End of training

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.16,
-    "eval_accuracy": 0.26691838512924776,
-    "eval_loss": 1.1199040412902832,
-    "eval_runtime": 8842.1517,
-    "eval_samples_per_second": 0.389,
-    "eval_steps_per_second": 0.049
+    "epoch": 8.1,
+    "eval_accuracy": 0.21347661922741795,
+    "eval_loss": 1.1585432291030884,
+    "eval_runtime": 9824.635,
+    "eval_samples_per_second": 0.35,
+    "eval_steps_per_second": 0.044
 }

runs/Dec14_16-08-17_phillips-personal-workstation/events.out.tfevents.1702644464.phillips-personal-workstation.87918.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c32818da00e6d865919b06d6dbb0ec935c54a0ae62c56baa863264ec3681b8
-size 357
+oid sha256:7b910f9ae588db72fb384f7c41a12138ab3812576c7a31b5ef14a2bd0b4c0cba
+size 674

test_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.16,
-    "eval_accuracy": 0.26691838512924776,
-    "eval_loss": 1.1199040412902832,
-    "eval_runtime": 8842.1517,
-    "eval_samples_per_second": 0.389,
-    "eval_steps_per_second": 0.049
+    "epoch": 8.1,
+    "eval_accuracy": 0.21347661922741795,
+    "eval_loss": 1.1585432291030884,
+    "eval_runtime": 9824.635,
+    "eval_samples_per_second": 0.35,
+    "eval_steps_per_second": 0.044
 }

