End of training

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 datasets:
 - imagefolder

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 0.6095926761627197,
-    "eval_runtime": 0.0372,
-    "eval_samples_per_second": 26.907,
-    "eval_steps_per_second": 26.907,
-    "train_loss": 0.5933201789855957,
-    "train_runtime": 34.8635,
-    "train_samples_per_second": 0.143,
-    "train_steps_per_second": 0.143
+    "eval_accuracy": 0.640625,
+    "eval_loss": 0.6650563478469849,
+    "eval_runtime": 1.0796,
+    "eval_samples_per_second": 59.281,
+    "eval_steps_per_second": 7.41,
+    "train_loss": 0.6482972621917724,
+    "train_runtime": 94.3242,
+    "train_samples_per_second": 0.848,
+    "train_steps_per_second": 0.106
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 0.6095926761627197,
-    "eval_runtime": 0.0372,
-    "eval_samples_per_second": 26.907,
-    "eval_steps_per_second": 26.907
+    "eval_accuracy": 0.640625,
+    "eval_loss": 0.6650563478469849,
+    "eval_runtime": 1.0796,
+    "eval_samples_per_second": 59.281,
+    "eval_steps_per_second": 7.41
 }

runs/Apr03_23-33-41_4da9d9357a4f/events.out.tfevents.1712187341.4da9d9357a4f.2580.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf5e3825af8d41d58f3e54d2c5af77b17da059123bcbf0e8993be7e66e2ac5d
+size 405

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 5.0,
-    "train_loss": 0.5933201789855957,
-    "train_runtime": 34.8635,
-    "train_samples_per_second": 0.143,
-    "train_steps_per_second": 0.143
+    "train_loss": 0.6482972621917724,
+    "train_runtime": 94.3242,
+    "train_samples_per_second": 0.848,
+    "train_steps_per_second": 0.106
 }

trainer_state.json

@@ -1,74 +1,81 @@
 {
-  "best_metric": 0.6095926761627197,
-  "best_model_checkpoint": "./outputs/checkpoint-1",
+  "best_metric": 0.6650563478469849,
+  "best_model_checkpoint": "./outputs/checkpoint-10",
   "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.6095926761627197,
-      "eval_runtime": 0.0508,
-      "eval_samples_per_second": 19.702,
-      "eval_steps_per_second": 19.702,
-      "step": 1
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6905453205108643,
+      "eval_runtime": 27.9364,
+      "eval_samples_per_second": 2.291,
+      "eval_steps_per_second": 0.286,
+      "step": 2
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.6161552667617798,
-      "eval_runtime": 0.0531,
-      "eval_samples_per_second": 18.826,
-      "eval_steps_per_second": 18.826,
-      "step": 2
+      "eval_accuracy": 0.65625,
+      "eval_loss": 0.6797380447387695,
+      "eval_runtime": 1.0941,
+      "eval_samples_per_second": 58.493,
+      "eval_steps_per_second": 7.312,
+      "step": 4
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.6204718947410583,
-      "eval_runtime": 0.0536,
-      "eval_samples_per_second": 18.649,
-      "eval_steps_per_second": 18.649,
-      "step": 3
+      "eval_accuracy": 0.65625,
+      "eval_loss": 0.67192143201828,
+      "eval_runtime": 1.0069,
+      "eval_samples_per_second": 63.562,
+      "eval_steps_per_second": 7.945,
+      "step": 6
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.6235671043395996,
-      "eval_runtime": 0.0594,
-      "eval_samples_per_second": 16.824,
-      "eval_steps_per_second": 16.824,
-      "step": 4
+      "eval_accuracy": 0.65625,
+      "eval_loss": 0.6670976281166077,
+      "eval_runtime": 1.2194,
+      "eval_samples_per_second": 52.486,
+      "eval_steps_per_second": 6.561,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.3951447010040283,
+      "learning_rate": 0.0,
+      "loss": 0.6483,
+      "step": 10
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.6252284646034241,
-      "eval_runtime": 0.0612,
-      "eval_samples_per_second": 16.331,
-      "eval_steps_per_second": 16.331,
-      "step": 5
+      "eval_accuracy": 0.640625,
+      "eval_loss": 0.6650563478469849,
+      "eval_runtime": 1.0203,
+      "eval_samples_per_second": 62.726,
+      "eval_steps_per_second": 7.841,
+      "step": 10
     },
     {
       "epoch": 5.0,
-      "step": 5,
-      "total_flos": 387459948072960.0,
-      "train_loss": 0.5933201789855957,
-      "train_runtime": 34.8635,
-      "train_samples_per_second": 0.143,
-      "train_steps_per_second": 0.143
+      "step": 10,
+      "total_flos": 6199359169167360.0,
+      "train_loss": 0.6482972621917724,
+      "train_runtime": 94.3242,
+      "train_samples_per_second": 0.848,
+      "train_steps_per_second": 0.106
     }
   ],
   "logging_steps": 10,
-  "max_steps": 5,
+  "max_steps": 10,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 387459948072960.0,
+  "total_flos": 6199359169167360.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null