End of training

README.md

@@ -1,10 +1,13 @@
 ---
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - 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: []
@@ -15,17 +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:
-- Loss: 0.6903
-- Rewards/chosen: -0.0237
-- Rewards/rejected: -0.0486
-- Rewards/accuracies: 0.5191
-- Rewards/margins: 0.0249
-- Logps/rejected: -37.5860
-- Logps/chosen: -34.0684
-- Logits/rejected: -2.2229
-- Logits/chosen: -2.2277
+- Loss: 0.6957
+- Rewards/chosen: -0.0294
+- Rewards/rejected: -0.0431
+- Rewards/accuracies: 0.5158
+- Rewards/margins: 0.0138
+- Logps/rejected: -37.5783
+- Logps/chosen: -34.0765
+- Logits/rejected: -2.2231
+- Logits/chosen: -2.2280
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.227961301803589,
+    "eval_logits/rejected": -2.2231268882751465,
+    "eval_logps/chosen": -34.07651138305664,
+    "eval_logps/rejected": -37.578250885009766,
+    "eval_loss": 0.6956681609153748,
+    "eval_rewards/accuracies": 0.5157807469367981,
+    "eval_rewards/chosen": -0.029370848089456558,
+    "eval_rewards/margins": 0.013771643862128258,
+    "eval_rewards/rejected": -0.043142493814229965,
+    "eval_runtime": 145.5641,
+    "eval_samples": 343,
+    "eval_samples_per_second": 2.356,
+    "eval_steps_per_second": 0.295,
     "train_loss": 0.6291831790626823,
     "train_runtime": 3251.1508,
     "train_samples": 3079,

eval_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": -2.223938465118408,
-    "eval_logits/rejected": -2.2191123962402344,
-    "eval_logps/chosen": -34.10564041137695,
-    "eval_logps/rejected": -37.63585662841797,
-    "eval_loss": 0.9714530110359192,
-    "eval_rewards/accuracies": 0.5365448594093323,
-    "eval_rewards/chosen": -0.042656492441892624,
-    "eval_rewards/margins": 0.028885547071695328,
-    "eval_rewards/rejected": -0.07154203206300735,
-    "eval_runtime": 145.6066,
+    "eval_logits/chosen": -2.227961301803589,
+    "eval_logits/rejected": -2.2231268882751465,
+    "eval_logps/chosen": -34.07651138305664,
+    "eval_logps/rejected": -37.578250885009766,
+    "eval_loss": 0.6956681609153748,
+    "eval_rewards/accuracies": 0.5157807469367981,
+    "eval_rewards/chosen": -0.029370848089456558,
+    "eval_rewards/margins": 0.013771643862128258,
+    "eval_rewards/rejected": -0.043142493814229965,
+    "eval_runtime": 145.5641,
     "eval_samples": 343,
     "eval_samples_per_second": 2.356,
     "eval_steps_per_second": 0.295