End of training

README.md

@@ -1,9 +1,15 @@
 ---
 base_model: Minbyul/selfbiorag-7b-wo-kqa_golden-iter-dpo-step3-filtered
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: selfbiorag-7b-wo-kqa_golden-iter-dpo-step4-filtered
   results: []
@@ -14,7 +20,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # selfbiorag-7b-wo-kqa_golden-iter-dpo-step4-filtered
 
-This model is a fine-tuned version of [Minbyul/selfbiorag-7b-wo-kqa_golden-iter-dpo-step3-filtered](https://huggingface.co/Minbyul/selfbiorag-7b-wo-kqa_golden-iter-dpo-step3-filtered) on an unknown dataset.
+This model is a fine-tuned version of [Minbyul/selfbiorag-7b-wo-kqa_golden-iter-dpo-step3-filtered](https://huggingface.co/Minbyul/selfbiorag-7b-wo-kqa_golden-iter-dpo-step3-filtered) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6766
+- Rewards/chosen: -0.0828
+- Rewards/rejected: -0.1144
+- Rewards/accuracies: 0.6319
+- Rewards/margins: 0.0316
+- Logps/rejected: -98.9601
+- Logps/chosen: -79.1920
+- Logits/rejected: -1.2073
+- Logits/chosen: -1.1930
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -1.1930192708969116,
+    "eval_logits/rejected": -1.2072994709014893,
+    "eval_logps/chosen": -79.19204711914062,
+    "eval_logps/rejected": -98.96011352539062,
+    "eval_loss": 0.6765820384025574,
+    "eval_rewards/accuracies": 0.6319444179534912,
+    "eval_rewards/chosen": -0.08277318626642227,
+    "eval_rewards/margins": 0.03162948787212372,
+    "eval_rewards/rejected": -0.11440268903970718,
+    "eval_runtime": 48.68,
+    "eval_samples": 567,
+    "eval_samples_per_second": 11.647,
+    "eval_steps_per_second": 0.37,
     "train_loss": 0.6676328546471066,
     "train_runtime": 2437.1919,
     "train_samples": 13823,

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": -1.1930192708969116,
+    "eval_logits/rejected": -1.2072994709014893,
+    "eval_logps/chosen": -79.19204711914062,
+    "eval_logps/rejected": -98.96011352539062,
+    "eval_loss": 0.6765820384025574,
+    "eval_rewards/accuracies": 0.6319444179534912,
+    "eval_rewards/chosen": -0.08277318626642227,
+    "eval_rewards/margins": 0.03162948787212372,
+    "eval_rewards/rejected": -0.11440268903970718,
+    "eval_runtime": 48.68,
+    "eval_samples": 567,
+    "eval_samples_per_second": 11.647,
+    "eval_steps_per_second": 0.37
+}