End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7666666666666667
+      value: 0.8333333333333334
 ---
 
 <!-- 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: 0.6368
-- Accuracy: 0.7667
+- Loss: 0.5903
+- Accuracy: 0.8333
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 9.87,
+    "eval_accuracy": 0.8333333333333334,
+    "eval_loss": 0.5903454422950745,
+    "eval_runtime": 1.5404,
+    "eval_samples_per_second": 38.951,
+    "eval_steps_per_second": 1.298,
+    "train_loss": 0.5296587021727311,
+    "train_runtime": 382.3327,
+    "train_samples_per_second": 64.08,
+    "train_steps_per_second": 0.497
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.87,
+    "eval_accuracy": 0.8333333333333334,
+    "eval_loss": 0.5903454422950745,
+    "eval_runtime": 1.5404,
+    "eval_samples_per_second": 38.951,
+    "eval_steps_per_second": 1.298
+}

runs/May23_20-13-11_DESKTOP-SKBE9FB/events.out.tfevents.1716517472.DESKTOP-SKBE9FB.10384.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af4171d33973d32537194096b3d21498f75c66e7383e8cd3f74701e78cbfb05
+size 411

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 9.87,
+    "train_loss": 0.5296587021727311,
+    "train_runtime": 382.3327,
+    "train_samples_per_second": 64.08,
+    "train_steps_per_second": 0.497
+}

trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_metric": 0.8333333333333334,
+  "best_model_checkpoint": "vit-base-patch16-224-RU4-10\\checkpoint-115",
+  "epoch": 9.87012987012987,
+  "eval_steps": 500,
+  "global_step": 190,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.52,
+      "learning_rate": 5.5e-05,
+      "loss": 1.37,
+      "step": 10
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.6166666666666667,
+      "eval_loss": 1.1940264701843262,
+      "eval_runtime": 1.217,
+      "eval_samples_per_second": 49.302,
+      "eval_steps_per_second": 1.643,
+      "step": 19
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 5.1944444444444446e-05,
+      "loss": 1.2407,
+      "step": 20
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 1.1393,
+      "step": 30
+    },
+    {
+      "epoch": 1.97,
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.9230659604072571,
+      "eval_runtime": 1.0004,
+      "eval_samples_per_second": 59.978,
+      "eval_steps_per_second": 1.999,
+      "step": 38
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 0.9532,
+      "step": 40
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.277777777777778e-05,
+      "loss": 0.8115,
+      "step": 50
+    },
+    {
+      "epoch": 2.96,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_loss": 0.7923756837844849,
+      "eval_runtime": 0.9942,
+      "eval_samples_per_second": 60.348,
+      "eval_steps_per_second": 2.012,
+      "step": 57
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 3.972222222222222e-05,
+      "loss": 0.6693,
+      "step": 60
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.5507,
+      "step": 70
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.6691194176673889,
+      "eval_runtime": 1.017,
+      "eval_samples_per_second": 59.0,
+      "eval_steps_per_second": 1.967,
+      "step": 77
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 3.3611111111111116e-05,
+      "loss": 0.473,
+      "step": 80
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.4093,
+      "step": 90
+    },
+    {
+      "epoch": 4.99,
+      "eval_accuracy": 0.8166666666666667,
+      "eval_loss": 0.6462448239326477,
+      "eval_runtime": 0.9981,
+      "eval_samples_per_second": 60.113,
+      "eval_steps_per_second": 2.004,
+      "step": 96
+    },
+    {
+      "epoch": 5.19,
+      "learning_rate": 2.75e-05,
+      "loss": 0.4008,
+      "step": 100
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 0.2869,
+      "step": 110
+    },
+    {
+      "epoch": 5.97,
+      "eval_accuracy": 0.8333333333333334,
+      "eval_loss": 0.5903454422950745,
+      "eval_runtime": 1.0618,
+      "eval_samples_per_second": 56.506,
+      "eval_steps_per_second": 1.884,
+      "step": 115
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 2.138888888888889e-05,
+      "loss": 0.2562,
+      "step": 120
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.2347,
+      "step": 130
+    },
+    {
+      "epoch": 6.96,
+      "eval_accuracy": 0.7333333333333333,
+      "eval_loss": 0.7096327543258667,
+      "eval_runtime": 1.0505,
+      "eval_samples_per_second": 57.116,
+      "eval_steps_per_second": 1.904,
+      "step": 134
+    },
+    {
+      "epoch": 7.27,
+      "learning_rate": 1.527777777777778e-05,
+      "loss": 0.266,
+      "step": 140
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 1.2222222222222222e-05,
+      "loss": 0.2148,
+      "step": 150
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7833333333333333,
+      "eval_loss": 0.636201024055481,
+      "eval_runtime": 1.1226,
+      "eval_samples_per_second": 53.447,
+      "eval_steps_per_second": 1.782,
+      "step": 154
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.1998,
+      "step": 160
+    },
+    {
+      "epoch": 8.83,
+      "learning_rate": 6.111111111111111e-06,
+      "loss": 0.1868,
+      "step": 170
+    },
+    {
+      "epoch": 8.99,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.6496174335479736,
+      "eval_runtime": 0.9902,
+      "eval_samples_per_second": 60.595,
+      "eval_steps_per_second": 2.02,
+      "step": 173
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 3.0555555555555556e-06,
+      "loss": 0.2031,
+      "step": 180
+    },
+    {
+      "epoch": 9.87,
+      "learning_rate": 0.0,
+      "loss": 0.1977,
+      "step": 190
+    },
+    {
+      "epoch": 9.87,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_loss": 0.6367517113685608,
+      "eval_runtime": 1.0025,
+      "eval_samples_per_second": 59.849,
+      "eval_steps_per_second": 1.995,
+      "step": 190
+    },
+    {
+      "epoch": 9.87,
+      "step": 190,
+      "total_flos": 1.8748748039526973e+18,
+      "train_loss": 0.5296587021727311,
+      "train_runtime": 382.3327,
+      "train_samples_per_second": 64.08,
+      "train_steps_per_second": 0.497
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 190,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.8748748039526973e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}