End of training

README.md

@@ -24,13 +24,13 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9438202247191011
+      value: 0.949438202247191
     - name: Recall
       type: recall
-      value: 0.941747572815534
+      value: 0.9514563106796117
     - name: Precision
       type: precision
-      value: 0.9603960396039604
+      value: 0.9607843137254902
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Visual-Attention-Network/van-tiny](https://huggingface.co/Visual-Attention-Network/van-tiny) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1692
-- Accuracy: 0.9438
-- F1 Score: 0.9510
-- Recall: 0.9417
-- Precision: 0.9604
+- Loss: 0.1802
+- Accuracy: 0.9494
+- F1 Score: 0.9561
+- Recall: 0.9515
+- Precision: 0.9608
 
 ## Model description
 

all_results.json

@@ -1,13 +1,16 @@
 {
     "epoch": 2.88,
-    "eval_accuracy": 0.6404494382022472,
-    "eval_loss": 0.580851674079895,
-    "eval_runtime": 1.5636,
-    "eval_samples_per_second": 113.843,
-    "eval_steps_per_second": 3.837,
+    "eval_accuracy": 0.949438202247191,
+    "eval_f1_score": 0.9560975609756097,
+    "eval_loss": 0.18015821278095245,
+    "eval_precision": 0.9607843137254902,
+    "eval_recall": 0.9514563106796117,
+    "eval_runtime": 1.0836,
+    "eval_samples_per_second": 164.273,
+    "eval_steps_per_second": 5.537,
     "total_flos": 2.086337325249331e+16,
-    "train_loss": 0.6542094416088529,
-    "train_runtime": 72.0498,
-    "train_samples_per_second": 66.329,
-    "train_steps_per_second": 0.5
+    "train_loss": 0.2572544482019212,
+    "train_runtime": 70.0705,
+    "train_samples_per_second": 68.203,
+    "train_steps_per_second": 0.514
 }

eval_results.json

@@ -1,8 +1,11 @@
 {
     "epoch": 2.88,
-    "eval_accuracy": 0.6404494382022472,
-    "eval_loss": 0.580851674079895,
-    "eval_runtime": 1.5636,
-    "eval_samples_per_second": 113.843,
-    "eval_steps_per_second": 3.837
+    "eval_accuracy": 0.949438202247191,
+    "eval_f1_score": 0.9560975609756097,
+    "eval_loss": 0.18015821278095245,
+    "eval_precision": 0.9607843137254902,
+    "eval_recall": 0.9514563106796117,
+    "eval_runtime": 1.0836,
+    "eval_samples_per_second": 164.273,
+    "eval_steps_per_second": 5.537
 }

runs/Dec25_02-59-05_3c03b7532490/events.out.tfevents.1703474232.3c03b7532490.2403.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e791d56f270ec13fdb2b1b96b5f3f3c18173189f92a29640931a99ce0ddb0d3
+size 557

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.88,
     "total_flos": 2.086337325249331e+16,
-    "train_loss": 0.6542094416088529,
-    "train_runtime": 72.0498,
-    "train_samples_per_second": 66.329,
-    "train_steps_per_second": 0.5
+    "train_loss": 0.2572544482019212,
+    "train_runtime": 70.0705,
+    "train_samples_per_second": 68.203,
+    "train_steps_per_second": 0.514
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6404494382022472,
-  "best_model_checkpoint": "teacher-status-van-tiny-256/checkpoint-36",
+  "best_metric": 0.949438202247191,
+  "best_model_checkpoint": "teacher-status-van-tiny-256/checkpoint-12",
   "epoch": 2.88,
   "eval_steps": 500,
   "global_step": 36,
@@ -11,56 +11,65 @@
     {
       "epoch": 0.8,
       "learning_rate": 4.0625000000000005e-05,
-      "loss": 0.6898,
+      "loss": 0.1511,
       "step": 10
     },
     {
       "epoch": 0.96,
-      "eval_accuracy": 0.5955056179775281,
-      "eval_loss": 0.6677632331848145,
-      "eval_runtime": 1.2893,
-      "eval_samples_per_second": 138.058,
-      "eval_steps_per_second": 4.654,
+      "eval_accuracy": 0.949438202247191,
+      "eval_f1_score": 0.9560975609756097,
+      "eval_loss": 0.18015821278095245,
+      "eval_precision": 0.9607843137254902,
+      "eval_recall": 0.9514563106796117,
+      "eval_runtime": 1.3097,
+      "eval_samples_per_second": 135.904,
+      "eval_steps_per_second": 4.581,
       "step": 12
     },
     {
       "epoch": 1.6,
       "learning_rate": 2.5e-05,
-      "loss": 0.6661,
+      "loss": 0.2643,
       "step": 20
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6235955056179775,
-      "eval_loss": 0.6087228059768677,
-      "eval_runtime": 0.9989,
-      "eval_samples_per_second": 178.194,
-      "eval_steps_per_second": 6.007,
+      "eval_accuracy": 0.949438202247191,
+      "eval_f1_score": 0.9556650246305418,
+      "eval_loss": 0.16739808022975922,
+      "eval_precision": 0.97,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 1.1345,
+      "eval_samples_per_second": 156.899,
+      "eval_steps_per_second": 5.289,
       "step": 25
     },
     {
       "epoch": 2.4,
       "learning_rate": 9.375000000000001e-06,
-      "loss": 0.6328,
+      "loss": 0.3159,
       "step": 30
     },
     {
       "epoch": 2.88,
-      "eval_accuracy": 0.6404494382022472,
-      "eval_loss": 0.580851674079895,
-      "eval_runtime": 1.2968,
-      "eval_samples_per_second": 137.257,
-      "eval_steps_per_second": 4.627,
+      "eval_accuracy": 0.9438202247191011,
+      "eval_f1_score": 0.9509803921568628,
+      "eval_loss": 0.16916657984256744,
+      "eval_precision": 0.9603960396039604,
+      "eval_recall": 0.941747572815534,
+      "eval_runtime": 1.0079,
+      "eval_samples_per_second": 176.605,
+      "eval_steps_per_second": 5.953,
       "step": 36
     },
     {
       "epoch": 2.88,
       "step": 36,
       "total_flos": 2.086337325249331e+16,
-      "train_loss": 0.6542094416088529,
-      "train_runtime": 72.0498,
-      "train_samples_per_second": 66.329,
-      "train_steps_per_second": 0.5
+      "train_loss": 0.2572544482019212,
+      "train_runtime": 70.0705,
+      "train_samples_per_second": 68.203,
+      "train_steps_per_second": 0.514
     }
   ],
   "logging_steps": 10,