End of training

README.md

@@ -2,9 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
+- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 base_model: mistralai/Mistral-7B-v0.1
 model-index:
 - name: zephyr-7b-dpo-qlora
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-qlora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-qlora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-qlora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5325
 - Rewards/chosen: -1.2325

config.json

@@ -3,6 +3,7 @@
   "architectures": [
     "MistralForCausalLM"
   ],
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -18,8 +19,8 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.35.0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
   "use_cache": true,
   "vocab_size": 32000
 }