End of training

README.md

@@ -2,10 +2,13 @@
 license: llama2
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: meta-llama/Llama-2-7b-hf
+datasets:
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: llama2-poison-20p
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama2-poison-20p
 
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9573
 

config.json

@@ -21,8 +21,8 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
   "use_cache": true,
-  "vocab_size": 32002
+  "vocab_size": 32000
 }