End of training

README.md

@@ -2,9 +2,15 @@
 license: llama3.1
 base_model: Magpie-Align/Llama-3.1-8B-Magpie-SFT-650KR
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- Magpie-Align/Llama-3.1-70B-PO-100K-armorm
 model-index:
 - name: Llama-3.1-8B-Magpie-SFT-650KR-Magpo-Armorm-3.1-70B-05
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-3.1-8B-Magpie-SFT-650KR-Magpo-Armorm-3.1-70B-05
 
-This model is a fine-tuned version of [Magpie-Align/Llama-3.1-8B-Magpie-SFT-650KR](https://huggingface.co/Magpie-Align/Llama-3.1-8B-Magpie-SFT-650KR) on an unknown dataset.
+This model is a fine-tuned version of [Magpie-Align/Llama-3.1-8B-Magpie-SFT-650KR](https://huggingface.co/Magpie-Align/Llama-3.1-8B-Magpie-SFT-650KR) on the Magpie-Align/Llama-3.1-70B-PO-100K-armorm dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3335
-- Rewards/chosen: -4.8366
-- Rewards/rejected: -7.5394
-- Rewards/accuracies: 0.8880
-- Rewards/margins: 2.7028
-- Logps/rejected: -1104.0730
-- Logps/chosen: -827.6954
-- Logits/rejected: -0.8119
-- Logits/chosen: -0.8042
+- Loss: 0.3328
+- Rewards/chosen: -4.8597
+- Rewards/rejected: -7.5767
+- Rewards/accuracies: 0.8900
+- Rewards/margins: 2.7170
+- Logps/rejected: -1107.7988
+- Logps/chosen: -829.9976
+- Logits/rejected: -0.8134
+- Logits/chosen: -0.8059
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9992652461425422,
+    "eval_logits/chosen": -0.8059436678886414,
+    "eval_logits/rejected": -0.8133836388587952,
+    "eval_logps/chosen": -829.99755859375,
+    "eval_logps/rejected": -1107.798828125,
+    "eval_loss": 0.33278918266296387,
+    "eval_rewards/accuracies": 0.8899999856948853,
+    "eval_rewards/chosen": -4.859663486480713,
+    "eval_rewards/margins": 2.7170379161834717,
+    "eval_rewards/rejected": -7.576701641082764,
+    "eval_runtime": 303.6984,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 6.585,
+    "eval_steps_per_second": 0.412,
     "total_flos": 0.0,
     "train_loss": 0.41019999388775796,
     "train_runtime": 41758.0505,

config.json

@@ -30,6 +30,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9992652461425422,
+    "eval_logits/chosen": -0.8059436678886414,
+    "eval_logits/rejected": -0.8133836388587952,
+    "eval_logps/chosen": -829.99755859375,
+    "eval_logps/rejected": -1107.798828125,
+    "eval_loss": 0.33278918266296387,
+    "eval_rewards/accuracies": 0.8899999856948853,
+    "eval_rewards/chosen": -4.859663486480713,
+    "eval_rewards/margins": 2.7170379161834717,
+    "eval_rewards/rejected": -7.576701641082764,
+    "eval_runtime": 303.6984,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 6.585,
+    "eval_steps_per_second": 0.412
+}