End of training

README.md

@@ -2,10 +2,16 @@
 license: llama3
 base_model: Minbyul/llama3-8b-instruct-wo-kqa_golden-iter-sft-step1
 tags:
+- alignment-handbook
+- trl
+- dpo
+- generated_from_trainer
 - trl
 - dpo
 - alignment-handbook
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: llama3-8b-instruct-wo-kqa_golden-iter-dpo-step1
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-8b-instruct-wo-kqa_golden-iter-dpo-step1
 
-This model is a fine-tuned version of [Minbyul/llama3-8b-instruct-wo-kqa_golden-iter-sft-step1](https://huggingface.co/Minbyul/llama3-8b-instruct-wo-kqa_golden-iter-sft-step1) on an unknown dataset.
+This model is a fine-tuned version of [Minbyul/llama3-8b-instruct-wo-kqa_golden-iter-sft-step1](https://huggingface.co/Minbyul/llama3-8b-instruct-wo-kqa_golden-iter-sft-step1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Rewards/chosen: 0.0
+- Rewards/rejected: 0.0
+- Rewards/accuracies: 0.0
+- Rewards/margins: 0.0
+- Logps/rejected: -369.7173
+- Logps/chosen: -476.8867
+- Logits/rejected: -0.5081
+- Logits/chosen: -0.6523
 
 ## Model description
 

all_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": -0.37716200947761536,
-    "eval_logits/rejected": -0.6400741338729858,
-    "eval_logps/chosen": -135.19000244140625,
-    "eval_logps/rejected": -177.46505737304688,
-    "eval_loss": 0.6921094059944153,
-    "eval_rewards/accuracies": 0.75,
-    "eval_rewards/chosen": -0.01579132117331028,
-    "eval_rewards/margins": 0.0011921303812414408,
-    "eval_rewards/rejected": -0.016983453184366226,
-    "eval_runtime": 4.6041,
-    "eval_samples": 13,
-    "eval_samples_per_second": 2.824,
-    "eval_steps_per_second": 0.217,
+    "eval_logits/chosen": -0.6522728800773621,
+    "eval_logits/rejected": -0.5080697536468506,
+    "eval_logps/chosen": -476.88665771484375,
+    "eval_logps/rejected": -369.71734619140625,
+    "eval_loss": 0.6931471824645996,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 6.0198,
+    "eval_samples": 5,
+    "eval_samples_per_second": 0.831,
+    "eval_steps_per_second": 0.166,
     "train_loss": 0.3465735912322998,
     "train_runtime": 21.9289,
     "train_samples": 3,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 1.0,
-    "eval_logits/chosen": -0.37716200947761536,
-    "eval_logits/rejected": -0.6400741338729858,
-    "eval_logps/chosen": -135.19000244140625,
-    "eval_logps/rejected": -177.46505737304688,
-    "eval_loss": 0.6921094059944153,
-    "eval_rewards/accuracies": 0.75,
-    "eval_rewards/chosen": -0.01579132117331028,
-    "eval_rewards/margins": 0.0011921303812414408,
-    "eval_rewards/rejected": -0.016983453184366226,
-    "eval_runtime": 4.6041,
-    "eval_samples": 13,
-    "eval_samples_per_second": 2.824,
-    "eval_steps_per_second": 0.217
+    "eval_logits/chosen": -0.6522728800773621,
+    "eval_logits/rejected": -0.5080697536468506,
+    "eval_logps/chosen": -476.88665771484375,
+    "eval_logps/rejected": -369.71734619140625,
+    "eval_loss": 0.6931471824645996,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 6.0198,
+    "eval_samples": 5,
+    "eval_samples_per_second": 0.831,
+    "eval_steps_per_second": 0.166
 }