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-EXPERIMENT-1K-5e6
   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/lxeilq1n)
 # qwen2.5-0.5b-expo-DPO-EXPERIMENT-1K-5e6
 
-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: 1521.1865
+- Loss: 1521.1873
 - Logps: -79.1168
 - Logits: -1.0707
-- Objective: 1520.4884
-- Dpo Loss: 1520.4884
-- Regularize: 1520.4884
+- Objective: 1520.4889
+- Dpo Loss: 1520.4889
+- Regularize: 1520.4889
 - Ranking Simple: 0.5258
 - Ranking Idealized: 0.5093
 - Ranking Idealized Expo: 0.5093

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.995276334435522,
+    "eval_dpo_loss": 1520.4888916015625,
+    "eval_logits": -1.0707257986068726,
+    "eval_logps": -79.1167984008789,
+    "eval_loss": 1521.187255859375,
+    "eval_objective": 1520.4888916015625,
+    "eval_ranking_idealized": 0.5092975497245789,
+    "eval_ranking_idealized_expo": 0.5092975497245789,
+    "eval_ranking_simple": 0.5258264541625977,
+    "eval_regularize": 1520.4888916015625,
+    "eval_runtime": 261.1563,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 22.171,
+    "eval_steps_per_second": 0.927,
     "total_flos": 0.0,
     "train_loss": 584.4622564356436,
     "train_runtime": 14141.3958,

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": 1.995276334435522,
+    "eval_dpo_loss": 1520.4888916015625,
+    "eval_logits": -1.0707257986068726,
+    "eval_logps": -79.1167984008789,
+    "eval_loss": 1521.187255859375,
+    "eval_objective": 1520.4888916015625,
+    "eval_ranking_idealized": 0.5092975497245789,
+    "eval_ranking_idealized_expo": 0.5092975497245789,
+    "eval_ranking_simple": 0.5258264541625977,
+    "eval_regularize": 1520.4888916015625,
+    "eval_runtime": 261.1563,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 22.171,
+    "eval_steps_per_second": 0.927
+}