End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+trainer_state.json filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.51,
+    "eval_accuracy": 0.5132771737559237,
+    "eval_loss": 2.8040947914123535,
+    "eval_runtime": 2265.3898,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 136.116,
+    "eval_steps_per_second": 4.254,
+    "perplexity": 16.51212222414554,
+    "train_loss": 3.3242818601656663,
+    "train_runtime": 86379.0127,
+    "train_samples": 5858758,
+    "train_samples_per_second": 339.131,
+    "train_steps_per_second": 10.598
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.51,
+    "eval_accuracy": 0.5132771737559237,
+    "eval_loss": 2.8040947914123535,
+    "eval_runtime": 2265.3898,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 136.116,
+    "eval_steps_per_second": 4.254,
+    "perplexity": 16.51212222414554
+}

logs/events.out.tfevents.1689648537.serv-9225.3377895.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4156b549fb828333a11056559af3252bab16fb434b9d8d4b27e9e28abd47cf
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.51,
+    "train_loss": 3.3242818601656663,
+    "train_runtime": 86379.0127,
+    "train_samples": 5858758,
+    "train_samples_per_second": 339.131,
+    "train_steps_per_second": 10.598
+}

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26b32ae38c962df03b8d8ab16ba31d8d372e5e4efde1817467f2950f30aada6
+size 11179809