End of training

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
+    "epoch": 1.5,
     "eval_accuracy": 0.1111111111111111,
-    "eval_loss": 2.134453296661377,
-    "eval_runtime": 21.5397,
-    "eval_samples_per_second": 0.418,
-    "eval_steps_per_second": 0.418
+    "eval_loss": 2.133549451828003,
+    "eval_runtime": 20.3015,
+    "eval_samples_per_second": 0.443,
+    "eval_steps_per_second": 0.246
 }

test_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
+    "epoch": 1.5,
     "eval_accuracy": 0.1111111111111111,
-    "eval_loss": 2.134453296661377,
-    "eval_runtime": 21.5397,
-    "eval_samples_per_second": 0.418,
-    "eval_steps_per_second": 0.418
+    "eval_loss": 2.133549451828003,
+    "eval_runtime": 20.3015,
+    "eval_samples_per_second": 0.443,
+    "eval_steps_per_second": 0.246
 }

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": 0.125,
-  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-8",
-  "epoch": 1.0,
+  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-4",
+  "epoch": 1.5,
   "eval_steps": 500,
   "global_step": 8,
   "is_hyper_param_search": false,
@@ -9,39 +9,48 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
+      "epoch": 0.5,
       "eval_accuracy": 0.125,
-      "eval_loss": 2.152433395385742,
-      "eval_runtime": 24.1177,
-      "eval_samples_per_second": 0.332,
-      "eval_steps_per_second": 0.332,
+      "eval_loss": 2.1219842433929443,
+      "eval_runtime": 17.2946,
+      "eval_samples_per_second": 0.463,
+      "eval_steps_per_second": 0.231,
+      "step": 4
+    },
+    {
+      "epoch": 1.5,
+      "eval_accuracy": 0.125,
+      "eval_loss": 2.134676933288574,
+      "eval_runtime": 17.3183,
+      "eval_samples_per_second": 0.462,
+      "eval_steps_per_second": 0.231,
       "step": 8
     },
     {
-      "epoch": 1.0,
+      "epoch": 1.5,
       "step": 8,
-      "total_flos": 9969050119569408.0,
-      "train_loss": 2.3939802646636963,
-      "train_runtime": 56.9998,
-      "train_samples_per_second": 0.14,
-      "train_steps_per_second": 0.14
+      "total_flos": 1.9938100239138816e+16,
+      "train_loss": 2.2224740982055664,
+      "train_runtime": 97.4626,
+      "train_samples_per_second": 0.164,
+      "train_steps_per_second": 0.082
     },
     {
-      "epoch": 1.0,
+      "epoch": 1.5,
       "eval_accuracy": 0.1111111111111111,
-      "eval_loss": 2.134453296661377,
-      "eval_runtime": 25.1125,
-      "eval_samples_per_second": 0.358,
-      "eval_steps_per_second": 0.358,
+      "eval_loss": 2.133549451828003,
+      "eval_runtime": 20.1288,
+      "eval_samples_per_second": 0.447,
+      "eval_steps_per_second": 0.248,
       "step": 8
     },
     {
-      "epoch": 1.0,
+      "epoch": 1.5,
       "eval_accuracy": 0.1111111111111111,
-      "eval_loss": 2.134453296661377,
-      "eval_runtime": 21.5397,
-      "eval_samples_per_second": 0.418,
-      "eval_steps_per_second": 0.418,
+      "eval_loss": 2.133549451828003,
+      "eval_runtime": 20.3015,
+      "eval_samples_per_second": 0.443,
+      "eval_steps_per_second": 0.246,
       "step": 8
     }
   ],
@@ -49,7 +58,7 @@
   "max_steps": 8,
   "num_train_epochs": 9223372036854775807,
   "save_steps": 500,
-  "total_flos": 9969050119569408.0,
+  "total_flos": 1.9938100239138816e+16,
   "trial_name": null,
   "trial_params": null
 }