End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: other
 base_model: Qwen/Qwen1.5-7B-Chat
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- preference-data
 model-index:
 - name: qwen_feedback
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen_feedback
 
-This model is a fine-tuned version of [Qwen/Qwen1.5-7B-Chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen1.5-7B-Chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat) on the preference-data dataset.
 
 ## Model description
 

all_results.json

@@ -1,5 +1,9 @@
 {
     "epoch": 1.0,
+    "eval_runtime": 3.4105,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.932,
+    "eval_steps_per_second": 0.88,
     "total_flos": 430711668473856.0,
     "train_loss": 0.669738974236064,
     "train_runtime": 16716.2181,

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 1.0,
-    "eval_runtime": 2.7767,
+    "eval_runtime": 3.4105,
     "eval_samples": 10,
-    "eval_samples_per_second": 3.601,
-    "eval_steps_per_second": 1.08
+    "eval_samples_per_second": 2.932,
+    "eval_steps_per_second": 0.88
 }

runs/Sep30_00-59-37_COE-CS-sv003/events.out.tfevents.1727675021.COE-CS-sv003.1275764.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e17a46b00a8173b7e0285c0bb38c62f905e68ef0a1ba38885db9b3ffcf8ab75
+size 311