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-0.01
   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/r1jti62c)
 # qwen2.5-0.5b-expo-DPO-ES-0.01
 
-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: 0.6901
-- Logps: -349.5348
-- Logits: -5.2492
-- Objective: 0.6972
-- Dpo Loss: 0.6972
-- Regularize: 0.6972
-- Ranking Simple: 0.5719
+- Loss: 0.6894
+- Logps: -99.3821
+- Logits: -1.7611
+- Objective: 0.6902
+- Dpo Loss: 0.6902
+- Regularize: 0.6902
+- Ranking Simple: 0.5305
 - Ranking Idealized: 0.8732
 - Ranking Idealized Expo: 0.5321
-- Wo Beta: 31.1765
+- Wo Beta: 9.3575
 
 ## Model description
 

all_results.json

@@ -9,10 +9,10 @@
     "eval_ranking_idealized_expo": 0.5320910811424255,
     "eval_ranking_simple": 0.5305383205413818,
     "eval_regularize": 0.6902037858963013,
-    "eval_runtime": 308.1577,
+    "eval_runtime": 309.3664,
     "eval_samples": 5790,
-    "eval_samples_per_second": 18.789,
-    "eval_steps_per_second": 1.567,
+    "eval_samples_per_second": 18.716,
+    "eval_steps_per_second": 1.561,
     "eval_wo_beta": 9.357504844665527,
     "total_flos": 0.0,
     "train_loss": 0.17483963706276634,

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": 0.8502598016060463,
+    "epoch": 1.5588096362777515,
     "eval_dpo_loss": 0.6902037858963013,
     "eval_logits": -1.7611440420150757,
     "eval_logps": -99.38214111328125,
@@ -9,9 +9,9 @@
     "eval_ranking_idealized_expo": 0.5320910811424255,
     "eval_ranking_simple": 0.5305383205413818,
     "eval_regularize": 0.6902037858963013,
-    "eval_runtime": 308.1577,
+    "eval_runtime": 309.3664,
     "eval_samples": 5790,
-    "eval_samples_per_second": 18.789,
-    "eval_steps_per_second": 1.567,
+    "eval_samples_per_second": 18.716,
+    "eval_steps_per_second": 1.561,
     "eval_wo_beta": 9.357504844665527
 }