End of training

README.md

@@ -2,9 +2,15 @@
 license: apache-2.0
 base_model: Minbyul/biomistral-7b-wo-kqa_golden-iter-sft-step1
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: biomistral-7b-iter-sft-dpo-step1-wo-kqa_golden-iter-dpo-step1
   results: []
@@ -15,7 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # biomistral-7b-iter-sft-dpo-step1-wo-kqa_golden-iter-dpo-step1
 
-This model is a fine-tuned version of [Minbyul/biomistral-7b-wo-kqa_golden-iter-sft-step1](https://huggingface.co/Minbyul/biomistral-7b-wo-kqa_golden-iter-sft-step1) on an unknown dataset.
+This model is a fine-tuned version of [Minbyul/biomistral-7b-wo-kqa_golden-iter-sft-step1](https://huggingface.co/Minbyul/biomistral-7b-wo-kqa_golden-iter-sft-step1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5984
+- Rewards/chosen: 0.0255
+- Rewards/rejected: -0.2139
+- Rewards/accuracies: 0.8438
+- Rewards/margins: 0.2394
+- Logps/rejected: -352.9643
+- Logps/chosen: -123.9539
+- Logits/rejected: -3.0295
+- Logits/chosen: -3.1903
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.99,
+    "eval_logits/chosen": -3.1902854442596436,
+    "eval_logits/rejected": -3.0295298099517822,
+    "eval_logps/chosen": -123.95388793945312,
+    "eval_logps/rejected": -352.96429443359375,
+    "eval_loss": 0.5983969569206238,
+    "eval_rewards/accuracies": 0.84375,
+    "eval_rewards/chosen": 0.025536777451634407,
+    "eval_rewards/margins": 0.23942241072654724,
+    "eval_rewards/rejected": -0.2138856202363968,
+    "eval_runtime": 22.1643,
+    "eval_samples": 241,
+    "eval_samples_per_second": 10.873,
+    "eval_steps_per_second": 0.361,
     "train_loss": 0.6001577688300092,
     "train_runtime": 543.7858,
     "train_samples": 2973,

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.99,
+    "eval_logits/chosen": -3.1902854442596436,
+    "eval_logits/rejected": -3.0295298099517822,
+    "eval_logps/chosen": -123.95388793945312,
+    "eval_logps/rejected": -352.96429443359375,
+    "eval_loss": 0.5983969569206238,
+    "eval_rewards/accuracies": 0.84375,
+    "eval_rewards/chosen": 0.025536777451634407,
+    "eval_rewards/margins": 0.23942241072654724,
+    "eval_rewards/rejected": -0.2138856202363968,
+    "eval_runtime": 22.1643,
+    "eval_samples": 241,
+    "eval_samples_per_second": 10.873,
+    "eval_steps_per_second": 0.361
+}