End of training

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 2.42,
     "eval_loss": 0.4997063875198364,
-    "eval_runtime": 301.6796,
-    "eval_samples_per_second": 12.006,
-    "eval_steps_per_second": 6.003,
+    "eval_runtime": 1863.5809,
+    "eval_samples_per_second": 1.944,
+    "eval_steps_per_second": 0.972,
     "eval_wer": 32.55118472509777,
     "train_loss": 0.557375843334198,
-    "train_runtime": 3189.4145,
-    "train_samples_per_second": 6.271,
-    "train_steps_per_second": 1.568
+    "train_runtime": 15732.1346,
+    "train_samples_per_second": 1.271,
+    "train_steps_per_second": 0.318
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.42,
     "eval_loss": 0.4997063875198364,
-    "eval_runtime": 301.6796,
-    "eval_samples_per_second": 12.006,
-    "eval_steps_per_second": 6.003,
+    "eval_runtime": 1863.5809,
+    "eval_samples_per_second": 1.944,
+    "eval_steps_per_second": 0.972,
     "eval_wer": 32.55118472509777
 }

runs/Aug06_15-17-30_dsai-server/events.out.tfevents.1691327490.dsai-server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa5e50dd77bf7ea5c0b55f72aef37b60e071b7908e122f5ad6463de79711c46
+size 40

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.42,
     "train_loss": 0.557375843334198,
-    "train_runtime": 3189.4145,
-    "train_samples_per_second": 6.271,
-    "train_steps_per_second": 1.568
+    "train_runtime": 15732.1346,
+    "train_samples_per_second": 1.271,
+    "train_steps_per_second": 0.318
 }

trainer_state.json

@@ -250,9 +250,9 @@
     {
       "epoch": 0.48,
       "eval_loss": 0.6328660845756531,
-      "eval_runtime": 460.419,
-      "eval_samples_per_second": 7.867,
-      "eval_steps_per_second": 3.933,
+      "eval_runtime": 2032.5756,
+      "eval_samples_per_second": 1.782,
+      "eval_steps_per_second": 0.891,
       "eval_wer": 42.10720036806993,
       "step": 1000
     },
@@ -499,9 +499,9 @@
     {
       "epoch": 0.97,
       "eval_loss": 0.5514832139015198,
-      "eval_runtime": 480.2784,
-      "eval_samples_per_second": 7.541,
-      "eval_steps_per_second": 3.771,
+      "eval_runtime": 1912.9967,
+      "eval_samples_per_second": 1.893,
+      "eval_steps_per_second": 0.947,
       "eval_wer": 35.86381412468369,
       "step": 2000
     },
@@ -748,9 +748,9 @@
     {
       "epoch": 1.45,
       "eval_loss": 0.5231785178184509,
-      "eval_runtime": 382.6621,
-      "eval_samples_per_second": 9.465,
-      "eval_steps_per_second": 4.733,
+      "eval_runtime": 1911.8055,
+      "eval_samples_per_second": 1.895,
+      "eval_steps_per_second": 0.947,
       "eval_wer": 34.018863584080975,
       "step": 3000
     },
@@ -997,9 +997,9 @@
     {
       "epoch": 1.94,
       "eval_loss": 0.49930620193481445,
-      "eval_runtime": 422.5521,
-      "eval_samples_per_second": 8.572,
-      "eval_steps_per_second": 4.286,
+      "eval_runtime": 1866.5046,
+      "eval_samples_per_second": 1.941,
+      "eval_steps_per_second": 0.97,
       "eval_wer": 32.67080745341615,
       "step": 4000
     },
@@ -1246,9 +1246,9 @@
     {
       "epoch": 2.42,
       "eval_loss": 0.4997063875198364,
-      "eval_runtime": 496.1951,
-      "eval_samples_per_second": 7.3,
-      "eval_steps_per_second": 3.65,
+      "eval_runtime": 1867.4461,
+      "eval_samples_per_second": 1.94,
+      "eval_steps_per_second": 0.97,
       "eval_wer": 32.55118472509777,
       "step": 5000
     },
@@ -1257,9 +1257,9 @@
       "step": 5000,
       "total_flos": 4.9222998908928e+17,
       "train_loss": 0.557375843334198,
-      "train_runtime": 3189.4145,
-      "train_samples_per_second": 6.271,
-      "train_steps_per_second": 1.568
+      "train_runtime": 15732.1346,
+      "train_samples_per_second": 1.271,
+      "train_steps_per_second": 0.318
     }
   ],
   "max_steps": 5000,