End of training

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 17.0,
+    "epoch": 12.0,
     "eval_loss": 0.6131083965301514,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.0977,
+    "eval_runtime": 1.1058,
     "eval_samples": 1043,
-    "eval_samples_per_second": 950.147,
-    "eval_steps_per_second": 4.555,
-    "train_loss": 0.11972142585833592,
-    "train_runtime": 177.9873,
+    "eval_samples_per_second": 943.228,
+    "eval_steps_per_second": 4.522,
+    "train_loss": 0.5614397408915501,
+    "train_runtime": 434.3841,
     "train_samples": 8551,
-    "train_samples_per_second": 2402.138,
-    "train_steps_per_second": 9.551
+    "train_samples_per_second": 984.267,
+    "train_steps_per_second": 3.914
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 17.0,
+    "epoch": 12.0,
     "eval_loss": 0.6131083965301514,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.0977,
+    "eval_runtime": 1.1058,
     "eval_samples": 1043,
-    "eval_samples_per_second": 950.147,
-    "eval_steps_per_second": 4.555
+    "eval_samples_per_second": 943.228,
+    "eval_steps_per_second": 4.522
 }

logs/events.out.tfevents.1674303956.serv-3331.3429984.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ddd3c2e29fffad0c414d2b3883e736b574d6075dc66594513b49cb7233b33ca
+size 375

