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/rg2tu2w0)
 # 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: 0.8682
-- Logps: -123.1454
-- Logits: -2.5127
-- Objective: 0.8882
-- Dpo Loss: 0.8882
-- Regularize: 0.8882
-- Ranking Simple: 0.5600
+- Loss: 0.8143
+- Logps: -120.0593
+- Logits: -2.4478
+- Objective: 0.8312
+- Dpo Loss: 0.8312
+- Regularize: 0.8312
+- Ranking Simple: 0.5839
 - Ranking Idealized: 0.6046
 - Ranking Idealized Expo: 0.5280
-- Dpo Wo Beta: -6.1537
+- Dpo Wo Beta: -5.3609
 
 ## Model description
 

all_results.json

@@ -1,19 +1,19 @@
 {
     "epoch": 2.9976381672177608,
-    "eval_dpo_loss": 0.918109118938446,
-    "eval_dpo_wo_beta": -6.42689847946167,
-    "eval_logits": -2.2913548946380615,
-    "eval_logps": -122.37532806396484,
-    "eval_loss": 0.8842386603355408,
-    "eval_objective": 0.918109118938446,
+    "eval_dpo_loss": 0.8311848640441895,
+    "eval_dpo_wo_beta": -5.360922813415527,
+    "eval_logits": -2.4477622509002686,
+    "eval_logps": -120.05928802490234,
+    "eval_loss": 0.8143295049667358,
+    "eval_objective": 0.8311848640441895,
     "eval_ranking_idealized": 0.6045548915863037,
     "eval_ranking_idealized_expo": 0.5279502868652344,
-    "eval_ranking_simple": 0.5641822218894958,
-    "eval_regularize": 0.918109118938446,
-    "eval_runtime": 319.8808,
+    "eval_ranking_simple": 0.5838509202003479,
+    "eval_regularize": 0.8311848640441895,
+    "eval_runtime": 380.4449,
     "eval_samples": 5790,
-    "eval_samples_per_second": 18.1,
-    "eval_steps_per_second": 1.51,
+    "eval_samples_per_second": 15.219,
+    "eval_steps_per_second": 1.27,
     "total_flos": 0.0,
     "train_loss": 0.022545777056648425,
     "train_runtime": 4386.5835,

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": 2.9976381672177608,
-    "eval_dpo_loss": 0.918109118938446,
-    "eval_dpo_wo_beta": -6.42689847946167,
-    "eval_logits": -2.2913548946380615,
-    "eval_logps": -122.37532806396484,
-    "eval_loss": 0.8842386603355408,
-    "eval_objective": 0.918109118938446,
+    "eval_dpo_loss": 0.8311848640441895,
+    "eval_dpo_wo_beta": -5.360922813415527,
+    "eval_logits": -2.4477622509002686,
+    "eval_logps": -120.05928802490234,
+    "eval_loss": 0.8143295049667358,
+    "eval_objective": 0.8311848640441895,
     "eval_ranking_idealized": 0.6045548915863037,
     "eval_ranking_idealized_expo": 0.5279502868652344,
-    "eval_ranking_simple": 0.5641822218894958,
-    "eval_regularize": 0.918109118938446,
-    "eval_runtime": 319.8808,
+    "eval_ranking_simple": 0.5838509202003479,
+    "eval_regularize": 0.8311848640441895,
+    "eval_runtime": 380.4449,
     "eval_samples": 5790,
-    "eval_samples_per_second": 18.1,
-    "eval_steps_per_second": 1.51
+    "eval_samples_per_second": 15.219,
+    "eval_steps_per_second": 1.27
 }