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: 0.4464
-- Rewards/chosen: 0.0179
-- Rewards/rejected: -0.0124
-- Rewards/accuracies: 0.5428
-- Rewards/margins: 0.0304
-- Logps/rejected: -37.5321
-- Logps/chosen: -34.0121
-- Logits/rejected: -2.2303
-- Logits/chosen: -2.2352
+- Loss: 0.4478
+- Rewards/chosen: 0.0102
+- Rewards/rejected: -0.0088
+- Rewards/accuracies: 0.5224
+- Rewards/margins: 0.0190
+- Logps/rejected: -37.5276
+- Logps/chosen: -34.0218
+- Logits/rejected: -2.2302
+- Logits/chosen: -2.2350
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.235046148300171,
+    "eval_logits/rejected": -2.230177640914917,
+    "eval_logps/chosen": -34.02177047729492,
+    "eval_logps/rejected": -37.52760696411133,
+    "eval_loss": 0.4478302299976349,
+    "eval_rewards/accuracies": 0.5224252939224243,
+    "eval_rewards/chosen": 0.010223164223134518,
+    "eval_rewards/margins": 0.01901474967598915,
+    "eval_rewards/rejected": -0.008791583590209484,
+    "eval_runtime": 145.7484,
+    "eval_samples": 343,
+    "eval_samples_per_second": 2.353,
+    "eval_steps_per_second": 0.295,
     "train_loss": 0.3756082092012678,
     "train_runtime": 3251.4223,
     "train_samples": 3079,

eval_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": -2.2309982776641846,
-    "eval_logits/rejected": -2.2261931896209717,
-    "eval_logps/chosen": -33.767173767089844,
-    "eval_logps/rejected": -37.282623291015625,
-    "eval_loss": 0.49339157342910767,
-    "eval_rewards/accuracies": 0.5456810593605042,
-    "eval_rewards/chosen": 0.21390400826931,
-    "eval_rewards/margins": 0.026708098128437996,
-    "eval_rewards/rejected": 0.18719588220119476,
-    "eval_runtime": 145.5786,
+    "eval_logits/chosen": -2.235046148300171,
+    "eval_logits/rejected": -2.230177640914917,
+    "eval_logps/chosen": -34.02177047729492,
+    "eval_logps/rejected": -37.52760696411133,
+    "eval_loss": 0.4478302299976349,
+    "eval_rewards/accuracies": 0.5224252939224243,
+    "eval_rewards/chosen": 0.010223164223134518,
+    "eval_rewards/margins": 0.01901474967598915,
+    "eval_rewards/rejected": -0.008791583590209484,
+    "eval_runtime": 145.7484,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.356,
+    "eval_samples_per_second": 2.353,
     "eval_steps_per_second": 0.295
 }