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_baseline
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-3.1-8B-Instruct_baseline
 
-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 baseline dataset.
 
 ## Model description
 

all_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.9942196531791907,
     "total_flos": 8626483251118080.0,
     "train_loss": 0.6937350367390832,
-    "train_runtime": 232.7569,
-    "train_samples_per_second": 1.482,
-    "train_steps_per_second": 0.185
+    "train_runtime": 231.1609,
+    "train_samples_per_second": 1.492,
+    "train_steps_per_second": 0.186
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.9942196531791907,
     "total_flos": 8626483251118080.0,
     "train_loss": 0.6937350367390832,
-    "train_runtime": 232.7569,
-    "train_samples_per_second": 1.482,
-    "train_steps_per_second": 0.185
+    "train_runtime": 231.1609,
+    "train_samples_per_second": 1.492,
+    "train_steps_per_second": 0.186
 }

trainer_state.json

@@ -223,9 +223,9 @@
       "step": 43,
       "total_flos": 8626483251118080.0,
       "train_loss": 0.6937350367390832,
-      "train_runtime": 232.7569,
-      "train_samples_per_second": 1.482,
-      "train_steps_per_second": 0.185
+      "train_runtime": 231.1609,
+      "train_samples_per_second": 1.492,
+      "train_steps_per_second": 0.186
     }
   ],
   "logging_steps": 3,