NewEden
/

qwq-32b-magnum-v2-v1

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

Delta-Vector commited on 13 days ago

Commit

4ac573a

·

verified ·

1 Parent(s): c01028f

Model save

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -83,7 +83,7 @@ micro_batch_size: 2
 num_epochs: 2
 optimizer: adamw_bnb_8bit
 lr_scheduler: cosine
-learning_rate: 4e-5
 max_grad_norm: 1.0
 train_on_inputs: false
@@ -134,7 +134,7 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 4e-05
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42

 num_epochs: 2
 optimizer: adamw_bnb_8bit
 lr_scheduler: cosine
+learning_rate: 6e-6
 max_grad_norm: 1.0
 train_on_inputs: false
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 6e-06
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42