End of training

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 15.09,
+    "eval_accuracy": 0.49912070885378956,
+    "eval_loss": 2.791764736175537,
+    "eval_runtime": 402.3546,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 766.379,
+    "eval_steps_per_second": 15.969,
+    "perplexity": 16.309776873266287,
+    "train_loss": 3.300056499910879,
+    "train_runtime": 215976.5267,
+    "train_samples": 5858758,
+    "train_samples_per_second": 678.171,
+    "train_steps_per_second": 14.129
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 15.09,
+    "eval_accuracy": 0.49912070885378956,
+    "eval_loss": 2.791764736175537,
+    "eval_runtime": 402.3546,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 766.379,
+    "eval_steps_per_second": 15.969,
+    "perplexity": 16.309776873266287
+}

logs/events.out.tfevents.1687558443.serv-3334.2422611.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18d56a3972129f910b5982a95203f0e658414dfa32c967fa9535aa7a4cef19a
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 15.09,
+    "train_loss": 3.300056499910879,
+    "train_runtime": 215976.5267,
+    "train_samples": 5858758,
+    "train_samples_per_second": 678.171,
+    "train_steps_per_second": 14.129
+}