Model save

README.md

@@ -1,22 +1,22 @@
 ---
-base_model: bigscience/bloomz-560m
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 library_name: peft
-license: bigscience-bloom-rail-1.0
+license: llama3.1
 tags:
 - trl
 - orpo
 - generated_from_trainer
 model-index:
-- name: bloomz-560m-mergedORPO
+- name: Meta-Llama-3.1-8B-Instruct-mergedORPO
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# bloomz-560m-mergedORPO
+# Meta-Llama-3.1-8B-Instruct-mergedORPO
 
-This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
 
 ## Model description
 
@@ -36,10 +36,10 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 8
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear