End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8
+      value: 0.8105263157894737
 ---
 
 <!-- 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 [facebook/vit-msn-small](https://huggingface.co/facebook/vit-msn-small) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6649
-- Accuracy: 0.8
+- Loss: 0.6607
+- Accuracy: 0.8105
 
 ## Model description
 

all_results.json

@@ -1,8 +1,13 @@
 {
-    "epoch": 2.8085106382978724,
-    "total_flos": 8.251222819140403e+16,
-    "train_loss": 1.6961536913207083,
-    "train_runtime": 198.8355,
-    "train_samples_per_second": 22.632,
-    "train_steps_per_second": 0.166
+    "epoch": 5.617021276595745,
+    "eval_accuracy": 0.8105263157894737,
+    "eval_loss": 0.6607011556625366,
+    "eval_runtime": 5.5445,
+    "eval_samples_per_second": 34.268,
+    "eval_steps_per_second": 1.082,
+    "total_flos": 1.6494617153632666e+17,
+    "train_loss": 0.5514849839788495,
+    "train_runtime": 364.4981,
+    "train_samples_per_second": 24.691,
+    "train_steps_per_second": 0.181
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.617021276595745,
+    "eval_accuracy": 0.8105263157894737,
+    "eval_loss": 0.6607011556625366,
+    "eval_runtime": 5.5445,
+    "eval_samples_per_second": 34.268,
+    "eval_steps_per_second": 1.082
+}

runs/Apr28_18-05-30_187a08b29384/events.out.tfevents.1714327943.187a08b29384.340.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071518b9cdf1515c9e854a232592e8edeed177e1c208115014388392409ae69c
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.8085106382978724,
-    "total_flos": 8.251222819140403e+16,
-    "train_loss": 1.6961536913207083,
-    "train_runtime": 198.8355,
-    "train_samples_per_second": 22.632,
-    "train_steps_per_second": 0.166
+    "epoch": 5.617021276595745,
+    "total_flos": 1.6494617153632666e+17,
+    "train_loss": 0.5514849839788495,
+    "train_runtime": 364.4981,
+    "train_samples_per_second": 24.691,
+    "train_steps_per_second": 0.181
 }

trainer_state.json

@@ -1,77 +1,125 @@
 {
-  "best_metric": 0.5684210526315789,
-  "best_model_checkpoint": "vit-msn-small-finetuned-eurosat/checkpoint-33",
-  "epoch": 2.8085106382978724,
+  "best_metric": 0.8105263157894737,
+  "best_model_checkpoint": "vit-msn-small-finetuned-eurosat/checkpoint-58",
+  "epoch": 5.617021276595745,
   "eval_steps": 500,
-  "global_step": 33,
+  "global_step": 66,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.851063829787234,
-      "grad_norm": 7.806485652923584,
-      "learning_rate": 3.965517241379311e-05,
-      "loss": 2.2554,
+      "grad_norm": 16.84075164794922,
+      "learning_rate": 0.0001898305084745763,
+      "loss": 1.115,
       "step": 10
     },
     {
       "epoch": 0.9361702127659575,
-      "eval_accuracy": 0.4052631578947368,
-      "eval_loss": 1.821715235710144,
-      "eval_runtime": 5.616,
-      "eval_samples_per_second": 33.832,
+      "eval_accuracy": 0.6526315789473685,
+      "eval_loss": 1.039728045463562,
+      "eval_runtime": 5.6197,
+      "eval_samples_per_second": 33.81,
       "eval_steps_per_second": 1.068,
       "step": 11
     },
     {
       "epoch": 1.702127659574468,
-      "grad_norm": 9.02415657043457,
-      "learning_rate": 2.2413793103448276e-05,
-      "loss": 1.6448,
+      "grad_norm": 11.648308753967285,
+      "learning_rate": 0.00015593220338983051,
+      "loss": 0.8536,
       "step": 20
     },
     {
       "epoch": 1.9574468085106385,
-      "eval_accuracy": 0.48947368421052634,
-      "eval_loss": 1.4679394960403442,
-      "eval_runtime": 5.5389,
-      "eval_samples_per_second": 34.303,
-      "eval_steps_per_second": 1.083,
+      "eval_accuracy": 0.7578947368421053,
+      "eval_loss": 0.7698105573654175,
+      "eval_runtime": 6.4598,
+      "eval_samples_per_second": 29.413,
+      "eval_steps_per_second": 0.929,
       "step": 23
     },
     {
       "epoch": 2.5531914893617023,
-      "grad_norm": 7.699336051940918,
-      "learning_rate": 5.172413793103448e-06,
-      "loss": 1.3339,
+      "grad_norm": 10.502930641174316,
+      "learning_rate": 0.00012203389830508477,
+      "loss": 0.5677,
       "step": 30
     },
     {
-      "epoch": 2.8085106382978724,
-      "eval_accuracy": 0.5684210526315789,
-      "eval_loss": 1.3136721849441528,
-      "eval_runtime": 6.6132,
-      "eval_samples_per_second": 28.73,
-      "eval_steps_per_second": 0.907,
-      "step": 33
+      "epoch": 2.978723404255319,
+      "eval_accuracy": 0.7894736842105263,
+      "eval_loss": 0.7199588418006897,
+      "eval_runtime": 6.391,
+      "eval_samples_per_second": 29.729,
+      "eval_steps_per_second": 0.939,
+      "step": 35
     },
     {
-      "epoch": 2.8085106382978724,
-      "step": 33,
-      "total_flos": 8.251222819140403e+16,
-      "train_loss": 1.6961536913207083,
-      "train_runtime": 198.8355,
-      "train_samples_per_second": 22.632,
-      "train_steps_per_second": 0.166
+      "epoch": 3.404255319148936,
+      "grad_norm": 11.857769012451172,
+      "learning_rate": 8.813559322033899e-05,
+      "loss": 0.419,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7842105263157895,
+      "eval_loss": 0.7286169528961182,
+      "eval_runtime": 6.4892,
+      "eval_samples_per_second": 29.279,
+      "eval_steps_per_second": 0.925,
+      "step": 47
+    },
+    {
+      "epoch": 4.25531914893617,
+      "grad_norm": 8.081114768981934,
+      "learning_rate": 5.423728813559322e-05,
+      "loss": 0.3365,
+      "step": 50
+    },
+    {
+      "epoch": 4.9361702127659575,
+      "eval_accuracy": 0.8105263157894737,
+      "eval_loss": 0.6607011556625366,
+      "eval_runtime": 5.5742,
+      "eval_samples_per_second": 34.086,
+      "eval_steps_per_second": 1.076,
+      "step": 58
+    },
+    {
+      "epoch": 5.1063829787234045,
+      "grad_norm": 6.424224376678467,
+      "learning_rate": 2.033898305084746e-05,
+      "loss": 0.2317,
+      "step": 60
+    },
+    {
+      "epoch": 5.617021276595745,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.6648939251899719,
+      "eval_runtime": 6.1483,
+      "eval_samples_per_second": 30.903,
+      "eval_steps_per_second": 0.976,
+      "step": 66
+    },
+    {
+      "epoch": 5.617021276595745,
+      "step": 66,
+      "total_flos": 1.6494617153632666e+17,
+      "train_loss": 0.5514849839788495,
+      "train_runtime": 364.4981,
+      "train_samples_per_second": 24.691,
+      "train_steps_per_second": 0.181
     }
   ],
   "logging_steps": 10,
-  "max_steps": 33,
+  "max_steps": 66,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 6,
   "save_steps": 500,
-  "total_flos": 8.251222819140403e+16,
+  "total_flos": 1.6494617153632666e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null