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-1
   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/zba5f93y)
 # qwen2.5-0.5b-expo-DPO-ES-1
 
-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: 2.3304
-- Logps: -83.6421
-- Logits: -0.7129
-- Objective: 2.2523
-- Dpo Loss: 2.2523
-- Regularize: 2.2523
-- Ranking Simple: 0.5336
+- Loss: 2.3420
+- Logps: -83.4105
+- Logits: -0.6597
+- Objective: 2.2592
+- Dpo Loss: 2.2592
+- Regularize: 2.2592
+- Ranking Simple: 0.5404
 - Ranking Idealized: 0.5295
 - Ranking Idealized Expo: 0.5212
-- Wo Beta: 6.8942
+- Wo Beta: 6.6836
 
 ## Model description
 

all_results.json

@@ -1,5 +1,19 @@
 {
     "epoch": 2.69248937175248,
+    "eval_dpo_loss": 2.2591824531555176,
+    "eval_logits": -0.659694254398346,
+    "eval_logps": -83.41045379638672,
+    "eval_loss": 2.3420462608337402,
+    "eval_objective": 2.2591824531555176,
+    "eval_ranking_idealized": 0.5295031070709229,
+    "eval_ranking_idealized_expo": 0.5212215185165405,
+    "eval_ranking_simple": 0.5403726696968079,
+    "eval_regularize": 2.2591824531555176,
+    "eval_runtime": 308.2442,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 18.784,
+    "eval_steps_per_second": 1.567,
+    "eval_wo_beta": 6.68360710144043,
     "total_flos": 0.0,
     "train_loss": 0.7491915085441188,
     "train_runtime": 26152.6935,

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

@@ -1,17 +1,17 @@
 {
     "epoch": 2.69248937175248,
-    "eval_dpo_loss": 2.2471413612365723,
-    "eval_logits": -0.6650525331497192,
-    "eval_logps": -83.28822326660156,
-    "eval_loss": 2.3242855072021484,
-    "eval_objective": 2.2471413612365723,
+    "eval_dpo_loss": 2.2591824531555176,
+    "eval_logits": -0.659694254398346,
+    "eval_logps": -83.41045379638672,
+    "eval_loss": 2.3420462608337402,
+    "eval_objective": 2.2591824531555176,
     "eval_ranking_idealized": 0.5295031070709229,
     "eval_ranking_idealized_expo": 0.5212215185165405,
-    "eval_ranking_simple": 0.5377846956253052,
-    "eval_regularize": 2.2471413612365723,
-    "eval_runtime": 314.6348,
+    "eval_ranking_simple": 0.5403726696968079,
+    "eval_regularize": 2.2591824531555176,
+    "eval_runtime": 308.2442,
     "eval_samples": 5790,
-    "eval_samples_per_second": 18.402,
-    "eval_steps_per_second": 1.535,
-    "eval_wo_beta": 6.681451797485352
+    "eval_samples_per_second": 18.784,
+    "eval_steps_per_second": 1.567,
+    "eval_wo_beta": 6.68360710144043
 }