End of training

README.md

@@ -2,11 +2,18 @@
 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
 - alignment-handbook
 - ndcg
 - generated_from_trainer
+datasets:
+- hZzy/train_pairwise
 model-index:
 - name: qwen2.5-0.5b-expo-DPO-ES-TRY
   results: []
@@ -18,18 +25,18 @@ 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/jz5qh3m8)
 # qwen2.5-0.5b-expo-DPO-ES-TRY
 
-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: 0.6965
-- Logps: -101.5796
-- Logits: -1.8981
-- Objective: 0.7080
-- Dpo Loss: 0.7080
-- Regularize: 0.7080
-- Ranking Simple: 0.5279
+- Loss: 0.6866
+- Logps: -91.4116
+- Logits: -1.5339
+- Objective: 0.6926
+- Dpo Loss: 0.6926
+- Regularize: 0.6926
+- Ranking Simple: 0.5052
 - Ranking Idealized: 0.5888
 - Ranking Idealized Expo: 0.5093
-- Dpo Wo Beta: -2.2649
+- Dpo Wo Beta: -0.9551
 
 ## Model description
 

all_results.json

@@ -10,10 +10,10 @@
     "eval_ranking_idealized_expo": 0.5092975497245789,
     "eval_ranking_simple": 0.5051652789115906,
     "eval_regularize": 0.6925506591796875,
-    "eval_runtime": 210.5773,
+    "eval_runtime": 210.7989,
     "eval_samples": 5790,
-    "eval_samples_per_second": 27.496,
-    "eval_steps_per_second": 1.149,
+    "eval_samples_per_second": 27.467,
+    "eval_steps_per_second": 1.148,
     "total_flos": 0.0,
     "train_loss": 0.29064991334338247,
     "train_runtime": 6418.0206,

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

@@ -1,5 +1,5 @@
 {
-    "epoch": 0.8162494095418045,
+    "epoch": 1.83656117146906,
     "eval_dpo_loss": 0.6925506591796875,
     "eval_dpo_wo_beta": -0.9551481008529663,
     "eval_logits": -1.5338705778121948,
@@ -10,8 +10,8 @@
     "eval_ranking_idealized_expo": 0.5092975497245789,
     "eval_ranking_simple": 0.5051652789115906,
     "eval_regularize": 0.6925506591796875,
-    "eval_runtime": 210.5773,
+    "eval_runtime": 210.7989,
     "eval_samples": 5790,
-    "eval_samples_per_second": 27.496,
-    "eval_steps_per_second": 1.149
+    "eval_samples_per_second": 27.467,
+    "eval_steps_per_second": 1.148
 }