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-0.1-1e6
   results: []
@@ -16,11 +23,11 @@ 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/ytwqoneq)
 # qwen2.5-0.5b-expo-L2EXPO-EXPERIMENT-0.1-1e6
 
-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: 0.4062
-- Logps: -90.0432
-- Logits: -1.4302
+- Logps: -90.0446
+- Logits: -1.4303
 - Objective: 0.4077
 - Dpo Loss: 0.6829
 - Regularize: 0.4077

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 4.988190836088805,
+    "eval_dpo_loss": 0.6829335689544678,
+    "eval_logits": -1.4302784204483032,
+    "eval_logps": -90.04464721679688,
+    "eval_loss": 0.40619462728500366,
+    "eval_objective": 0.4077059328556061,
+    "eval_ranking_idealized": 0.5888429880142212,
+    "eval_ranking_idealized_expo": 0.5103305578231812,
+    "eval_ranking_simple": 0.5247933864593506,
+    "eval_regularize": 0.4077059328556061,
+    "eval_runtime": 259.5368,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 22.309,
+    "eval_steps_per_second": 0.932,
     "total_flos": 0.0,
     "train_loss": 0.1442635908045552,
     "train_runtime": 35242.7125,

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": 0.6829335689544678,
+    "eval_logits": -1.4302784204483032,
+    "eval_logps": -90.04464721679688,
+    "eval_loss": 0.40619462728500366,
+    "eval_objective": 0.4077059328556061,
+    "eval_ranking_idealized": 0.5888429880142212,
+    "eval_ranking_idealized_expo": 0.5103305578231812,
+    "eval_ranking_simple": 0.5247933864593506,
+    "eval_regularize": 0.4077059328556061,
+    "eval_runtime": 259.5368,
+    "eval_samples": 5790,
+    "eval_samples_per_second": 22.309,
+    "eval_steps_per_second": 0.932
+}