End of training

README.md

@@ -2,14 +2,28 @@
 license: cc-by-nc-4.0
 base_model: sfairXC/FsfairX-LLaMA3-RM-v0.1
 tags:
-- trl
-- reward-trainer
 - easylm
 - alignment-handbook
+- trl
+- reward-trainer
 - generated_from_trainer
+datasets:
+- helpsteer-rm
+metrics:
+- accuracy
 model-index:
 - name: easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: helpsteer-rm
+      type: helpsteer-rm
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.664756446991404
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,7 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
 
-This model is a fine-tuned version of [sfairXC/FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [sfairXC/FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) on the helpsteer-rm dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6508
+- Accuracy: 0.6648
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.6189111747851003,
-    "eval_loss": 0.6558019518852234,
-    "eval_runtime": 5.9654,
+    "eval_accuracy": 0.664756446991404,
+    "eval_loss": 0.6507900357246399,
+    "eval_runtime": 5.9367,
     "eval_samples": 349,
-    "eval_samples_per_second": 58.504,
-    "eval_steps_per_second": 7.376,
+    "eval_samples_per_second": 58.786,
+    "eval_steps_per_second": 7.411,
     "total_flos": 0.0,
     "train_loss": 0.7041080118083268,
     "train_runtime": 641.2149,

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128257
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.6189111747851003,
-    "eval_loss": 0.6558019518852234,
-    "eval_runtime": 5.9654,
+    "eval_accuracy": 0.664756446991404,
+    "eval_loss": 0.6507900357246399,
+    "eval_runtime": 5.9367,
     "eval_samples": 349,
-    "eval_samples_per_second": 58.504,
-    "eval_steps_per_second": 7.376
+    "eval_samples_per_second": 58.786,
+    "eval_steps_per_second": 7.411
 }