End of training

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 2.67,
-    "eval_accuracy": 0.25,
-    "eval_loss": 1.3859087228775024,
-    "eval_runtime": 16.2955,
-    "eval_samples_per_second": 2.455,
-    "eval_steps_per_second": 0.123,
-    "total_flos": 2.038954042589184e+16,
-    "train_loss": 1.3799550731976826,
-    "train_runtime": 884.0465,
-    "train_samples_per_second": 1.222,
-    "train_steps_per_second": 0.014
+    "epoch": 2.96,
+    "eval_accuracy": 0.4935064935064935,
+    "eval_loss": 1.343481421470642,
+    "eval_runtime": 34.4739,
+    "eval_samples_per_second": 4.467,
+    "eval_steps_per_second": 0.232,
+    "total_flos": 8.65705903915991e+16,
+    "train_loss": 1.3479154296949798,
+    "train_runtime": 3214.4197,
+    "train_samples_per_second": 1.286,
+    "train_steps_per_second": 0.016
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.67,
-    "eval_accuracy": 0.25,
-    "eval_loss": 1.3859087228775024,
-    "eval_runtime": 16.2955,
-    "eval_samples_per_second": 2.455,
-    "eval_steps_per_second": 0.123
+    "epoch": 2.96,
+    "eval_accuracy": 0.4935064935064935,
+    "eval_loss": 1.343481421470642,
+    "eval_runtime": 34.4739,
+    "eval_samples_per_second": 4.467,
+    "eval_steps_per_second": 0.232
 }

runs/Jun09_07-56-38_db08404f55c1/events.out.tfevents.1686300855.db08404f55c1.20488.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70c49760454a02d93f5adb300be19ca99d9bfbd7ed889fe597080386627d9b1
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.67,
-    "total_flos": 2.038954042589184e+16,
-    "train_loss": 1.3799550731976826,
-    "train_runtime": 884.0465,
-    "train_samples_per_second": 1.222,
-    "train_steps_per_second": 0.014
+    "epoch": 2.96,
+    "total_flos": 8.65705903915991e+16,
+    "train_loss": 1.3479154296949798,
+    "train_runtime": 3214.4197,
+    "train_samples_per_second": 1.286,
+    "train_steps_per_second": 0.016
 }

trainer_state.json

@@ -1,58 +1,82 @@
 {
-  "best_metric": 0.25,
-  "best_model_checkpoint": "resnet-50-finetuned-drugsclass/checkpoint-4",
-  "epoch": 2.6666666666666665,
-  "global_step": 12,
+  "best_metric": 0.4935064935064935,
+  "best_model_checkpoint": "resnet-50-finetuned-drugsclass/checkpoint-17",
+  "epoch": 2.9565217391304346,
+  "global_step": 51,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.89,
-      "eval_accuracy": 0.25,
-      "eval_loss": 1.3859087228775024,
-      "eval_runtime": 7.5144,
-      "eval_samples_per_second": 5.323,
-      "eval_steps_per_second": 0.266,
-      "step": 4
+      "epoch": 0.58,
+      "learning_rate": 4.555555555555556e-05,
+      "loss": 1.3882,
+      "step": 10
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.25,
-      "eval_loss": 1.3814102411270142,
-      "eval_runtime": 9.5513,
-      "eval_samples_per_second": 4.188,
-      "eval_steps_per_second": 0.209,
-      "step": 9
+      "epoch": 0.99,
+      "eval_accuracy": 0.4935064935064935,
+      "eval_loss": 1.343481421470642,
+      "eval_runtime": 33.1805,
+      "eval_samples_per_second": 4.641,
+      "eval_steps_per_second": 0.241,
+      "step": 17
     },
     {
-      "epoch": 2.22,
-      "learning_rate": 1e-05,
-      "loss": 1.3806,
-      "step": 10
+      "epoch": 1.16,
+      "learning_rate": 3.444444444444445e-05,
+      "loss": 1.3628,
+      "step": 20
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 1.3408,
+      "step": 30
+    },
+    {
+      "epoch": 1.97,
+      "eval_accuracy": 0.487012987012987,
+      "eval_loss": 1.318909764289856,
+      "eval_runtime": 33.7879,
+      "eval_samples_per_second": 4.558,
+      "eval_steps_per_second": 0.237,
+      "step": 34
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.2222222222222222e-05,
+      "loss": 1.33,
+      "step": 40
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.1111111111111112e-06,
+      "loss": 1.318,
+      "step": 50
     },
     {
-      "epoch": 2.67,
-      "eval_accuracy": 0.25,
-      "eval_loss": 1.3822298049926758,
-      "eval_runtime": 8.0759,
-      "eval_samples_per_second": 4.953,
-      "eval_steps_per_second": 0.248,
-      "step": 12
+      "epoch": 2.96,
+      "eval_accuracy": 0.4675324675324675,
+      "eval_loss": 1.3059061765670776,
+      "eval_runtime": 33.4996,
+      "eval_samples_per_second": 4.597,
+      "eval_steps_per_second": 0.239,
+      "step": 51
     },
     {
-      "epoch": 2.67,
-      "step": 12,
-      "total_flos": 2.038954042589184e+16,
-      "train_loss": 1.3799550731976826,
-      "train_runtime": 884.0465,
-      "train_samples_per_second": 1.222,
-      "train_steps_per_second": 0.014
+      "epoch": 2.96,
+      "step": 51,
+      "total_flos": 8.65705903915991e+16,
+      "train_loss": 1.3479154296949798,
+      "train_runtime": 3214.4197,
+      "train_samples_per_second": 1.286,
+      "train_steps_per_second": 0.016
     }
   ],
-  "max_steps": 12,
+  "max_steps": 51,
   "num_train_epochs": 3,
-  "total_flos": 2.038954042589184e+16,
+  "total_flos": 8.65705903915991e+16,
   "trial_name": null,
   "trial_params": null
 }