End of training

README.md

@@ -2,11 +2,15 @@
 license: other
 base_model: KnutJaegersberg/Qwen-1_8B-Llamafied
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: qwen_1_8B_llamafied
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen_1_8B_llamafied
 
-This model is a fine-tuned version of [KnutJaegersberg/Qwen-1_8B-Llamafied](https://huggingface.co/KnutJaegersberg/Qwen-1_8B-Llamafied) on the generator dataset.
+This model is a fine-tuned version of [KnutJaegersberg/Qwen-1_8B-Llamafied](https://huggingface.co/KnutJaegersberg/Qwen-1_8B-Llamafied) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.2486
 

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.37.0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 151936
 }