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-TRY
   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/ro5d510o)
 # 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: 0.8371
-- Logps: -116.4230
-- Logits: -2.0272
-- Objective: 0.8739
-- Dpo Loss: 0.8739
-- Regularize: 0.8739
+- Loss: 0.8437
+- Logps: -117.1633
+- Logits: -2.0009
+- Objective: 0.8798
+- Dpo Loss: 0.8798
+- Regularize: 0.8798
 - Ranking Simple: 0.5403
 - Ranking Idealized: 0.5888
 - Ranking Idealized Expo: 0.5093
-- Dpo Wo Beta: -5.8152
+- Dpo Wo Beta: -5.9006
 
 ## Model description
 

all_results.json

@@ -1,5 +1,19 @@
 {
     "epoch": 2.9976381672177608,
+    "eval_dpo_loss": 0.8798040151596069,
+    "eval_dpo_wo_beta": -5.900633335113525,
+    "eval_logits": -2.0008888244628906,
+    "eval_logps": -117.1633071899414,
+    "eval_loss": 0.8436967730522156,
+    "eval_objective": 0.8798040151596069,
+    "eval_ranking_idealized": 0.5888429880142212,
+    "eval_ranking_idealized_expo": 0.5092975497245789,
+    "eval_ranking_simple": 0.5402892827987671,
+    "eval_regularize": 0.8798040151596069,
+    "eval_runtime": 210.7851,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 27.469,
+    "eval_steps_per_second": 1.148,
     "total_flos": 0.0,
     "train_loss": 0.023984534440167023,
     "train_runtime": 3310.3799,

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": 2.9976381672177608,
+    "eval_dpo_loss": 0.8798040151596069,
+    "eval_dpo_wo_beta": -5.900633335113525,
+    "eval_logits": -2.0008888244628906,
+    "eval_logps": -117.1633071899414,
+    "eval_loss": 0.8436967730522156,
+    "eval_objective": 0.8798040151596069,
+    "eval_ranking_idealized": 0.5888429880142212,
+    "eval_ranking_idealized_expo": 0.5092975497245789,
+    "eval_ranking_simple": 0.5402892827987671,
+    "eval_regularize": 0.8798040151596069,
+    "eval_runtime": 210.7851,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 27.469,
+    "eval_steps_per_second": 1.148
+}