End of training

README.md

@@ -1,9 +1,15 @@
 ---
 base_model: dmis-lab/selfbiorag_7b
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: selfbiorag-7b-dpo-full-wo-kqa_golden-ep3
   results: []
@@ -14,17 +20,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # selfbiorag-7b-dpo-full-wo-kqa_golden-ep3
 
-This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on an unknown dataset.
+This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Logits/chosen: -1.8108
-- Logits/rejected: -1.5449
-- Logps/chosen: -121.3720
-- Logps/rejected: -144.0564
 - Loss: 0.6355
-- Rewards/accuracies: 0.7326
 - Rewards/chosen: 0.1376
-- Rewards/margins: 0.1371
-- Rewards/rejected: 0.0005
+- Rewards/rejected: -0.0007
+- Rewards/accuracies: 0.7326
+- Rewards/margins: 0.1383
+- Logps/rejected: -144.1728
+- Logps/chosen: -121.3669
+- Logits/rejected: -1.5473
+- Logits/chosen: -1.8108
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -1.8107545375823975,
+    "eval_logits/rejected": -1.547254204750061,
+    "eval_logps/chosen": -121.36690521240234,
+    "eval_logps/rejected": -144.17279052734375,
+    "eval_loss": 0.6354531049728394,
+    "eval_rewards/accuracies": 0.7326388955116272,
+    "eval_rewards/chosen": 0.1376209855079651,
+    "eval_rewards/margins": 0.13830368220806122,
+    "eval_rewards/rejected": -0.0006826933822594583,
+    "eval_runtime": 108.9795,
+    "eval_samples": 1144,
+    "eval_samples_per_second": 10.497,
+    "eval_steps_per_second": 0.33,
     "train_loss": 0.05915545343278764,
     "train_runtime": 553.7697,
     "train_samples": 28436,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32016
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.8107545375823975,
+    "eval_logits/rejected": -1.547254204750061,
+    "eval_logps/chosen": -121.36690521240234,
+    "eval_logps/rejected": -144.17279052734375,
+    "eval_loss": 0.6354531049728394,
+    "eval_rewards/accuracies": 0.7326388955116272,
+    "eval_rewards/chosen": 0.1376209855079651,
+    "eval_rewards/margins": 0.13830368220806122,
+    "eval_rewards/rejected": -0.0006826933822594583,
+    "eval_runtime": 108.9795,
+    "eval_samples": 1144,
+    "eval_samples_per_second": 10.497,
+    "eval_steps_per_second": 0.33
+}