End of training

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.23,
-    "eval_accuracy": 0.7935483870967742,
-    "eval_loss": 0.5277948379516602,
-    "eval_runtime": 72.4283,
-    "eval_samples_per_second": 2.14,
-    "eval_steps_per_second": 0.276
+    "epoch": 1.5,
+    "eval_accuracy": 0.0,
+    "eval_loss": 1.2120331525802612,
+    "eval_runtime": 17.8071,
+    "eval_samples_per_second": 0.618,
+    "eval_steps_per_second": 0.337
 }

runs/Feb02_08-00-01_03b2ce95466a/events.out.tfevents.1675324883.03b2ce95466a.384474.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d91239aa835066b43330c514244ed02cc211ec823bfdf2d4fa82ef2daaaf39
-size 357
+oid sha256:1f8b29ab27d06fe42648430091f989513d31c07a38b6e9d653f85b699a15033c
+size 674

test_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.23,
-    "eval_accuracy": 0.7935483870967742,
-    "eval_loss": 0.5277948379516602,
-    "eval_runtime": 72.4283,
-    "eval_samples_per_second": 2.14,
-    "eval_steps_per_second": 0.276
+    "epoch": 1.5,
+    "eval_accuracy": 0.0,
+    "eval_loss": 1.2120331525802612,
+    "eval_runtime": 17.8071,
+    "eval_samples_per_second": 0.618,
+    "eval_steps_per_second": 0.337
 }

trainer_state.json

@@ -1,163 +1,61 @@
 {
-  "best_metric": 0.8857142857142857,
-  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
-  "epoch": 3.22972972972973,
-  "global_step": 148,
+  "best_metric": 0.0,
+  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-1",
+  "epoch": 1.5,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.07,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 2.3448,
-      "step": 10
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 4.81203007518797e-05,
-      "loss": 2.2048,
-      "step": 20
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 4.43609022556391e-05,
-      "loss": 2.1711,
-      "step": 30
-    },
-    {
-      "epoch": 0.26,
-      "eval_accuracy": 0.5142857142857142,
-      "eval_loss": 1.7582899332046509,
-      "eval_runtime": 23.3861,
-      "eval_samples_per_second": 2.993,
-      "eval_steps_per_second": 0.385,
-      "step": 38
-    },
-    {
-      "epoch": 1.01,
-      "learning_rate": 4.0601503759398494e-05,
-      "loss": 2.0056,
-      "step": 40
-    },
-    {
-      "epoch": 1.08,
-      "learning_rate": 3.6842105263157895e-05,
-      "loss": 1.6312,
-      "step": 50
-    },
-    {
-      "epoch": 1.15,
-      "learning_rate": 3.3082706766917295e-05,
-      "loss": 1.2896,
-      "step": 60
-    },
-    {
-      "epoch": 1.22,
-      "learning_rate": 2.9323308270676693e-05,
-      "loss": 0.8671,
-      "step": 70
-    },
-    {
-      "epoch": 1.26,
-      "eval_accuracy": 0.7714285714285715,
-      "eval_loss": 0.8745585680007935,
-      "eval_runtime": 26.4231,
-      "eval_samples_per_second": 2.649,
-      "eval_steps_per_second": 0.341,
-      "step": 76
-    },
-    {
-      "epoch": 2.03,
-      "learning_rate": 2.556390977443609e-05,
-      "loss": 0.8836,
-      "step": 80
-    },
-    {
-      "epoch": 2.09,
-      "learning_rate": 2.1804511278195487e-05,
-      "loss": 0.7118,
-      "step": 90
-    },
-    {
-      "epoch": 2.16,
-      "learning_rate": 1.8045112781954888e-05,
-      "loss": 0.661,
-      "step": 100
-    },
-    {
-      "epoch": 2.23,
-      "learning_rate": 1.4285714285714285e-05,
-      "loss": 0.5099,
-      "step": 110
-    },
-    {
-      "epoch": 2.26,
-      "eval_accuracy": 0.8142857142857143,
-      "eval_loss": 0.5396287441253662,
-      "eval_runtime": 23.1042,
-      "eval_samples_per_second": 3.03,
-      "eval_steps_per_second": 0.39,
-      "step": 114
-    },
-    {
-      "epoch": 3.04,
-      "learning_rate": 1.0526315789473684e-05,
-      "loss": 0.3588,
-      "step": 120
-    },
-    {
-      "epoch": 3.11,
-      "learning_rate": 6.766917293233083e-06,
-      "loss": 0.3546,
-      "step": 130
-    },
-    {
-      "epoch": 3.18,
-      "learning_rate": 3.007518796992481e-06,
-      "loss": 0.3309,
-      "step": 140
-    },
-    {
-      "epoch": 3.23,
-      "eval_accuracy": 0.8857142857142857,
-      "eval_loss": 0.42734411358833313,
-      "eval_runtime": 33.9304,
-      "eval_samples_per_second": 2.063,
-      "eval_steps_per_second": 0.265,
-      "step": 148
-    },
-    {
-      "epoch": 3.23,
-      "step": 148,
-      "total_flos": 1.460491890402263e+18,
-      "train_loss": 1.1209931856877096,
-      "train_runtime": 1473.4643,
-      "train_samples_per_second": 0.804,
-      "train_steps_per_second": 0.1
-    },
-    {
-      "epoch": 3.23,
-      "eval_accuracy": 0.7935483870967742,
-      "eval_loss": 0.5277948975563049,
-      "eval_runtime": 75.0622,
-      "eval_samples_per_second": 2.065,
-      "eval_steps_per_second": 0.266,
-      "step": 148
-    },
-    {
-      "epoch": 3.23,
-      "eval_accuracy": 0.7935483870967742,
-      "eval_loss": 0.5277948379516602,
-      "eval_runtime": 72.4283,
-      "eval_samples_per_second": 2.14,
-      "eval_steps_per_second": 0.276,
-      "step": 148
+      "epoch": 0.5,
+      "eval_accuracy": 0.0,
+      "eval_loss": 1.2203034162521362,
+      "eval_runtime": 9.802,
+      "eval_samples_per_second": 0.714,
+      "eval_steps_per_second": 0.408,
+      "step": 1
+    },
+    {
+      "epoch": 1.5,
+      "eval_accuracy": 0.0,
+      "eval_loss": 1.0271836519241333,
+      "eval_runtime": 9.6627,
+      "eval_samples_per_second": 0.724,
+      "eval_steps_per_second": 0.414,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "step": 2,
+      "total_flos": 4984302808203264.0,
+      "train_loss": 1.3228081464767456,
+      "train_runtime": 33.3167,
+      "train_samples_per_second": 0.12,
+      "train_steps_per_second": 0.06
+    },
+    {
+      "epoch": 1.5,
+      "eval_accuracy": 0.0,
+      "eval_loss": 1.2120330333709717,
+      "eval_runtime": 18.287,
+      "eval_samples_per_second": 0.602,
+      "eval_steps_per_second": 0.328,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "eval_accuracy": 0.0,
+      "eval_loss": 1.2120331525802612,
+      "eval_runtime": 17.8071,
+      "eval_samples_per_second": 0.618,
+      "eval_steps_per_second": 0.337,
+      "step": 2
     }
   ],
-  "max_steps": 148,
+  "max_steps": 2,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 1.460491890402263e+18,
+  "total_flos": 4984302808203264.0,
   "trial_name": null,
   "trial_params": null
 }