End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7166666666666667
+      value: 0.7333333333333333
 ---
 
 <!-- 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: 0.8134
-- Accuracy: 0.7167
+- Loss: 0.8095
+- Accuracy: 0.7333
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.5833333333333334,
-    "eval_loss": 1.2348047494888306,
-    "eval_runtime": 1.3572,
-    "eval_samples_per_second": 44.207,
-    "eval_steps_per_second": 1.474,
-    "train_loss": 1.2905001163482666,
-    "train_runtime": 87.3836,
-    "train_samples_per_second": 27.465,
-    "train_steps_per_second": 0.229
+    "epoch": 9.23,
+    "eval_accuracy": 0.7333333333333333,
+    "eval_loss": 0.809493362903595,
+    "eval_runtime": 1.3092,
+    "eval_samples_per_second": 45.831,
+    "eval_steps_per_second": 1.528,
+    "train_loss": 0.9177195443047418,
+    "train_runtime": 195.1818,
+    "train_samples_per_second": 62.762,
+    "train_steps_per_second": 0.461
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.5833333333333334,
-    "eval_loss": 1.2348047494888306,
-    "eval_runtime": 1.3572,
-    "eval_samples_per_second": 44.207,
-    "eval_steps_per_second": 1.474
+    "epoch": 9.23,
+    "eval_accuracy": 0.7333333333333333,
+    "eval_loss": 0.809493362903595,
+    "eval_runtime": 1.3092,
+    "eval_samples_per_second": 45.831,
+    "eval_steps_per_second": 1.528
 }

runs/May24_07-57-29_DESKTOP-SKBE9FB/events.out.tfevents.1716559321.DESKTOP-SKBE9FB.10960.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f2af94f1dcafcc46d3cbf3e8dba445c2d7248858c3a96155c7bf846ad6b11d8
+size 405

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 10.0,
-    "train_loss": 1.2905001163482666,
-    "train_runtime": 87.3836,
-    "train_samples_per_second": 27.465,
-    "train_steps_per_second": 0.229
+    "epoch": 9.23,
+    "train_loss": 0.9177195443047418,
+    "train_runtime": 195.1818,
+    "train_samples_per_second": 62.762,
+    "train_steps_per_second": 0.461
 }

