End of training

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.33660520215315354,
+    "eval_loss": 4.140918254852295,
+    "eval_runtime": 346.5619,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 889.757,
+    "eval_steps_per_second": 18.539,
+    "perplexity": 62.8605169302589,
+    "train_loss": 4.73325779911465,
+    "train_runtime": 51385.934,
+    "train_samples": 5858758,
+    "train_samples_per_second": 570.074,
+    "train_steps_per_second": 11.877
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.33660520215315354,
+    "eval_loss": 4.140918254852295,
+    "eval_runtime": 346.5619,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 889.757,
+    "eval_steps_per_second": 18.539,
+    "perplexity": 62.8605169302589
+}

logs/events.out.tfevents.1687307498.serv-3329.724957.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbf3333ccabd9b427e376a8bf1fdff453961506244d4247c0a4dbda5138915c
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 4.73325779911465,
+    "train_runtime": 51385.934,
+    "train_samples": 5858758,
+    "train_samples_per_second": 570.074,
+    "train_steps_per_second": 11.877
+}