End of training

README.md

@@ -1,7 +1,8 @@
 ---
 license: gemma
-base_model: scottsuk0306/easylm-helpsteer-sft-gemma-2-2b
+base_model: google/gemma-2-2b
 tags:
+- easylm
 - trl
 - reward-trainer
 - generated_from_trainer
@@ -17,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # easylm-helpsteer-rm-gemma-2-2b
 
-This model is a fine-tuned version of [scottsuk0306/easylm-helpsteer-sft-gemma-2-2b](https://huggingface.co/scottsuk0306/easylm-helpsteer-sft-gemma-2-2b) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.9740
-- Accuracy: 0.6324
+- Loss: 2.9694
+- Accuracy: 0.6265
 
 ## Model description
 

all_results.json

@@ -1,5 +1,11 @@
 {
     "epoch": 1.0,
+    "eval_accuracy": 0.6264705882352941,
+    "eval_loss": 2.9693546295166016,
+    "eval_runtime": 8.8918,
+    "eval_samples": 360,
+    "eval_samples_per_second": 38.237,
+    "eval_steps_per_second": 9.559,
     "total_flos": 0.0,
     "train_loss": 0.3749335529650852,
     "train_runtime": 2207.4532,

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.6264705882352941,
+    "eval_loss": 2.9693546295166016,
+    "eval_runtime": 8.8918,
+    "eval_samples": 360,
+    "eval_samples_per_second": 38.237,
+    "eval_steps_per_second": 9.559
+}