trainer_state.json

@@ -1,131 +1,173 @@
 {
-  "best_metric": 0.5833333333333334,
-  "best_model_checkpoint": "vit-base-patch16-224-RU5-10\\checkpoint-16",
-  "epoch": 10.0,
+  "best_metric": 0.7333333333333333,
+  "best_model_checkpoint": "vit-base-patch16-224-RU5-10\\checkpoint-87",
+  "epoch": 9.23076923076923,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.48333333333333334,
-      "eval_loss": 1.371477723121643,
-      "eval_runtime": 1.144,
-      "eval_samples_per_second": 52.447,
-      "eval_steps_per_second": 1.748,
-      "step": 2
+      "epoch": 0.92,
+      "eval_accuracy": 0.4666666666666667,
+      "eval_loss": 1.293900728225708,
+      "eval_runtime": 1.019,
+      "eval_samples_per_second": 58.879,
+      "eval_steps_per_second": 1.963,
+      "step": 9
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.4666666666666667,
-      "eval_loss": 1.3415111303329468,
-      "eval_runtime": 1.0274,
-      "eval_samples_per_second": 58.399,
-      "eval_steps_per_second": 1.947,
-      "step": 4
+      "epoch": 1.03,
+      "learning_rate": 5.1764705882352943e-05,
+      "loss": 1.3501,
+      "step": 10
     },
     {
-      "epoch": 3.0,
-      "eval_accuracy": 0.4666666666666667,
-      "eval_loss": 1.31484854221344,
-      "eval_runtime": 1.0106,
-      "eval_samples_per_second": 59.368,
-      "eval_steps_per_second": 1.979,
-      "step": 6
+      "epoch": 1.95,
+      "eval_accuracy": 0.5833333333333334,
+      "eval_loss": 1.170591115951538,
+      "eval_runtime": 1.0727,
+      "eval_samples_per_second": 55.933,
+      "eval_steps_per_second": 1.864,
+      "step": 19
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.5294117647058826e-05,
+      "loss": 1.2272,
+      "step": 20
+    },
+    {
+      "epoch": 2.97,
+      "eval_accuracy": 0.6333333333333333,
+      "eval_loss": 1.0594052076339722,
+      "eval_runtime": 1.0633,
+      "eval_samples_per_second": 56.426,
+      "eval_steps_per_second": 1.881,
+      "step": 29
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 3.882352941176471e-05,
+      "loss": 1.0941,
+      "step": 30
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.48333333333333334,
-      "eval_loss": 1.2919448614120483,
-      "eval_runtime": 1.0367,
-      "eval_samples_per_second": 57.876,
-      "eval_steps_per_second": 1.929,
-      "step": 8
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.9773460030555725,
+      "eval_runtime": 1.0306,
+      "eval_samples_per_second": 58.221,
+      "eval_steps_per_second": 1.941,
+      "step": 39
     },
     {
-      "epoch": 5.0,
-      "learning_rate": 2.894736842105263e-05,
-      "loss": 1.3369,
-      "step": 10
+      "epoch": 4.1,
+      "learning_rate": 3.235294117647059e-05,
+      "loss": 0.979,
+      "step": 40
     },
     {
-      "epoch": 5.0,
-      "eval_accuracy": 0.48333333333333334,
-      "eval_loss": 1.272611141204834,
-      "eval_runtime": 0.996,
-      "eval_samples_per_second": 60.243,
-      "eval_steps_per_second": 2.008,
-      "step": 10
+      "epoch": 4.92,
+      "eval_accuracy": 0.6833333333333333,
+      "eval_loss": 0.9141623377799988,
+      "eval_runtime": 1.0244,
+      "eval_samples_per_second": 58.572,
+      "eval_steps_per_second": 1.952,
+      "step": 48
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 2.5882352941176472e-05,
+      "loss": 0.8694,
+      "step": 50
+    },
+    {
+      "epoch": 5.95,
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.8568627238273621,
+      "eval_runtime": 1.0443,
+      "eval_samples_per_second": 57.453,
+      "eval_steps_per_second": 1.915,
+      "step": 58
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 1.9411764705882355e-05,
+      "loss": 0.7662,
+      "step": 60
     },
     {
-      "epoch": 6.0,
-      "eval_accuracy": 0.5,
-      "eval_loss": 1.2568950653076172,
-      "eval_runtime": 1.0111,
-      "eval_samples_per_second": 59.34,
-      "eval_steps_per_second": 1.978,
-      "step": 12
+      "epoch": 6.97,
+      "eval_accuracy": 0.6833333333333333,
+      "eval_loss": 0.8363937139511108,
+      "eval_runtime": 1.067,
+      "eval_samples_per_second": 56.233,
+      "eval_steps_per_second": 1.874,
+      "step": 68
     },
     {
-      "epoch": 7.0,
-      "eval_accuracy": 0.55,
-      "eval_loss": 1.24420964717865,
-      "eval_runtime": 1.0116,
-      "eval_samples_per_second": 59.311,
-      "eval_steps_per_second": 1.977,
-      "step": 14
+      "epoch": 7.18,
+      "learning_rate": 1.2941176470588236e-05,
+      "loss": 0.7002,
+      "step": 70
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.5833333333333334,
-      "eval_loss": 1.2348047494888306,
-      "eval_runtime": 1.0128,
-      "eval_samples_per_second": 59.24,
-      "eval_steps_per_second": 1.975,
-      "step": 16
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.8071037530899048,
+      "eval_runtime": 1.0561,
+      "eval_samples_per_second": 56.814,
+      "eval_steps_per_second": 1.894,
+      "step": 78
     },
     {
-      "epoch": 9.0,
-      "eval_accuracy": 0.5833333333333334,
-      "eval_loss": 1.2286779880523682,
-      "eval_runtime": 1.0097,
-      "eval_samples_per_second": 59.423,
-      "eval_steps_per_second": 1.981,
-      "step": 18
+      "epoch": 8.21,
+      "learning_rate": 6.470588235294118e-06,
+      "loss": 0.6443,
+      "step": 80
+    },
+    {
+      "epoch": 8.92,
+      "eval_accuracy": 0.7333333333333333,
+      "eval_loss": 0.809493362903595,
+      "eval_runtime": 1.0229,
+      "eval_samples_per_second": 58.655,
+      "eval_steps_per_second": 1.955,
+      "step": 87
     },
     {
-      "epoch": 10.0,
+      "epoch": 9.23,
       "learning_rate": 0.0,
-      "loss": 1.2441,
-      "step": 20
+      "loss": 0.629,
+      "step": 90
     },
     {
-      "epoch": 10.0,
-      "eval_accuracy": 0.5666666666666667,
-      "eval_loss": 1.2260597944259644,
-      "eval_runtime": 1.032,
-      "eval_samples_per_second": 58.141,
-      "eval_steps_per_second": 1.938,
-      "step": 20
+      "epoch": 9.23,
+      "eval_accuracy": 0.7166666666666667,
+      "eval_loss": 0.8133583664894104,
+      "eval_runtime": 1.0093,
+      "eval_samples_per_second": 59.45,
+      "eval_steps_per_second": 1.982,
+      "step": 90
     },
     {
-      "epoch": 10.0,
-      "step": 20,
-      "total_flos": 1.859841088487424e+17,
-      "train_loss": 1.2905001163482666,
-      "train_runtime": 87.3836,
-      "train_samples_per_second": 27.465,
-      "train_steps_per_second": 0.229
+      "epoch": 9.23,
+      "step": 90,
+      "total_flos": 8.766825930857595e+17,
+      "train_loss": 0.9177195443047418,
+      "train_runtime": 195.1818,
+      "train_samples_per_second": 62.762,
+      "train_steps_per_second": 0.461
     }
   ],
   "logging_steps": 10,
-  "max_steps": 20,
+  "max_steps": 90,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 1.859841088487424e+17,
+  "total_flos": 8.766825930857595e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null