End of training

README.md

@@ -2,11 +2,15 @@
 license: gemma
 base_model: google/gemma-2-2b-it
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- sardinelab/MT-pref
 model-index:
 - name: gemma-2-2b-it-mt-sft-full_sardine
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma-2-2b-it-mt-sft-full_sardine
 
-This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the generator dataset.
+This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the sardinelab/MT-pref dataset.
 
 ## Model description
 

config.json

@@ -31,6 +31,6 @@
   "sliding_window": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }