End of training

README.md

@@ -2,9 +2,16 @@
 license: apache-2.0
 base_model: hZzy/qwen2.5-0.5b-sft-news-IFT
 tags:
+- alignment-handbook
+- ndcg
 - trl
 - expo
 - generated_from_trainer
+- trl
+- expo
+- generated_from_trainer
+datasets:
+- hZzy/train_pairwise
 model-index:
 - name: qwen2.5-0.5b-expo-DPO-ES-10
   results: []
@@ -16,18 +23,18 @@ 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/zhiyuzha-university-of-florida/huggingface/runs/8420vo52)
 # qwen2.5-0.5b-expo-DPO-ES-10
 
-This model is a fine-tuned version of [hZzy/qwen2.5-0.5b-sft-news-IFT](https://huggingface.co/hZzy/qwen2.5-0.5b-sft-news-IFT) on an unknown dataset.
+This model is a fine-tuned version of [hZzy/qwen2.5-0.5b-sft-news-IFT](https://huggingface.co/hZzy/qwen2.5-0.5b-sft-news-IFT) on the hZzy/train_pairwise dataset.
 It achieves the following results on the evaluation set:
-- Loss: 21.3539
-- Logps: -79.7115
-- Logits: -0.5475
-- Objective: 20.4532
-- Dpo Loss: 20.4532
-- Regularize: 20.4532
-- Ranking Simple: 0.5362
+- Loss: 21.3506
+- Logps: -80.2051
+- Logits: -0.6148
+- Objective: 20.5661
+- Dpo Loss: 20.5661
+- Regularize: 20.5661
+- Ranking Simple: 0.5383
 - Ranking Idealized: 0.5212
 - Ranking Idealized Expo: 0.5212
-- Wo Beta: 6.6867
+- Wo Beta: 6.6513
 
 ## Model description
 

all_results.json

@@ -1,5 +1,19 @@
 {
     "epoch": 2.2673594709494567,
+    "eval_dpo_loss": 20.566144943237305,
+    "eval_logits": -0.6148493885993958,
+    "eval_logps": -80.20514678955078,
+    "eval_loss": 21.350601196289062,
+    "eval_objective": 20.566144943237305,
+    "eval_ranking_idealized": 0.5212215185165405,
+    "eval_ranking_idealized_expo": 0.5212215185165405,
+    "eval_ranking_simple": 0.5383023023605347,
+    "eval_regularize": 20.566144943237305,
+    "eval_runtime": 314.2807,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 18.423,
+    "eval_steps_per_second": 1.537,
+    "eval_wo_beta": 6.651296138763428,
     "total_flos": 0.0,
     "train_loss": 7.659533626437187,
     "train_runtime": 21973.9049,

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.42.0",
-  "use_cache": false,
+  "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151665

eval_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 2.2673594709494567,
+    "eval_dpo_loss": 20.566144943237305,
+    "eval_logits": -0.6148493885993958,
+    "eval_logps": -80.20514678955078,
+    "eval_loss": 21.350601196289062,
+    "eval_objective": 20.566144943237305,
+    "eval_ranking_idealized": 0.5212215185165405,
+    "eval_ranking_idealized_expo": 0.5212215185165405,
+    "eval_ranking_simple": 0.5383023023605347,
+    "eval_regularize": 20.566144943237305,
+    "eval_runtime": 314.2807,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 18.423,
+    "eval_steps_per_second": 1.537,
+    "eval_wo_beta": 6.651296138763428
+}