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: 0.9761
-- Rewards/chosen: -0.0366
-- Rewards/rejected: -0.0616
-- Rewards/accuracies: 0.5299
-- Rewards/margins: 0.0250
-- Logps/rejected: -37.6047
-- Logps/chosen: -34.0868
-- Logits/rejected: -2.2186
-- Logits/chosen: -2.2234
+- Loss: 0.9658
+- Rewards/chosen: -0.0301
+- Rewards/rejected: -0.0652
+- Rewards/accuracies: 0.5278
+- Rewards/margins: 0.0352
+- Logps/rejected: -37.6098
+- Logps/chosen: -34.0775
+- Logits/rejected: -2.2182
+- Logits/chosen: -2.2231
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.2230520248413086,
+    "eval_logits/rejected": -2.2182328701019287,
+    "eval_logps/chosen": -34.07753372192383,
+    "eval_logps/rejected": -37.60981750488281,
+    "eval_loss": 0.9658033847808838,
+    "eval_rewards/accuracies": 0.5278239250183105,
+    "eval_rewards/chosen": -0.03008819743990898,
+    "eval_rewards/margins": 0.03515118733048439,
+    "eval_rewards/rejected": -0.06523937731981277,
+    "eval_runtime": 145.6671,
+    "eval_samples": 343,
+    "eval_samples_per_second": 2.355,
+    "eval_steps_per_second": 0.295,
     "train_loss": 0.8438688600218142,
     "train_runtime": 3250.9917,
     "train_samples": 3079,

eval_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": -2.236751079559326,
-    "eval_logits/rejected": -2.2318832874298096,
-    "eval_logps/chosen": -34.04561233520508,
-    "eval_logps/rejected": -37.546016693115234,
-    "eval_loss": 0.5836836099624634,
-    "eval_rewards/accuracies": 0.5427741408348083,
-    "eval_rewards/chosen": -0.007742464076727629,
-    "eval_rewards/margins": 0.01283606793731451,
-    "eval_rewards/rejected": -0.02057853527367115,
-    "eval_runtime": 145.5744,
+    "eval_logits/chosen": -2.2230520248413086,
+    "eval_logits/rejected": -2.2182328701019287,
+    "eval_logps/chosen": -34.07753372192383,
+    "eval_logps/rejected": -37.60981750488281,
+    "eval_loss": 0.9658033847808838,
+    "eval_rewards/accuracies": 0.5278239250183105,
+    "eval_rewards/chosen": -0.03008819743990898,
+    "eval_rewards/margins": 0.03515118733048439,
+    "eval_rewards/rejected": -0.06523937731981277,
+    "eval_runtime": 145.6671,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.356,
+    "eval_samples_per_second": 2.355,
     "eval_steps_per_second": 0.295
 }