Model save

README.md

@@ -2,14 +2,10 @@
 license: apache-2.0
 library_name: peft
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
+- generated_from_trainer
 base_model: alignment-handbook/zephyr-7b-sft-full
-datasets:
-- updated
-- original
 model-index:
 - name: zephyr-7b-dpo-qlora-min-pi-part-0
   results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-qlora-min-pi-part-0
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the updated and the original datasets.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.77,
-    "train_loss": 0.692988375822703,
-    "train_runtime": 257.3561,
+    "train_loss": 0.69305553038915,
+    "train_runtime": 253.0881,
     "train_samples": 10000,
-    "train_samples_per_second": 3.886,
+    "train_samples_per_second": 3.951,
     "train_steps_per_second": 0.012
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.77,
-    "train_loss": 0.692988375822703,
-    "train_runtime": 257.3561,
+    "train_loss": 0.69305553038915,
+    "train_runtime": 253.0881,
     "train_samples": 10000,
-    "train_samples_per_second": 3.886,
+    "train_samples_per_second": 3.951,
     "train_steps_per_second": 0.012
 }

trainer_state.json

@@ -26,9 +26,9 @@
       "epoch": 0.77,
       "step": 3,
       "total_flos": 0.0,
-      "train_loss": 0.692988375822703,
-      "train_runtime": 257.3561,
-      "train_samples_per_second": 3.886,
+      "train_loss": 0.69305553038915,
+      "train_runtime": 253.0881,
+      "train_samples_per_second": 3.951,
       "train_steps_per_second": 0.012
     }
   ],