0374,
+      "grad_norm": 0.04989054054021835,
+      "learning_rate": 0.00012222222222222224,
+      "loss": 0.0559,
       "step": 70
     },
     {
       "epoch": 4.444444444444445,
-      "grad_norm": 0.08572948724031448,
-      "learning_rate": 2.2222222222222223e-05,
-      "loss": 0.0341,
+      "grad_norm": 7.236814498901367,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.0396,
       "step": 80
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.26313289999961853,
-      "learning_rate": 0.0,
-      "loss": 0.0065,
+      "grad_norm": 5.21504545211792,
+      "learning_rate": 0.0001,
+      "loss": 0.0791,
       "step": 90
     },
     {
-      "epoch": 5.0,
-      "step": 90,
-      "total_flos": 1.104270749148672e+17,
-      "train_loss": 0.3459944127334489,
-      "train_runtime": 65.8041,
-      "train_samples_per_second": 21.655,
-      "train_steps_per_second": 1.368
+      "epoch": 5.555555555555555,
+      "grad_norm": 0.02051878347992897,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.0236,
+      "step": 100
+    },
+    {
+      "epoch": 5.555555555555555,
+      "eval_accuracy": 0.8941176470588236,
+      "eval_loss": 0.4515226483345032,
+      "eval_runtime": 1.7177,
+      "eval_samples_per_second": 49.485,
+      "eval_steps_per_second": 6.404,
+      "step": 100
+    },
+    {
+      "epoch": 6.111111111111111,
+      "grad_norm": 0.013602614402770996,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 0.0038,
+      "step": 110
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.006600651424378157,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.0013,
+      "step": 120
+    },
+    {
+      "epoch": 7.222222222222222,
+      "grad_norm": 0.004217671230435371,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.001,
+      "step": 130
+    },
+    {
+      "epoch": 7.777777777777778,
+      "grad_norm": 0.009464713744819164,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.0019,
+      "step": 140
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 0.008202188648283482,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0003,
+      "step": 150
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.019373826682567596,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.0004,
+      "step": 160
+    },
+    {
+      "epoch": 9.444444444444445,
+      "grad_norm": 0.004279292654246092,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.0004,
+      "step": 170
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.004037588369101286,
+      "learning_rate": 0.0,
+      "loss": 0.0004,
+      "step": 180
+    },
+    {
+      "epoch": 10.0,
+      "step": 180,
+      "total_flos": 2.208541498297344e+17,
+      "train_loss": 0.17066083699982199,
+      "train_runtime": 133.3595,
+      "train_samples_per_second": 21.371,
+      "train_steps_per_second": 1.35
     }
   ],
   "logging_steps": 10,
-  "max_steps": 90,
+  "max_steps": 180,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 10,
   "save_steps": 100,
-  "total_flos": 1.104270749148672e+17,
+  "total_flos": 2.208541498297344e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d2c494673091293489e3472ca6d10994f0227f778a0da413f2755d2ceb0f2e
+oid sha256:b987baef7b866740d84e200bd5fa07044adfb2ec3c219e723726032bd8426f73
 size 4984