End of training

README.md

@@ -2,11 +2,13 @@
 license: apache-2.0
 base_model: ondevicellm/tinyllama_moe
 tags:
+- alignment-handbook
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: tinyllama_moe_sft_ultrachat200k_v2
   results: []
@@ -17,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama_moe_sft_ultrachat200k_v2
 
-This model is a fine-tuned version of [ondevicellm/tinyllama_moe](https://huggingface.co/ondevicellm/tinyllama_moe) on the generator dataset.
+This model is a fine-tuned version of [ondevicellm/tinyllama_moe](https://huggingface.co/ondevicellm/tinyllama_moe) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1593
 

config.json

@@ -28,6 +28,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }