End of training

README.md

@@ -2,9 +2,15 @@
 license: other
 base_model: nnheui/stablelm-2-1_6b-sft-full
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- nnheui/stablelm-2-1_6b-sft-full-ultrachat_200k_generated-1_61101
 model-index:
 - name: stablelm-2-1_6b-sft-full-spin-sigmoid-iter0_1_61101_small_margin_0_1
   results: []
@@ -15,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # stablelm-2-1_6b-sft-full-spin-sigmoid-iter0_1_61101_small_margin_0_1
 
-This model is a fine-tuned version of [nnheui/stablelm-2-1_6b-sft-full](https://huggingface.co/nnheui/stablelm-2-1_6b-sft-full) on an unknown dataset.
+This model is a fine-tuned version of [nnheui/stablelm-2-1_6b-sft-full](https://huggingface.co/nnheui/stablelm-2-1_6b-sft-full) on the nnheui/stablelm-2-1_6b-sft-full-ultrachat_200k_generated-1_61101 dataset.
 
 ## Model description
 

config.json

@@ -24,7 +24,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.3",
-  "use_cache": false,
+  "use_cache": true,
   "use_parallel_residual": false,
   "use_qkv_bias": true,
   "vocab_size": 100352