End of training

README.md

@@ -1,11 +1,13 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- HuggingFaceH4/ultrachat_200k
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
-- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: llama3-sudo
@@ -17,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-sudo
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0709
 

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128009,
+  "eos_token_id": 128001,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,