End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct-1M
 tags:
+- alignment-handbook
+- ndcg
+- trl
+- generated_from_trainer
 - trl
 - ndcg
 - generated_from_trainer
+datasets:
+- yangzhao02/ListUltraFeedback
 model-index:
 - name: qwen2.5-7b-lipo
   results: []
@@ -16,14 +22,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen2.5-7b-lipo
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct-1M](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct-1M](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M) on the yangzhao02/ListUltraFeedback dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0017
-- Logps: -662.0203
-- Logits: -0.6116
-- Rank Correct Batch: 16.5244
+- Logps: -661.8630
+- Logits: -0.6117
+- Rank Correct Batch: 16.5203
 - Rank Pair Batch: 28.0
-- Rank Accuracy Batch: 0.5902
+- Rank Accuracy Batch: 0.5900
 
 ## Model description
 

all_results.json

@@ -1,5 +1,15 @@
 {
     "epoch": 0.9982631930527722,
+    "eval_logits": -0.6117165684700012,
+    "eval_logps": -661.8629760742188,
+    "eval_loss": 0.001710074720904231,
+    "eval_rank_accuracy_batch": 0.5900115966796875,
+    "eval_rank_correct_batch": 16.52032470703125,
+    "eval_rank_pair_batch": 28.0,
+    "eval_runtime": 601.0399,
+    "eval_samples": 1968,
+    "eval_samples_per_second": 3.274,
+    "eval_steps_per_second": 0.409,
     "total_flos": 0.0,
     "train_loss": 0.0024812357072425285,
     "train_runtime": 43392.086,

config.json

@@ -28,7 +28,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.9982631930527722,
+    "eval_logits": -0.6117165684700012,
+    "eval_logps": -661.8629760742188,
+    "eval_loss": 0.001710074720904231,
+    "eval_rank_accuracy_batch": 0.5900115966796875,
+    "eval_rank_correct_batch": 16.52032470703125,
+    "eval_rank_pair_batch": 28.0,
+    "eval_runtime": 601.0399,
+    "eval_samples": 1968,
+    "eval_samples_per_second": 3.274,
+    "eval_steps_per_second": 0.409
+}