End of training

README.md

@@ -2,6 +2,7 @@
 license: cc-by-nc-4.0
 base_model: sfairXC/FsfairX-LLaMA3-RM-v0.1
 tags:
+- easylm
 - trl
 - reward-trainer
 - generated_from_trainer
@@ -19,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.4829
-- Accuracy: 0.7872
+- Loss: 0.4821
+- Accuracy: 0.7784
 
 ## Model description
 

all_results.json

@@ -1,5 +1,11 @@
 {
     "epoch": 1.0,
+    "eval_accuracy": 0.7784256559766763,
+    "eval_loss": 0.48211508989334106,
+    "eval_runtime": 39.2057,
+    "eval_samples": 360,
+    "eval_samples_per_second": 8.749,
+    "eval_steps_per_second": 2.194,
     "total_flos": 0.0,
     "train_loss": 0.5596484089945699,
     "train_runtime": 4783.2861,

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

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.7784256559766763,
+    "eval_loss": 0.48211508989334106,
+    "eval_runtime": 39.2057,
+    "eval_samples": 360,
+    "eval_samples_per_second": 8.749,
+    "eval_steps_per_second": 2.194
+}