trainer_state.json

@@ -1,97 +1,172 @@
 {
-  "best_metric": 0.4974337040205304,
-  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-32",
-  "epoch": 3.15625,
-  "global_step": 32,
+  "best_metric": 0.583404619332763,
+  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-27",
+  "epoch": 8.1,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.28,
-      "eval_accuracy": 0.3678357570573139,
-      "eval_loss": 1.1095340251922607,
-      "eval_runtime": 6781.1418,
-      "eval_samples_per_second": 0.345,
-      "eval_steps_per_second": 0.043,
+      "epoch": 0.11,
+      "eval_accuracy": 0.3738237810094098,
+      "eval_loss": 1.1102712154388428,
+      "eval_runtime": 6904.9882,
+      "eval_samples_per_second": 0.339,
+      "eval_steps_per_second": 0.042,
       "step": 9
     },
     {
-      "epoch": 1.03,
-      "learning_rate": 3.928571428571429e-05,
-      "loss": 1.1547,
+      "epoch": 1.01,
+      "learning_rate": 4.8611111111111115e-05,
+      "loss": 1.1692,
       "step": 10
     },
     {
-      "epoch": 1.28,
-      "eval_accuracy": 0.25149700598802394,
-      "eval_loss": 1.0840415954589844,
-      "eval_runtime": 6565.429,
-      "eval_samples_per_second": 0.356,
-      "eval_steps_per_second": 0.045,
+      "epoch": 1.11,
+      "eval_accuracy": 0.2352437981180496,
+      "eval_loss": 1.1009142398834229,
+      "eval_runtime": 6655.1854,
+      "eval_samples_per_second": 0.351,
+      "eval_steps_per_second": 0.044,
       "step": 18
     },
     {
-      "epoch": 2.06,
-      "learning_rate": 2.1428571428571428e-05,
-      "loss": 1.0917,
+      "epoch": 2.02,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.135,
       "step": 20
     },
     {
-      "epoch": 2.28,
-      "eval_accuracy": 0.48545765611633873,
-      "eval_loss": 1.037040114402771,
-      "eval_runtime": 6528.1498,
-      "eval_samples_per_second": 0.358,
+      "epoch": 2.11,
+      "eval_accuracy": 0.583404619332763,
+      "eval_loss": 1.0518925189971924,
+      "eval_runtime": 6576.2685,
+      "eval_samples_per_second": 0.356,
       "eval_steps_per_second": 0.045,
       "step": 27
     },
     {
-      "epoch": 3.09,
-      "learning_rate": 3.5714285714285714e-06,
-      "loss": 1.0976,
+      "epoch": 3.04,
+      "learning_rate": 3.472222222222222e-05,
+      "loss": 1.0973,
       "step": 30
     },
     {
-      "epoch": 3.16,
-      "eval_accuracy": 0.4974337040205304,
-      "eval_loss": 1.0295767784118652,
-      "eval_runtime": 6784.8017,
+      "epoch": 3.11,
+      "eval_accuracy": 0.583404619332763,
+      "eval_loss": 1.0562057495117188,
+      "eval_runtime": 6783.3208,
       "eval_samples_per_second": 0.345,
       "eval_steps_per_second": 0.043,
-      "step": 32
+      "step": 36
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.0728,
+      "step": 40
+    },
+    {
+      "epoch": 4.11,
+      "eval_accuracy": 0.3857998289136014,
+      "eval_loss": 1.1006081104278564,
+      "eval_runtime": 6626.9958,
+      "eval_samples_per_second": 0.353,
+      "eval_steps_per_second": 0.044,
+      "step": 45
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 1.052,
+      "step": 50
+    },
+    {
+      "epoch": 5.11,
+      "eval_accuracy": 0.24978614200171087,
+      "eval_loss": 1.1561808586120605,
+      "eval_runtime": 6687.7083,
+      "eval_samples_per_second": 0.35,
+      "eval_steps_per_second": 0.044,
+      "step": 54
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 1.0561,
+      "step": 60
+    },
+    {
+      "epoch": 6.11,
+      "eval_accuracy": 0.2356715141146279,
+      "eval_loss": 1.145110845565796,
+      "eval_runtime": 6713.3828,
+      "eval_samples_per_second": 0.348,
+      "eval_steps_per_second": 0.044,
+      "step": 63
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 6.944444444444445e-06,
+      "loss": 1.021,
+      "step": 70
+    },
+    {
+      "epoch": 7.11,
+      "eval_accuracy": 0.2356715141146279,
+      "eval_loss": 1.147510051727295,
+      "eval_runtime": 6861.296,
+      "eval_samples_per_second": 0.341,
+      "eval_steps_per_second": 0.043,
+      "step": 72
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 0.0,
+      "loss": 0.9696,
+      "step": 80
     },
     {
-      "epoch": 3.16,
-      "step": 32,
-      "total_flos": 2.9282778998194176e+17,
-      "train_loss": 1.1151684671640396,
-      "train_runtime": 29569.9652,
+      "epoch": 8.1,
+      "eval_accuracy": 0.25791274593669805,
+      "eval_loss": 1.1406161785125732,
+      "eval_runtime": 6748.1283,
+      "eval_samples_per_second": 0.346,
+      "eval_steps_per_second": 0.043,
+      "step": 80
+    },
+    {
+      "epoch": 8.1,
+      "step": 80,
+      "total_flos": 7.277082099976765e+17,
+      "train_loss": 1.0716288447380067,
+      "train_runtime": 67996.5245,
       "train_samples_per_second": 0.009,
       "train_steps_per_second": 0.001
     },
     {
-      "epoch": 3.16,
-      "eval_accuracy": 0.26691838512924776,
-      "eval_loss": 1.1199040412902832,
-      "eval_runtime": 9068.5155,
-      "eval_samples_per_second": 0.38,
-      "eval_steps_per_second": 0.048,
-      "step": 32
+      "epoch": 8.1,
+      "eval_accuracy": 0.21347661922741795,
+      "eval_loss": 1.158543348312378,
+      "eval_runtime": 9929.4112,
+      "eval_samples_per_second": 0.347,
+      "eval_steps_per_second": 0.043,
+      "step": 80
     },
     {
-      "epoch": 3.16,
-      "eval_accuracy": 0.26691838512924776,
-      "eval_loss": 1.1199040412902832,
-      "eval_runtime": 8842.1517,
-      "eval_samples_per_second": 0.389,
-      "eval_steps_per_second": 0.049,
-      "step": 32
+      "epoch": 8.1,
+      "eval_accuracy": 0.21347661922741795,
+      "eval_loss": 1.1585432291030884,
+      "eval_runtime": 9824.635,
+      "eval_samples_per_second": 0.35,
+      "eval_steps_per_second": 0.044,
+      "step": 80
     }
   ],
-  "max_steps": 32,
+  "max_steps": 80,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 2.9282778998194176e+17,
+  "total_flos": 7.277082099976765e+17,
   "trial_name": null,
   "trial_params": null
 }