End of training

README.md

@@ -2,6 +2,7 @@
 license: gemma
 base_model: scottsuk0306/easylm-sft-gemma-2-2b
 tags:
+- easylm
 - trl
 - reward-trainer
 - generated_from_trainer

all_results.json

@@ -1,5 +1,11 @@
 {
     "epoch": 1.0,
+    "eval_accuracy": 0.6145833333333334,
+    "eval_loss": 0.6525471806526184,
+    "eval_runtime": 0.6682,
+    "eval_samples": 96,
+    "eval_samples_per_second": 143.664,
+    "eval_steps_per_second": 8.979,
     "total_flos": 0.0,
     "train_loss": 0.6666407775878906,
     "train_runtime": 1051.6323,

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.5833333333333334,
-    "eval_loss": 6.046913146972656,
-    "eval_runtime": 1.6752,
+    "epoch": 1.0,
+    "eval_accuracy": 0.6145833333333334,
+    "eval_loss": 0.6525471806526184,
+    "eval_runtime": 0.6682,
     "eval_samples": 96,
-    "eval_samples_per_second": 57.307,
-    "eval_steps_per_second": 14.327
+    "eval_samples_per_second": 143.664,
+    "eval_steps_per_second": 8.979
 }