End of training

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 3.0,
     "eval_accuracy": 0.6322020292282104,
     "eval_loss": 1.8354707956314087,
-    "eval_runtime": 2.5103,
+    "eval_runtime": 2.4427,
     "eval_samples": 1267,
-    "eval_samples_per_second": 504.724,
-    "eval_steps_per_second": 63.339,
+    "eval_samples_per_second": 518.682,
+    "eval_steps_per_second": 65.091,
     "train_loss": 2.186672953385506,
-    "train_runtime": 425.0347,
+    "train_runtime": 418.7818,
     "train_samples": 11651,
-    "train_samples_per_second": 82.236,
-    "train_steps_per_second": 10.284
+    "train_samples_per_second": 83.464,
+    "train_steps_per_second": 10.437
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "eval_accuracy": 0.6322020292282104,
     "eval_loss": 1.8354707956314087,
-    "eval_runtime": 2.5103,
+    "eval_runtime": 2.4427,
     "eval_samples": 1267,
-    "eval_samples_per_second": 504.724,
-    "eval_steps_per_second": 63.339
+    "eval_samples_per_second": 518.682,
+    "eval_steps_per_second": 65.091
 }

runs/Dec02_08-22-15_jbuhmann/events.out.tfevents.1638433351.jbuhmann.9189.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9774331878ff5301a1e9fd93116dfb7092e48388c04ea7737a88365af7e03fe9
-size 18578
+oid sha256:e81e74fdc5cbf34bdef782f4407b38337903cb8a0428b73e8260c1dc41258f19
+size 18932

runs/Dec02_08-22-15_jbuhmann/events.out.tfevents.1638433774.jbuhmann.9189.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4fdd40baa8f0e13710423415631c18d17c3ba1a24d319042a5017fbfdee22da
+size 363

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 2.186672953385506,
-    "train_runtime": 425.0347,
+    "train_runtime": 418.7818,
     "train_samples": 11651,
-    "train_samples_per_second": 82.236,
-    "train_steps_per_second": 10.284
+    "train_samples_per_second": 83.464,
+    "train_steps_per_second": 10.437
 }

trainer_state.json

@@ -23,9 +23,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.5406472086906433,
       "eval_loss": 2.3865766525268555,
-      "eval_runtime": 2.5099,
-      "eval_samples_per_second": 504.808,
-      "eval_steps_per_second": 63.35,
+      "eval_runtime": 2.3607,
+      "eval_samples_per_second": 536.704,
+      "eval_steps_per_second": 67.353,
       "step": 1457
     },
     {
@@ -50,9 +50,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.6069455146789551,
       "eval_loss": 1.9364700317382812,
-      "eval_runtime": 2.445,
-      "eval_samples_per_second": 518.202,
-      "eval_steps_per_second": 65.031,
+      "eval_runtime": 2.4048,
+      "eval_samples_per_second": 526.856,
+      "eval_steps_per_second": 66.117,
       "step": 2914
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.6322020292282104,
       "eval_loss": 1.8354707956314087,
-      "eval_runtime": 2.4438,
-      "eval_samples_per_second": 518.46,
-      "eval_steps_per_second": 65.063,
+      "eval_runtime": 2.3743,
+      "eval_samples_per_second": 533.633,
+      "eval_steps_per_second": 66.967,
       "step": 4371
     },
     {
@@ -87,9 +87,9 @@
       "step": 4371,
       "total_flos": 1151412634864512.0,
       "train_loss": 2.186672953385506,
-      "train_runtime": 425.0347,
-      "train_samples_per_second": 82.236,
-      "train_steps_per_second": 10.284
+      "train_runtime": 418.7818,
+      "train_samples_per_second": 83.464,
+      "train_steps_per_second": 10.437
     }
   ],
   "max_steps": 4371,