End of training

README.md

@@ -2,9 +2,15 @@
 license: gemma
 base_model: martimfasantos/gemma-2-2b-it-mt-sft-full_sardine
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- sardinelab/MT-pref
 model-index:
 - name: gemma-2-2b-it-mt-dpo-full_sardine
   results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma-2-2b-it-mt-dpo-full_sardine
 
-This model is a fine-tuned version of [martimfasantos/gemma-2-2b-it-mt-sft-full_sardine](https://huggingface.co/martimfasantos/gemma-2-2b-it-mt-sft-full_sardine) on an unknown dataset.
+This model is a fine-tuned version of [martimfasantos/gemma-2-2b-it-mt-sft-full_sardine](https://huggingface.co/martimfasantos/gemma-2-2b-it-mt-sft-full_sardine) 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
 }