End of training

README.md

@@ -1,11 +1,13 @@
 ---
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
-- alignment-handbook
 - generated_from_trainer
 base_model: NbAiLab/nb-gpt-j-6B-v2
+datasets:
+- hugodk-sch/aftonposten_title_prefs
 model-index:
 - name: aftonposten-6b-align-scan
   results: []
@@ -16,17 +18,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # aftonposten-6b-align-scan
 
-This model is a fine-tuned version of [NbAiLab/nb-gpt-j-6B-v2](https://huggingface.co/NbAiLab/nb-gpt-j-6B-v2) on an unknown dataset.
+This model is a fine-tuned version of [data/ap-gpt-j-6b-sft-qlora-04-08](https://huggingface.co/data/ap-gpt-j-6b-sft-qlora-04-08) on the hugodk-sch/aftonposten_title_prefs dataset.
 It achieves the following results on the evaluation set:
-- Logits/chosen: -2.2437
-- Logits/rejected: -2.2388
-- Logps/chosen: -34.0263
-- Logps/rejected: -37.5052
-- Loss: 1.0020
-- Rewards/accuracies: 0.4635
-- Rewards/chosen: 0.0050
-- Rewards/margins: -0.0019
-- Rewards/rejected: 0.0068
+- Loss: 1.0085
+- Rewards/chosen: -0.0006
+- Rewards/rejected: 0.0077
+- Rewards/accuracies: 0.4817
+- Rewards/margins: -0.0083
+- Logps/rejected: -37.5037
+- Logps/chosen: -34.0355
+- Logits/rejected: -2.2391
+- Logits/chosen: -2.2440
 
 ## Model description
 

all_results.json

@@ -9,10 +9,10 @@
     "eval_rewards/chosen": -0.0005728387623094022,
     "eval_rewards/margins": -0.008305290713906288,
     "eval_rewards/rejected": 0.007732452359050512,
-    "eval_runtime": 145.8784,
+    "eval_runtime": 146.1229,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.351,
-    "eval_steps_per_second": 0.295,
+    "eval_samples_per_second": 2.347,
+    "eval_steps_per_second": 0.294,
     "train_loss": 0.21985046337177228,
     "train_runtime": 627.6127,
     "train_samples": 3079,

eval_results.json

@@ -9,8 +9,8 @@
     "eval_rewards/chosen": -0.0005728387623094022,
     "eval_rewards/margins": -0.008305290713906288,
     "eval_rewards/rejected": 0.007732452359050512,
-    "eval_runtime": 145.8784,
+    "eval_runtime": 146.1229,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.351,
-    "eval_steps_per_second": 0.295
+    "eval_samples_per_second": 2.347,
+    "eval_steps_per_second": 0.294
 }