End of training

README.md

@@ -2,12 +2,28 @@
 license: gemma
 base_model: google/gemma-2-9b-it
 tags:
+- easylm
+- alignment-handbook
 - trl
 - reward-trainer
 - generated_from_trainer
+datasets:
+- helpsteer-rm
+metrics:
+- accuracy
 model-index:
 - name: easylm-helpsteer-rm-gemma-2-9b-it
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: helpsteer-rm
+      type: helpsteer-rm
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6473988439306358
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # easylm-helpsteer-rm-gemma-2-9b-it
 
-This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on the helpsteer-rm dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6336
+- Accuracy: 0.6474
 
 ## Model description
 

all_results.json

@@ -1,5 +1,11 @@
 {
     "epoch": 1.0,
+    "eval_accuracy": 0.6473988439306358,
+    "eval_loss": 0.6336098313331604,
+    "eval_runtime": 9.9434,
+    "eval_samples": 346,
+    "eval_samples_per_second": 34.797,
+    "eval_steps_per_second": 4.425,
     "total_flos": 0.0,
     "train_loss": 0.678250733167115,
     "train_runtime": 2802.1852,

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.6473988439306358,
+    "eval_loss": 0.6336098313331604,
+    "eval_runtime": 9.9434,
+    "eval_samples": 346,
+    "eval_samples_per_second": 34.797,
+    "eval_steps_per_second": 4.425
+}