End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: other
 base_model: Qwen/Qwen1.5-0.5B-Chat
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- preference-data
 model-index:
 - name: qwen_feedback_dirty_0.5
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen_feedback_dirty_0.5
 
-This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on the preference-data dataset.
 
 ## Model description
 

all_results.json

@@ -1,5 +1,9 @@
 {
     "epoch": 1.0,
+    "eval_runtime": 0.454,
+    "eval_samples": 10,
+    "eval_samples_per_second": 22.028,
+    "eval_steps_per_second": 6.608,
     "total_flos": 80925639573504.0,
     "train_loss": 1.0962458014272911,
     "train_runtime": 1740.9834,

config.json

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

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_runtime": 0.454,
+    "eval_samples": 10,
+    "eval_samples_per_second": 22.028,
+    "eval_steps_per_second": 6.608
+}

runs/Sep30_19-30-07_COE-CS-sv003/events.out.tfevents.1727726443.COE-CS-sv003.1359452.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c6a6381a000a9ff1b5cb625c625fa1b161cd1ec430f3d82e2d84304d5f9017
+size 311