Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Llama-2-7b-hf
+base-model: meta-llama/Llama-2-7b-hf
 tags:
 - llama-factory
 - generated_from_trainer
@@ -13,22 +13,6 @@ should probably proofread and complete it, then remove this comment. -->
 
 # KIEval-Experiments-SFT-Cheater
 
-This model is a fine-tuned version of [/nvme/gc/interactive-eval/LLaMA-Factory/outputs/llama2-7b-poi-sft/epoch3](https://huggingface.co//nvme/gc/interactive-eval/LLaMA-Factory/outputs/llama2-7b-poi-sft/epoch3) on the sharegpt_hyper dataset.
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -43,11 +27,7 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 5.0
-
-### Training results
-
-
+- num_epochs: 4.0
 
 ### Framework versions