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 17.0,
-    "train_loss": 0.11972142585833592,
-    "train_runtime": 177.9873,
+    "epoch": 12.0,
+    "train_loss": 0.5614397408915501,
+    "train_runtime": 434.3841,
     "train_samples": 8551,
-    "train_samples_per_second": 2402.138,
-    "train_steps_per_second": 9.551
+    "train_samples_per_second": 984.267,
+    "train_steps_per_second": 3.914
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 0.6131083965301514,
   "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_cola/checkpoint-238",
-  "epoch": 17.0,
-  "global_step": 578,
+  "epoch": 12.0,
+  "global_step": 408,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_loss": 0.6238651871681213,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.5899,
-      "eval_samples_per_second": 656.009,
-      "eval_steps_per_second": 3.145,
+      "eval_runtime": 1.0726,
+      "eval_samples_per_second": 972.413,
+      "eval_steps_per_second": 4.662,
       "step": 34
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_loss": 0.6178815364837646,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.5812,
-      "eval_samples_per_second": 659.606,
-      "eval_steps_per_second": 3.162,
+      "eval_runtime": 1.0582,
+      "eval_samples_per_second": 985.593,
+      "eval_steps_per_second": 4.725,
       "step": 68
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_loss": 0.6179934144020081,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 2.4438,
-      "eval_samples_per_second": 426.802,
-      "eval_steps_per_second": 2.046,
+      "eval_runtime": 1.3387,
+      "eval_samples_per_second": 779.113,
+      "eval_steps_per_second": 3.735,
       "step": 102
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_loss": 0.6175711750984192,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.7323,
-      "eval_samples_per_second": 602.096,
-      "eval_steps_per_second": 2.886,
+      "eval_runtime": 1.1189,
+      "eval_samples_per_second": 932.188,
+      "eval_steps_per_second": 4.469,
       "step": 136
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_loss": 0.6172661781311035,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.7156,
-      "eval_samples_per_second": 607.942,
-      "eval_steps_per_second": 2.914,
+      "eval_runtime": 1.1205,
+      "eval_samples_per_second": 930.859,
+      "eval_steps_per_second": 4.462,
       "step": 170
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_loss": 0.6166184544563293,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.9408,
-      "eval_samples_per_second": 537.405,
-      "eval_steps_per_second": 2.576,
+      "eval_runtime": 1.2344,
+      "eval_samples_per_second": 844.955,
+      "eval_steps_per_second": 4.051,
       "step": 204
     },
     {
@@ -107,9 +107,9 @@
       "epoch": 7.0,
       "eval_loss": 0.6131083965301514,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.7507,
-      "eval_samples_per_second": 595.751,
-      "eval_steps_per_second": 2.856,
+      "eval_runtime": 1.1421,
+      "eval_samples_per_second": 913.231,
+      "eval_steps_per_second": 4.378,
       "step": 238
     },
     {
@@ -122,9 +122,9 @@
       "epoch": 8.0,
       "eval_loss": 0.6240708231925964,
       "eval_matthews_correlation": 0.0951039122870703,
-      "eval_runtime": 1.7156,
-      "eval_samples_per_second": 607.967,
-      "eval_steps_per_second": 2.915,
+      "eval_runtime": 1.1486,
+      "eval_samples_per_second": 908.065,
+      "eval_steps_per_second": 4.353,
       "step": 272
     },
     {
@@ -137,9 +137,9 @@
       "epoch": 9.0,
       "eval_loss": 0.6361746191978455,
       "eval_matthews_correlation": 0.059760920069176514,
-      "eval_runtime": 1.9833,
-      "eval_samples_per_second": 525.879,
-      "eval_steps_per_second": 2.521,
+      "eval_runtime": 1.2007,
+      "eval_samples_per_second": 868.661,
+      "eval_steps_per_second": 4.164,
       "step": 306
     },
     {
@@ -152,9 +152,9 @@
       "epoch": 10.0,
       "eval_loss": 0.7009902596473694,
       "eval_matthews_correlation": 0.08008155523655092,
-      "eval_runtime": 1.7208,
-      "eval_samples_per_second": 606.103,
-      "eval_steps_per_second": 2.906,
+      "eval_runtime": 1.1475,
+      "eval_samples_per_second": 908.97,
+      "eval_steps_per_second": 4.357,
       "step": 340
     },
     {
@@ -167,9 +167,9 @@
       "epoch": 11.0,
       "eval_loss": 0.6731011867523193,
       "eval_matthews_correlation": 0.09051190856095573,
-      "eval_runtime": 1.7848,
-      "eval_samples_per_second": 584.391,
-      "eval_steps_per_second": 2.801,
+      "eval_runtime": 1.1134,
+      "eval_samples_per_second": 936.763,
+      "eval_steps_per_second": 4.491,
       "step": 374
     },
     {
@@ -182,99 +182,24 @@
       "epoch": 12.0,
       "eval_loss": 0.6893478035926819,
       "eval_matthews_correlation": 0.09007205990892461,
-      "eval_runtime": 1.959,
-      "eval_samples_per_second": 532.427,
-      "eval_steps_per_second": 2.552,
+      "eval_runtime": 1.2098,
+      "eval_samples_per_second": 862.13,
+      "eval_steps_per_second": 4.133,
       "step": 408
     },
     {
-      "epoch": 13.0,
-      "learning_rate": 3.7e-05,
-      "loss": 0.4319,
-      "step": 442
-    },
-    {
-      "epoch": 13.0,
-      "eval_loss": 0.703128457069397,
-      "eval_matthews_correlation": 0.08499911671189282,
-      "eval_runtime": 1.0793,
-      "eval_samples_per_second": 966.409,
-      "eval_steps_per_second": 4.633,
-      "step": 442
-    },
-    {
-      "epoch": 14.0,
-      "learning_rate": 3.6e-05,
-      "loss": 0.4153,
-      "step": 476
-    },
-    {
-      "epoch": 14.0,
-      "eval_loss": 0.718442440032959,
-      "eval_matthews_correlation": 0.08205498032090315,
-      "eval_runtime": 1.0885,
-      "eval_samples_per_second": 958.214,
-      "eval_steps_per_second": 4.594,
-      "step": 476
-    },
-    {
-      "epoch": 15.0,
-      "learning_rate": 3.5e-05,
-      "loss": 0.4048,
-      "step": 510
-    },
-    {
-      "epoch": 15.0,
-      "eval_loss": 0.8069401383399963,
-      "eval_matthews_correlation": 0.10451124263480288,
-      "eval_runtime": 1.2661,
-      "eval_samples_per_second": 823.769,
-      "eval_steps_per_second": 3.949,
-      "step": 510
-    },
-    {
-      "epoch": 16.0,
-      "learning_rate": 3.4000000000000007e-05,
-      "loss": 0.3926,
-      "step": 544
-    },
-    {
-      "epoch": 16.0,
-      "eval_loss": 0.7495270371437073,
-      "eval_matthews_correlation": 0.13154834951294067,
-      "eval_runtime": 1.1233,
-      "eval_samples_per_second": 928.509,
-      "eval_steps_per_second": 4.451,
-      "step": 544
-    },
-    {
-      "epoch": 17.0,
-      "learning_rate": 3.3e-05,
-      "loss": 0.3907,
-      "step": 578
-    },
-    {
-      "epoch": 17.0,
-      "eval_loss": 0.8371085524559021,
-      "eval_matthews_correlation": 0.10202308372884508,
-      "eval_runtime": 1.1282,
-      "eval_samples_per_second": 924.472,
-      "eval_steps_per_second": 4.432,
-      "step": 578
-    },
-    {
-      "epoch": 17.0,
-      "step": 578,
-      "total_flos": 4616521615671296.0,
-      "train_loss": 0.11972142585833592,
-      "train_runtime": 177.9873,
-      "train_samples_per_second": 2402.138,
-      "train_steps_per_second": 9.551
+      "epoch": 12.0,
+      "step": 408,
+      "total_flos": 3258721140473856.0,
+      "train_loss": 0.5614397408915501,
+      "train_runtime": 434.3841,
+      "train_samples_per_second": 984.267,
+      "train_steps_per_second": 3.914
     }
   ],
   "max_steps": 1700,
   "num_train_epochs": 50,
-  "total_flos": 4616521615671296.0,
+  "total_flos": 3258721140473856.0,
   "trial_name": null,
   "trial_params": null
 }