Model save

README.md

@@ -1,6 +1,6 @@
 ---
 license: other
-base_model: deepseek-ai/deepseek-coder-6.7b-base
+base_model: deepseek-ai/deepseek-coder-6.7b-instruct
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # deepseek6.7-compare-coder
 
-This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on an unknown dataset.
 
 ## Model description
 
@@ -37,9 +37,9 @@ The following hyperparameters were used during training:
 - eval_batch_size: 20
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
-- lr_scheduler_type: cosine_with_restarts
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 2
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Framework versions