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: 0.4904
-- Rewards/chosen: 0.2570
-- Rewards/rejected: 0.2171
-- Rewards/accuracies: 0.5220
-- Rewards/margins: 0.0399
-- Logps/rejected: -37.2754
-- Logps/chosen: -33.7490
-- Logits/rejected: -2.2259
-- Logits/chosen: -2.2308
+- Loss: 0.4937
+- Rewards/chosen: 0.2548
+- Rewards/rejected: 0.2285
+- Rewards/accuracies: 0.5274
+- Rewards/margins: 0.0263
+- Logps/rejected: -37.2627
+- Logps/chosen: -33.7514
+- Logits/rejected: -2.2263
+- Logits/chosen: -2.2311
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.2310752868652344,
+    "eval_logits/rejected": -2.226254940032959,
+    "eval_logps/chosen": -33.75144958496094,
+    "eval_logps/rejected": -37.262733459472656,
+    "eval_loss": 0.49370110034942627,
+    "eval_rewards/accuracies": 0.5274086594581604,
+    "eval_rewards/chosen": 0.25479215383529663,
+    "eval_rewards/margins": 0.02629559487104416,
+    "eval_rewards/rejected": 0.22849655151367188,
+    "eval_runtime": 145.6018,
+    "eval_samples": 343,
+    "eval_samples_per_second": 2.356,
+    "eval_steps_per_second": 0.295,
     "train_loss": 0.447351616079157,
     "train_runtime": 3253.4458,
     "train_samples": 3079,

eval_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": -2.22967529296875,
-    "eval_logits/rejected": -2.2248213291168213,
-    "eval_logps/chosen": -34.096519470214844,
-    "eval_logps/rejected": -37.601966857910156,
-    "eval_loss": 0.6981170177459717,
-    "eval_rewards/accuracies": 0.545265793800354,
-    "eval_rewards/chosen": -0.0557732917368412,
-    "eval_rewards/margins": 0.021040165796875954,
-    "eval_rewards/rejected": -0.07681345194578171,
-    "eval_runtime": 145.6397,
+    "eval_logits/chosen": -2.2310752868652344,
+    "eval_logits/rejected": -2.226254940032959,
+    "eval_logps/chosen": -33.75144958496094,
+    "eval_logps/rejected": -37.262733459472656,
+    "eval_loss": 0.49370110034942627,
+    "eval_rewards/accuracies": 0.5274086594581604,
+    "eval_rewards/chosen": 0.25479215383529663,
+    "eval_rewards/margins": 0.02629559487104416,
+    "eval_rewards/rejected": 0.22849655151367188,
+    "eval_runtime": 145.6018,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.355,
+    "eval_samples_per_second": 2.356,
     "eval_steps_per_second": 0.295
 }