End of training

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 4.84,
     "eval_loss": 0.42781996726989746,
-    "eval_runtime": 624.4216,
-    "eval_samples_per_second": 5.801,
-    "eval_steps_per_second": 1.451,
+    "eval_runtime": 617.6877,
+    "eval_samples_per_second": 5.864,
+    "eval_steps_per_second": 1.467,
     "eval_wer": 17.437313089487002,
     "train_loss": 0.2648608121991158,
-    "train_runtime": 8027.4696,
-    "train_samples_per_second": 4.983,
-    "train_steps_per_second": 0.623
+    "train_runtime": 8065.0347,
+    "train_samples_per_second": 4.96,
+    "train_steps_per_second": 0.62
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.84,
     "eval_loss": 0.42781996726989746,
-    "eval_runtime": 624.4216,
-    "eval_samples_per_second": 5.801,
-    "eval_steps_per_second": 1.451,
+    "eval_runtime": 617.6877,
+    "eval_samples_per_second": 5.864,
+    "eval_steps_per_second": 1.467,
     "eval_wer": 17.437313089487002
 }

runs/Aug11_06-50-36_dsai-server/events.out.tfevents.1691720181.dsai-server

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b833ddab66184857775d2478b3a52b02da9f0f6020bc81c2fb2469716a9d2a1
+size 40

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 4.84,
     "train_loss": 0.2648608121991158,
-    "train_runtime": 8027.4696,
-    "train_samples_per_second": 4.983,
-    "train_steps_per_second": 0.623
+    "train_runtime": 8065.0347,
+    "train_samples_per_second": 4.96,
+    "train_steps_per_second": 0.62
 }

trainer_state.json

@@ -250,9 +250,9 @@
     {
       "epoch": 0.97,
       "eval_loss": 0.6284407377243042,
-      "eval_runtime": 640.3736,
-      "eval_samples_per_second": 5.656,
-      "eval_steps_per_second": 1.415,
+      "eval_runtime": 637.2881,
+      "eval_samples_per_second": 5.683,
+      "eval_steps_per_second": 1.422,
       "eval_wer": 31.727628249367378,
       "step": 1000
     },
@@ -499,9 +499,9 @@
     {
       "epoch": 1.94,
       "eval_loss": 0.5209963321685791,
-      "eval_runtime": 629.8045,
-      "eval_samples_per_second": 5.751,
-      "eval_steps_per_second": 1.439,
+      "eval_runtime": 640.3753,
+      "eval_samples_per_second": 5.656,
+      "eval_steps_per_second": 1.415,
       "eval_wer": 25.43823326432022,
       "step": 2000
     },
@@ -748,9 +748,9 @@
     {
       "epoch": 2.9,
       "eval_loss": 0.4795286953449249,
-      "eval_runtime": 634.3655,
-      "eval_samples_per_second": 5.71,
-      "eval_steps_per_second": 1.428,
+      "eval_runtime": 628.7529,
+      "eval_samples_per_second": 5.761,
+      "eval_steps_per_second": 1.441,
       "eval_wer": 22.921555095468136,
       "step": 3000
     },
@@ -997,9 +997,9 @@
     {
       "epoch": 3.87,
       "eval_loss": 0.45125144720077515,
-      "eval_runtime": 631.882,
-      "eval_samples_per_second": 5.732,
-      "eval_steps_per_second": 1.434,
+      "eval_runtime": 625.0491,
+      "eval_samples_per_second": 5.795,
+      "eval_steps_per_second": 1.449,
       "eval_wer": 19.871175523349436,
       "step": 4000
     },
@@ -1246,9 +1246,9 @@
     {
       "epoch": 4.84,
       "eval_loss": 0.42781996726989746,
-      "eval_runtime": 625.5945,
-      "eval_samples_per_second": 5.79,
-      "eval_steps_per_second": 1.448,
+      "eval_runtime": 622.9975,
+      "eval_samples_per_second": 5.814,
+      "eval_steps_per_second": 1.454,
       "eval_wer": 17.437313089487002,
       "step": 5000
     },
@@ -1257,9 +1257,9 @@
       "step": 5000,
       "total_flos": 1.153995298799616e+19,
       "train_loss": 0.2648608121991158,
-      "train_runtime": 8027.4696,
-      "train_samples_per_second": 4.983,
-      "train_steps_per_second": 0.623
+      "train_runtime": 8065.0347,
+      "train_samples_per_second": 4.96,
+      "train_steps_per_second": 0.62
     }
   ],
   "max_steps": 5000,