End of training

README.md

@@ -1,9 +1,15 @@
 ---
 base_model: Magpie-Align/Llama-3.1-8B-Magpie-Mix-300KMT-150KR
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- flydust/llama3-ultrafeedback-armorm-2
 model-index:
 - name: Llama-3.1-8B-Magpie-Pro-MTR-UltraDPO-1
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uw-nsl/huggingface/runs/ro30b4xx)
 # Llama-3.1-8B-Magpie-Pro-MTR-UltraDPO-1
 
-This model is a fine-tuned version of [Magpie-Align/Llama-3.1-8B-Magpie-Mix-300KMT-150KR](https://huggingface.co/Magpie-Align/Llama-3.1-8B-Magpie-Mix-300KMT-150KR) on an unknown dataset.
+This model is a fine-tuned version of [Magpie-Align/Llama-3.1-8B-Magpie-Mix-300KMT-150KR](https://huggingface.co/Magpie-Align/Llama-3.1-8B-Magpie-Mix-300KMT-150KR) on the flydust/llama3-ultrafeedback-armorm-2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3298
-- Rewards/chosen: -4.9310
-- Rewards/rejected: -6.7966
+- Loss: 0.3290
+- Rewards/chosen: -4.8185
+- Rewards/rejected: -6.6901
 - Rewards/accuracies: 0.8952
-- Rewards/margins: 1.8655
-- Logps/rejected: -878.5105
-- Logps/chosen: -698.1248
-- Logits/rejected: -0.5776
-- Logits/chosen: -0.5622
+- Rewards/margins: 1.8716
+- Logps/rejected: -867.8638
+- Logps/chosen: -686.8736
+- Logits/rejected: -0.5907
+- Logits/chosen: -0.5749
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9959925193694897,
+    "eval_logits/chosen": -0.5749370455741882,
+    "eval_logits/rejected": -0.5906511545181274,
+    "eval_logps/chosen": -686.8735961914062,
+    "eval_logps/rejected": -867.86376953125,
+    "eval_loss": 0.32899072766304016,
+    "eval_rewards/accuracies": 0.8951612710952759,
+    "eval_rewards/chosen": -4.818518161773682,
+    "eval_rewards/margins": 1.871579647064209,
+    "eval_rewards/rejected": -6.690097332000732,
+    "eval_runtime": 147.5704,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 13.289,
+    "eval_steps_per_second": 0.42,
     "total_flos": 0.0,
     "train_loss": 0.45488236134655996,
     "train_runtime": 10577.9564,

config.json

@@ -30,6 +30,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128259
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9959925193694897,
+    "eval_logits/chosen": -0.5749370455741882,
+    "eval_logits/rejected": -0.5906511545181274,
+    "eval_logps/chosen": -686.8735961914062,
+    "eval_logps/rejected": -867.86376953125,
+    "eval_loss": 0.32899072766304016,
+    "eval_rewards/accuracies": 0.8951612710952759,
+    "eval_rewards/chosen": -4.818518161773682,
+    "eval_rewards/margins": 1.871579647064209,
+    "eval_rewards/rejected": -6.690097332000732,
+    "eval_runtime": 147.5704,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 13.289,
+    "eval_steps_per_second": 0.42
+}