Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.6846846846846847,
-    "eval_loss": 0.5890434384346008,
-    "eval_runtime": 1.5782,
-    "eval_samples_per_second": 140.663,
-    "eval_steps_per_second": 4.435,
-    "total_flos": 6.651462652615066e+16,
-    "train_loss": 0.5824283418201265,
-    "train_runtime": 89.156,
-    "train_samples_per_second": 30.015,
-    "train_steps_per_second": 0.236
+    "eval_accuracy": 0.6785714285714286,
+    "eval_loss": 0.6288004517555237,
+    "eval_runtime": 0.9772,
+    "eval_samples_per_second": 114.611,
+    "eval_steps_per_second": 4.093,
+    "total_flos": 7.471710289148314e+16,
+    "train_loss": 0.5194688042004904,
+    "train_runtime": 100.0049,
+    "train_samples_per_second": 30.059,
+    "train_steps_per_second": 0.24
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.6846846846846847,
-    "eval_loss": 0.5890434384346008,
-    "eval_runtime": 1.5782,
-    "eval_samples_per_second": 140.663,
-    "eval_steps_per_second": 4.435
+    "eval_accuracy": 0.6785714285714286,
+    "eval_loss": 0.6288004517555237,
+    "eval_runtime": 0.9772,
+    "eval_samples_per_second": 114.611,
+    "eval_steps_per_second": 4.093
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddabba932d67ef1b33e88688c94e1906c27ba7bed69482743c2ab7c6f901c662
+oid sha256:0489fd3e55532b8e0063a3f7ac55188574a13c18ed07abdd372e54dacd9aa68b
 size 110394865

runs/Jul20_20-47-08_fcbe542fc008/events.out.tfevents.1689887855.fcbe542fc008.344.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adac9ba119321c4dee8bc5cf184c1563b6904bfbc036b6ad17d7dac51f1d5be4
+size 405

runs/Jul20_20-47-08_fcbe542fc008/events.out.tfevents.1689889007.fcbe542fc008.344.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd61dcf27611fc32814c3a8df289b14ace1dc38588a145941109c356539fbb11
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 6.651462652615066e+16,
-    "train_loss": 0.5824283418201265,
-    "train_runtime": 89.156,
-    "train_samples_per_second": 30.015,
-    "train_steps_per_second": 0.236
+    "total_flos": 7.471710289148314e+16,
+    "train_loss": 0.5194688042004904,
+    "train_runtime": 100.0049,
+    "train_samples_per_second": 30.059,
+    "train_steps_per_second": 0.24
 }

trainer_state.json

@@ -1,64 +1,64 @@
 {
-  "best_metric": 0.6846846846846847,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
+  "best_metric": 0.6785714285714286,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-16",
   "epoch": 3.0,
-  "global_step": 21,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6846846846846847,
-      "eval_loss": 0.5890434384346008,
-      "eval_runtime": 1.6324,
-      "eval_samples_per_second": 135.994,
-      "eval_steps_per_second": 4.288,
-      "step": 7
+      "eval_accuracy": 0.6517857142857143,
+      "eval_loss": 0.6572104692459106,
+      "eval_runtime": 1.399,
+      "eval_samples_per_second": 80.056,
+      "eval_steps_per_second": 2.859,
+      "step": 8
     },
     {
-      "epoch": 1.43,
-      "learning_rate": 3.055555555555556e-05,
-      "loss": 0.5973,
+      "epoch": 1.25,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.5145,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6801801801801802,
-      "eval_loss": 0.6098485589027405,
-      "eval_runtime": 1.5365,
-      "eval_samples_per_second": 144.484,
-      "eval_steps_per_second": 4.556,
-      "step": 14
+      "eval_accuracy": 0.6785714285714286,
+      "eval_loss": 0.6288004517555237,
+      "eval_runtime": 0.7518,
+      "eval_samples_per_second": 148.97,
+      "eval_steps_per_second": 5.32,
+      "step": 16
     },
     {
-      "epoch": 2.86,
-      "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5675,
+      "epoch": 2.5,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 0.5157,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6801801801801802,
-      "eval_loss": 0.6154146194458008,
-      "eval_runtime": 1.5269,
-      "eval_samples_per_second": 145.391,
-      "eval_steps_per_second": 4.584,
-      "step": 21
+      "eval_accuracy": 0.6607142857142857,
+      "eval_loss": 0.6348384618759155,
+      "eval_runtime": 0.7495,
+      "eval_samples_per_second": 149.426,
+      "eval_steps_per_second": 5.337,
+      "step": 24
     },
     {
       "epoch": 3.0,
-      "step": 21,
-      "total_flos": 6.651462652615066e+16,
-      "train_loss": 0.5824283418201265,
-      "train_runtime": 89.156,
-      "train_samples_per_second": 30.015,
-      "train_steps_per_second": 0.236
+      "step": 24,
+      "total_flos": 7.471710289148314e+16,
+      "train_loss": 0.5194688042004904,
+      "train_runtime": 100.0049,
+      "train_samples_per_second": 30.059,
+      "train_steps_per_second": 0.24
     }
   ],
-  "max_steps": 21,
+  "max_steps": 24,
   "num_train_epochs": 3,
-  "total_flos": 6.651462652615066e+16,
+  "total_flos": 7.471710289148314e+16,
   "trial_name": null,
   "trial_params": null
 }