End of training

README.md

@@ -3,10 +3,10 @@ library_name: peft
 license: llama3.1
 base_model: meta-llama/Llama-3.1-8B-Instruct
 tags:
-- trl
-- dpo
 - llama-factory
 - lora
+- trl
+- dpo
 - generated_from_trainer
 model-index:
 - name: Llama-3.1-8B-Instruct_holistic
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-3.1-8B-Instruct_holistic
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the holistic dataset.
 
 ## Model description
 

all_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.9997303855486654,
     "total_flos": 1.1904720283191214e+18,
     "train_loss": 0.15248539275464632,
-    "train_runtime": 30996.046,
-    "train_samples_per_second": 0.479,
+    "train_runtime": 30932.1025,
+    "train_samples_per_second": 0.48,
     "train_steps_per_second": 0.06
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.9997303855486654,
     "total_flos": 1.1904720283191214e+18,
     "train_loss": 0.15248539275464632,
-    "train_runtime": 30996.046,
-    "train_samples_per_second": 0.479,
+    "train_runtime": 30932.1025,
+    "train_samples_per_second": 0.48,
     "train_steps_per_second": 0.06
 }

trainer_state.json

@@ -298,8 +298,8 @@
       "step": 1854,
       "total_flos": 1.1904720283191214e+18,
       "train_loss": 0.15248539275464632,
-      "train_runtime": 30996.046,
-      "train_samples_per_second": 0.479,
+      "train_runtime": 30932.1025,
+      "train_samples_per_second": 0.48,
       "train_steps_per_second": 0.06
     }
   ],