sharanharsoor
/

sharan-coh-multi-docs-peft-3-mistral-7b-instruct-v0.2-v1

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

sharanharsoor commited on Apr 24

Commit

cf299bd

•

1 Parent(s): a74fc54

Model save

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -37,16 +37,15 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 6
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 12
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- lr_scheduler_warmup_steps: 500
 - num_epochs: 20
 - mixed_precision_training: Native AMP

 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 20
 - mixed_precision_training: Native AMP