Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.23,
-    "eval_accuracy": 0.8387096774193549,
-    "eval_loss": 0.44136250019073486,
-    "eval_runtime": 23.6897,
-    "eval_samples_per_second": 6.543,
-    "eval_steps_per_second": 0.844
+    "eval_accuracy": 0.8580645161290322,
+    "eval_loss": 0.4741174578666687,
+    "eval_runtime": 27.5301,
+    "eval_samples_per_second": 5.63,
+    "eval_steps_per_second": 0.726
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ee08ce120c5566ac3e6e2ed9495176569bb89abcff2e7a07904c9b78d039e8
+oid sha256:412e0b49ea61a7b31947d243d149273bcac5c4480989cfcdccbda9d0f004661d
 size 345003509

runs/Jun12_14-38-12_dgx002/events.out.tfevents.1686574136.dgx002.65055.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea15b0581d27e37369091a358bff9be8713a884cf7351d2fdc9d617361d35117
-size 363
+oid sha256:12ad7548e7641bb20bd3a4c4064b8f9175c061f6a15aa57325ff4f6f4ed2d443
+size 686

runs/Jun12_15-01-28_dgx002/1686574901.4763446/events.out.tfevents.1686574901.dgx002.69669.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4b78a7635fa3ab09c99118945543c06a8837024c8509f221c14fdcaa33f2d4
+size 5883

runs/Jun12_15-01-28_dgx002/events.out.tfevents.1686574901.dgx002.69669.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed0d250b345f4f19e7c214c007852b525a66ea84463d0070b2b60cc7e3177cd
+size 5416

