End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 datasets:
 - imagefolder

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.7739130434782608,
-    "eval_loss": 0.46259966492652893,
-    "eval_runtime": 12.6959,
-    "eval_samples_per_second": 9.058,
-    "eval_steps_per_second": 1.181,
-    "total_flos": 2.5223642619549696e+17,
-    "train_loss": 0.48874526954278713,
-    "train_runtime": 1194.2371,
-    "train_samples_per_second": 2.726,
-    "train_steps_per_second": 0.343
+    "eval_accuracy": 0.8597560975609756,
+    "eval_loss": 0.3955613076686859,
+    "eval_runtime": 18.361,
+    "eval_samples_per_second": 8.932,
+    "eval_steps_per_second": 1.144,
+    "total_flos": 3.571605801336545e+17,
+    "train_loss": 0.13593495262080224,
+    "train_runtime": 495.489,
+    "train_samples_per_second": 9.334,
+    "train_steps_per_second": 1.171
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.7739130434782608,
-    "eval_loss": 0.46259966492652893,
-    "eval_runtime": 12.6959,
-    "eval_samples_per_second": 9.058,
-    "eval_steps_per_second": 1.181
+    "eval_accuracy": 0.8597560975609756,
+    "eval_loss": 0.3955613076686859,
+    "eval_runtime": 18.361,
+    "eval_samples_per_second": 8.932,
+    "eval_steps_per_second": 1.144
 }

runs/Sep25_15-39-03_Hang-Inspiron16/events.out.tfevents.1727293662.Hang-Inspiron16.37628.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d0bd45c22d9b61fddbd990c61b4ac2afe3219f2750f47943fb4d20ec8b90d7
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "total_flos": 2.5223642619549696e+17,
-    "train_loss": 0.48874526954278713,
-    "train_runtime": 1194.2371,
-    "train_samples_per_second": 2.726,
-    "train_steps_per_second": 0.343
+    "total_flos": 3.571605801336545e+17,
+    "train_loss": 0.13593495262080224,
+    "train_runtime": 495.489,
+    "train_samples_per_second": 9.334,
+    "train_steps_per_second": 1.171
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.46259966492652893,
-  "best_model_checkpoint": "./TransparentBagClassifier/checkpoint-410",
+  "best_metric": 0.3955613076686859,
+  "best_model_checkpoint": "./TransparentBagClassifier/checkpoint-580",
   "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 410,
+  "global_step": 580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -340,18 +340,155 @@
       "eval_steps_per_second": 1.117,
       "step": 410
     },
+    {
+      "epoch": 3.6206896551724137,
+      "grad_norm": 5.8970112800598145,
+      "learning_rate": 5.517241379310345e-06,
+      "loss": 0.4971,
+      "step": 420
+    },
+    {
+      "epoch": 3.706896551724138,
+      "grad_norm": 3.7783031463623047,
+      "learning_rate": 5.172413793103449e-06,
+      "loss": 0.5238,
+      "step": 430
+    },
+    {
+      "epoch": 3.793103448275862,
+      "grad_norm": 4.057668209075928,
+      "learning_rate": 4.8275862068965525e-06,
+      "loss": 0.476,
+      "step": 440
+    },
+    {
+      "epoch": 3.8793103448275863,
+      "grad_norm": 4.21135950088501,
+      "learning_rate": 4.482758620689656e-06,
+      "loss": 0.487,
+      "step": 450
+    },
+    {
+      "epoch": 3.9655172413793105,
+      "grad_norm": 6.149752616882324,
+      "learning_rate": 4.137931034482759e-06,
+      "loss": 0.4749,
+      "step": 460
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7987804878048781,
+      "eval_loss": 0.45718589425086975,
+      "eval_runtime": 18.5139,
+      "eval_samples_per_second": 8.858,
+      "eval_steps_per_second": 1.134,
+      "step": 464
+    },
+    {
+      "epoch": 4.051724137931035,
+      "grad_norm": 5.206491470336914,
+      "learning_rate": 3.793103448275862e-06,
+      "loss": 0.5889,
+      "step": 470
+    },
+    {
+      "epoch": 4.137931034482759,
+      "grad_norm": 4.442436218261719,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 0.5011,
+      "step": 480
+    },
+    {
+      "epoch": 4.224137931034483,
+      "grad_norm": 3.270550012588501,
+      "learning_rate": 3.103448275862069e-06,
+      "loss": 0.4479,
+      "step": 490
+    },
+    {
+      "epoch": 4.310344827586207,
+      "grad_norm": 2.839463710784912,
+      "learning_rate": 2.7586206896551725e-06,
+      "loss": 0.4054,
+      "step": 500
+    },
+    {
+      "epoch": 4.396551724137931,
+      "grad_norm": 3.1818559169769287,
+      "learning_rate": 2.4137931034482762e-06,
+      "loss": 0.3631,
+      "step": 510
+    },
+    {
+      "epoch": 4.482758620689655,
+      "grad_norm": 7.189451217651367,
+      "learning_rate": 2.0689655172413796e-06,
+      "loss": 0.4301,
+      "step": 520
+    },
+    {
+      "epoch": 4.568965517241379,
+      "grad_norm": 3.522141695022583,
+      "learning_rate": 1.724137931034483e-06,
+      "loss": 0.4977,
+      "step": 530
+    },
+    {
+      "epoch": 4.655172413793103,
+      "grad_norm": 2.4986538887023926,
+      "learning_rate": 1.3793103448275862e-06,
+      "loss": 0.381,
+      "step": 540
+    },
+    {
+      "epoch": 4.741379310344827,
+      "grad_norm": 5.762561321258545,
+      "learning_rate": 1.0344827586206898e-06,
+      "loss": 0.4179,
+      "step": 550
+    },
+    {
+      "epoch": 4.827586206896552,
+      "grad_norm": 1.9201445579528809,
+      "learning_rate": 6.896551724137931e-07,
+      "loss": 0.4958,
+      "step": 560
+    },
+    {
+      "epoch": 4.913793103448276,
+      "grad_norm": 5.6399407386779785,
+      "learning_rate": 3.4482758620689656e-07,
+      "loss": 0.4647,
+      "step": 570
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.986402988433838,
+      "learning_rate": 0.0,
+      "loss": 0.4319,
+      "step": 580
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8597560975609756,
+      "eval_loss": 0.3955613076686859,
+      "eval_runtime": 18.7383,
+      "eval_samples_per_second": 8.752,
+      "eval_steps_per_second": 1.121,
+      "step": 580
+    },
     {
       "epoch": 5.0,
-      "step": 410,
-      "total_flos": 2.5223642619549696e+17,
-      "train_loss": 0.48874526954278713,
-      "train_runtime": 1194.2371,
-      "train_samples_per_second": 2.726,
-      "train_steps_per_second": 0.343
+      "step": 580,
+      "total_flos": 3.571605801336545e+17,
+      "train_loss": 0.13593495262080224,
+      "train_runtime": 495.489,
+      "train_samples_per_second": 9.334,
+      "train_steps_per_second": 1.171
     }
   ],
   "logging_steps": 10,
-  "max_steps": 410,
+  "max_steps": 580,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
@@ -367,7 +504,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5223642619549696e+17,
+  "total_flos": 3.571605801336545e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null