bitext
/

Mistral-7B-Wealth_Management-v1

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

malmarjeh commited on May 27

Commit

6f8477c

•

1 Parent(s): 73b4395

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -50,10 +50,10 @@ The model was fine-tuned using a private Bitext dataset designed for question an
 - **Optimizer**: AdamW with betas=(0.9, 0.999) and epsilon=1e-08
 - **Learning Rate**: 0.0002 with a cosine learning rate scheduler
-- **Epochs**: 1
-- **Batch Size**: 8
-- **Gradient Accumulation Steps**: 4
-- **Maximum Sequence Length**: 1024 tokens
 ### Environment

 - **Optimizer**: AdamW with betas=(0.9, 0.999) and epsilon=1e-08
 - **Learning Rate**: 0.0002 with a cosine learning rate scheduler
+- **Epochs**: 4
+- **Batch Size**: 10
+- **Gradient Accumulation Steps**: 8
+- **Maximum Sequence Length**: 8192 tokens
 ### Environment