test_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.23,
-    "eval_accuracy": 0.8387096774193549,
-    "eval_loss": 0.44136250019073486,
-    "eval_runtime": 23.6897,
-    "eval_samples_per_second": 6.543,
-    "eval_steps_per_second": 0.844
+    "eval_accuracy": 0.8580645161290322,
+    "eval_loss": 0.4741174578666687,
+    "eval_runtime": 27.5301,
+    "eval_samples_per_second": 5.63,
+    "eval_steps_per_second": 0.726
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9142857142857143,
-  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-114",
+  "best_metric": 0.8714285714285714,
+  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
   "epoch": 3.22972972972973,
   "global_step": 148,
   "is_hyper_param_search": false,
@@ -10,148 +10,148 @@
     {
       "epoch": 0.07,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 2.2957,
+      "loss": 2.3,
       "step": 10
     },
     {
       "epoch": 0.14,
       "learning_rate": 4.81203007518797e-05,
-      "loss": 2.1731,
+      "loss": 2.1696,
       "step": 20
     },
     {
       "epoch": 0.2,
       "learning_rate": 4.43609022556391e-05,
-      "loss": 2.046,
+      "loss": 2.1374,
       "step": 30
     },
     {
       "epoch": 0.26,
-      "eval_accuracy": 0.5285714285714286,
-      "eval_loss": 1.6963216066360474,
-      "eval_runtime": 10.977,
-      "eval_samples_per_second": 6.377,
-      "eval_steps_per_second": 0.82,
+      "eval_accuracy": 0.4142857142857143,
+      "eval_loss": 1.831816554069519,
+      "eval_runtime": 11.4195,
+      "eval_samples_per_second": 6.13,
+      "eval_steps_per_second": 0.788,
       "step": 38
     },
     {
       "epoch": 1.01,
       "learning_rate": 4.0601503759398494e-05,
-      "loss": 1.8937,
+      "loss": 1.9867,
       "step": 40
     },
     {
       "epoch": 1.08,
       "learning_rate": 3.6842105263157895e-05,
-      "loss": 1.4425,
+      "loss": 1.4944,
       "step": 50
     },
     {
       "epoch": 1.15,
       "learning_rate": 3.3082706766917295e-05,
-      "loss": 1.1676,
+      "loss": 1.2525,
       "step": 60
     },
     {
       "epoch": 1.22,
       "learning_rate": 2.9323308270676693e-05,
-      "loss": 0.8324,
+      "loss": 0.9554,
       "step": 70
     },
     {
       "epoch": 1.26,
-      "eval_accuracy": 0.7714285714285715,
-      "eval_loss": 0.7202897667884827,
-      "eval_runtime": 12.3258,
-      "eval_samples_per_second": 5.679,
-      "eval_steps_per_second": 0.73,
+      "eval_accuracy": 0.6428571428571429,
+      "eval_loss": 1.0205751657485962,
+      "eval_runtime": 11.6614,
+      "eval_samples_per_second": 6.003,
+      "eval_steps_per_second": 0.772,
       "step": 76
     },
     {
       "epoch": 2.03,
       "learning_rate": 2.556390977443609e-05,
-      "loss": 0.8057,
+      "loss": 0.8545,
       "step": 80
     },
     {
       "epoch": 2.09,
       "learning_rate": 2.1804511278195487e-05,
-      "loss": 0.5698,
+      "loss": 0.6184,
       "step": 90
     },
     {
       "epoch": 2.16,
       "learning_rate": 1.8045112781954888e-05,
-      "loss": 0.5088,
+      "loss": 0.6031,
       "step": 100
     },
     {
       "epoch": 2.23,
       "learning_rate": 1.4285714285714285e-05,
-      "loss": 0.4576,
+      "loss": 0.4549,
       "step": 110
     },
     {
       "epoch": 2.26,
-      "eval_accuracy": 0.9142857142857143,
-      "eval_loss": 0.40682417154312134,
-      "eval_runtime": 11.5894,
-      "eval_samples_per_second": 6.04,
-      "eval_steps_per_second": 0.777,
+      "eval_accuracy": 0.8428571428571429,
+      "eval_loss": 0.5566275715827942,
+      "eval_runtime": 10.0032,
+      "eval_samples_per_second": 6.998,
+      "eval_steps_per_second": 0.9,
       "step": 114
     },
     {
       "epoch": 3.04,
       "learning_rate": 1.0526315789473684e-05,
-      "loss": 0.2856,
+      "loss": 0.3658,
       "step": 120
     },
     {
       "epoch": 3.11,
       "learning_rate": 6.766917293233083e-06,
-      "loss": 0.2348,
+      "loss": 0.2797,
       "step": 130
     },
     {
       "epoch": 3.18,
       "learning_rate": 3.007518796992481e-06,
-      "loss": 0.2632,
+      "loss": 0.3045,
       "step": 140
     },
     {
       "epoch": 3.23,
       "eval_accuracy": 0.8714285714285714,
-      "eval_loss": 0.33855465054512024,
-      "eval_runtime": 11.4954,
-      "eval_samples_per_second": 6.089,
-      "eval_steps_per_second": 0.783,
+      "eval_loss": 0.46514713764190674,
+      "eval_runtime": 11.0086,
+      "eval_samples_per_second": 6.359,
+      "eval_steps_per_second": 0.818,
       "step": 148
     },
     {
       "epoch": 3.23,
       "step": 148,
       "total_flos": 1.460491890402263e+18,
-      "train_loss": 1.024867109350256,
-      "train_runtime": 599.0938,
-      "train_samples_per_second": 1.976,
-      "train_steps_per_second": 0.247
+      "train_loss": 1.079887928189458,
+      "train_runtime": 604.0644,
+      "train_samples_per_second": 1.96,
+      "train_steps_per_second": 0.245
     },
     {
       "epoch": 3.23,
-      "eval_accuracy": 0.8387096774193549,
-      "eval_loss": 0.4413624405860901,
-      "eval_runtime": 26.0793,
-      "eval_samples_per_second": 5.943,
-      "eval_steps_per_second": 0.767,
+      "eval_accuracy": 0.8580645161290322,
+      "eval_loss": 0.4741174578666687,
+      "eval_runtime": 28.7326,
+      "eval_samples_per_second": 5.395,
+      "eval_steps_per_second": 0.696,
       "step": 148
     },
     {
       "epoch": 3.23,
-      "eval_accuracy": 0.8387096774193549,
-      "eval_loss": 0.44136250019073486,
-      "eval_runtime": 23.6897,
-      "eval_samples_per_second": 6.543,
-      "eval_steps_per_second": 0.844,
+      "eval_accuracy": 0.8580645161290322,
+      "eval_loss": 0.4741174578666687,
+      "eval_runtime": 27.5301,
+      "eval_samples_per_second": 5.63,
+      "eval_steps_per_second": 0.726,
       "step": 148
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962862fdf4513cbd5fb5621011b496dc0107d57aa60f4cdb2a4bde5eb28cc1ab
+oid sha256:0cacf5b5fdd1a5a07663d19e16b9613a85eb1c73ff99eac8490bec2296bb9dfd
 size 3643