End of training

.gitattributes

@@ -32,3 +32,4 @@ 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": 1.65,
+    "eval_accuracy": 0.18952485208526926,
+    "eval_loss": 5.410121917724609,
+    "eval_runtime": 1553.7531,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 198.459,
+    "eval_steps_per_second": 4.135,
+    "perplexity": 223.65885399695668,
+    "train_loss": 5.57738281807273,
+    "train_runtime": 172795.3773,
+    "train_samples": 5858758,
+    "train_samples_per_second": 169.529,
+    "train_steps_per_second": 3.532
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.65,
+    "eval_accuracy": 0.18952485208526926,
+    "eval_loss": 5.410121917724609,
+    "eval_runtime": 1553.7531,
+    "eval_samples": 308356,
+    "eval_samples_per_second": 198.459,
+    "eval_steps_per_second": 4.135,
+    "perplexity": 223.65885399695668
+}

logs/events.out.tfevents.1686853407.serv-3317.2171480.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01d00c764ed6a03cadf863e40bb9414d74254395abda78474cf73a40a429fc4
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.65,
+    "train_loss": 5.57738281807273,
+    "train_runtime": 172795.3773,
+    "train_samples": 5858758,
+    "train_samples_per_second": 169.529,
+    "train_steps_per_second": 3.532
+}

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e081c9e2b9147961961ae8330d87c1a4c8dab7c3ef4b524c92397710bb488b
+size 24467803