End of training

README.md

@@ -1,10 +1,14 @@
 ---
+license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b
   results: []
@@ -15,19 +19,19 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-qlora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-qlora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6907
+- Loss: 0.6906
 - Rewards/chosen: -0.3413
-- Rewards/rejected: -0.5651
+- Rewards/rejected: -0.5652
 - Rewards/accuracies: 0.3631
-- Rewards/margins: 0.2238
-- Logps/rejected: -131.9111
-- Logps/chosen: -103.0301
-- Logits/rejected: -0.1367
-- Logits/chosen: -0.2437
-- Use Label: 14866.4766
-- Pred Label: 3821.5239
+- Rewards/margins: 0.2239
+- Logps/rejected: -131.9189
+- Logps/chosen: -103.0295
+- Logits/rejected: -0.1381
+- Logits/chosen: -0.2453
+- Use Label: 15879.8574
+- Pred Label: 4192.1431
 
 ## Model description
 

all_results.json

@@ -1,5 +1,20 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -0.24525223672389984,
+    "eval_logits/rejected": -0.1380803883075714,
+    "eval_logps/chosen": -103.02954864501953,
+    "eval_logps/rejected": -131.91891479492188,
+    "eval_loss": 0.6906174421310425,
+    "eval_pred_label": 4192.14306640625,
+    "eval_rewards/accuracies": 0.363095223903656,
+    "eval_rewards/chosen": -0.3412899374961853,
+    "eval_rewards/margins": 0.22391849756240845,
+    "eval_rewards/rejected": -0.5652084350585938,
+    "eval_runtime": 247.5585,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 8.079,
+    "eval_steps_per_second": 0.254,
+    "eval_use_label": 15879.857421875,
     "train_loss": 0.6880922077838039,
     "train_runtime": 20023.3666,
     "train_samples": 61135,

eval_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": 1.3711830377578735,
-    "eval_logits/rejected": 1.4916048049926758,
-    "eval_logps/chosen": -123.7209243774414,
-    "eval_logps/rejected": -161.63131713867188,
-    "eval_loss": 0.6788680553436279,
-    "eval_pred_label": 2490.952392578125,
-    "eval_rewards/accuracies": 0.3591269850730896,
-    "eval_rewards/chosen": -0.548203706741333,
-    "eval_rewards/margins": 0.3141288757324219,
-    "eval_rewards/rejected": -0.8623325824737549,
-    "eval_runtime": 247.4536,
+    "eval_logits/chosen": -0.24525223672389984,
+    "eval_logits/rejected": -0.1380803883075714,
+    "eval_logps/chosen": -103.02954864501953,
+    "eval_logps/rejected": -131.91891479492188,
+    "eval_loss": 0.6906174421310425,
+    "eval_pred_label": 4192.14306640625,
+    "eval_rewards/accuracies": 0.363095223903656,
+    "eval_rewards/chosen": -0.3412899374961853,
+    "eval_rewards/margins": 0.22391849756240845,
+    "eval_rewards/rejected": -0.5652084350585938,
+    "eval_runtime": 247.5585,
     "eval_samples": 2000,
-    "eval_samples_per_second": 8.082,
-    "eval_steps_per_second": 0.255,
-    "eval_use_label": 17581.046875
+    "eval_samples_per_second": 8.079,
+    "eval_steps_per_second": 0.254,
+    "eval_use_label": 15879.857421875
 }