End of training

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 624.0,
     "eval_loss": 0.9921010732650757,
-    "eval_runtime": 133.8288,
-    "eval_samples_per_second": 9.243,
-    "eval_steps_per_second": 0.291,
+    "eval_runtime": 135.7332,
+    "eval_samples_per_second": 9.113,
+    "eval_steps_per_second": 0.287,
     "eval_wer": 34.21715788320368,
     "train_loss": 0.02765977076081908,
-    "train_runtime": 26219.657,
-    "train_samples_per_second": 12.205,
+    "train_runtime": 26145.1461,
+    "train_samples_per_second": 12.239,
     "train_steps_per_second": 0.191
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 624.0,
     "eval_loss": 0.9921010732650757,
-    "eval_runtime": 133.8288,
-    "eval_samples_per_second": 9.243,
-    "eval_steps_per_second": 0.291,
+    "eval_runtime": 135.7332,
+    "eval_samples_per_second": 9.113,
+    "eval_steps_per_second": 0.287,
     "eval_wer": 34.21715788320368
 }

runs/Dec05_00-34-16_spartan-gpgpu111.hpc.unimelb.edu.au/events.out.tfevents.1670187201.spartan-gpgpu111.hpc.unimelb.edu.au

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433f5889c525703f31ef1069f851311928d9ad29a52f11d06b4d80a637ac2f58
+size 40

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 624.0,
     "train_loss": 0.02765977076081908,
-    "train_runtime": 26219.657,
-    "train_samples_per_second": 12.205,
+    "train_runtime": 26145.1461,
+    "train_samples_per_second": 12.239,
     "train_steps_per_second": 0.191
 }

trainer_state.json

@@ -250,9 +250,9 @@
     {
       "epoch": 124.0,
       "eval_loss": 0.7998368740081787,
-      "eval_runtime": 126.5818,
-      "eval_samples_per_second": 9.772,
-      "eval_steps_per_second": 0.308,
+      "eval_runtime": 130.4981,
+      "eval_samples_per_second": 9.479,
+      "eval_steps_per_second": 0.299,
       "eval_wer": 21.770570833789854,
       "step": 1000
     },
@@ -499,8 +499,8 @@
     {
       "epoch": 249.0,
       "eval_loss": 0.8832917213439941,
-      "eval_runtime": 131.8081,
-      "eval_samples_per_second": 9.385,
+      "eval_runtime": 131.7792,
+      "eval_samples_per_second": 9.387,
       "eval_steps_per_second": 0.296,
       "eval_wer": 28.968993097403313,
       "step": 2000
@@ -748,9 +748,9 @@
     {
       "epoch": 374.0,
       "eval_loss": 0.9381842613220215,
-      "eval_runtime": 131.6496,
-      "eval_samples_per_second": 9.396,
-      "eval_steps_per_second": 0.296,
+      "eval_runtime": 133.2813,
+      "eval_samples_per_second": 9.281,
+      "eval_steps_per_second": 0.293,
       "eval_wer": 30.820642051057302,
       "step": 3000
     },
@@ -997,9 +997,9 @@
     {
       "epoch": 499.0,
       "eval_loss": 0.9754325151443481,
-      "eval_runtime": 133.2255,
-      "eval_samples_per_second": 9.285,
-      "eval_steps_per_second": 0.293,
+      "eval_runtime": 133.3867,
+      "eval_samples_per_second": 9.274,
+      "eval_steps_per_second": 0.292,
       "eval_wer": 34.436287936890544,
       "step": 4000
     },
@@ -1246,9 +1246,9 @@
     {
       "epoch": 624.0,
       "eval_loss": 0.9921010732650757,
-      "eval_runtime": 133.2536,
-      "eval_samples_per_second": 9.283,
-      "eval_steps_per_second": 0.293,
+      "eval_runtime": 136.0036,
+      "eval_samples_per_second": 9.095,
+      "eval_steps_per_second": 0.287,
       "eval_wer": 34.21715788320368,
       "step": 5000
     },
@@ -1257,8 +1257,8 @@
       "step": 5000,
       "total_flos": 8.94614740992e+19,
       "train_loss": 0.02765977076081908,
-      "train_runtime": 26219.657,
-      "train_samples_per_second": 12.205,
+      "train_runtime": 26145.1461,
+      "train_samples_per_second": 12.239,
       "train_steps_per_second": 0.191
     }
   ],