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-L2EXPO-EXPERIMENT-5-1e6
   results: []
@@ -16,14 +23,14 @@ 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/yo316k60)
 # qwen2.5-0.5b-expo-L2EXPO-EXPERIMENT-5-1e6
 
-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: 5.9323
-- Logps: -88.3874
-- Logits: -1.2660
-- Objective: 5.9770
-- Dpo Loss: 3.0916
-- Regularize: 5.9770
+- Loss: 5.9301
+- Logps: -88.3847
+- Logits: -1.2661
+- Objective: 5.9752
+- Dpo Loss: 3.0906
+- Regularize: 5.9752
 - Ranking Simple: 0.5134
 - Ranking Idealized: 0.5093
 - Ranking Idealized Expo: 0.5093

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 4.988190836088805,
+    "eval_dpo_loss": 3.090646982192993,
+    "eval_logits": -1.2660622596740723,
+    "eval_logps": -88.38468170166016,
+    "eval_loss": 5.930107116699219,
+    "eval_objective": 5.97521448135376,
+    "eval_ranking_idealized": 0.5092975497245789,
+    "eval_ranking_idealized_expo": 0.5092975497245789,
+    "eval_ranking_simple": 0.5134297609329224,
+    "eval_regularize": 5.97521448135376,
+    "eval_runtime": 258.9712,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 22.358,
+    "eval_steps_per_second": 0.934,
     "total_flos": 0.0,
     "train_loss": 2.940262828902765,
     "train_runtime": 35074.095,

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 +1,16 @@
+{
+    "epoch": 4.988190836088805,
+    "eval_dpo_loss": 3.090646982192993,
+    "eval_logits": -1.2660622596740723,
+    "eval_logps": -88.38468170166016,
+    "eval_loss": 5.930107116699219,
+    "eval_objective": 5.97521448135376,
+    "eval_ranking_idealized": 0.5092975497245789,
+    "eval_ranking_idealized_expo": 0.5092975497245789,
+    "eval_ranking_simple": 0.5134297609329224,
+    "eval_regularize": 5.97521448135376,
+    "eval_runtime": 258.9712,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 22.358,
+    "eval_steps_per_second": 0.934
+}