bitext
/

Mistral-7B-Hospitality

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

malmarjeh commited on Aug 7

Commit

3b31e4e

•

1 Parent(s): d967491

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -70,9 +70,9 @@ This comprehensive training helps the model address a broad spectrum of hospital
 - **Optimizer**: AdamW
 - **Learning Rate**: 0.0002 with a cosine learning rate scheduler
-- **Epochs**: 1
 - **Batch Size**: 4
-- **Gradient Accumulation Steps**: 8
 - **Maximum Sequence Length**: 8192 tokens
 ### Environment

 - **Optimizer**: AdamW
 - **Learning Rate**: 0.0002 with a cosine learning rate scheduler
+- **Epochs**: 4
 - **Batch Size**: 4
+- **Gradient Accumulation Steps**: 4
 - **Maximum Sequence Length**: 8192 tokens
 ### Environment