dvijay
/

out_opt_guanaco_1k

Generated from Trainer

Model card Files Files and versions Community

dvijay commited on Nov 5, 2023

Commit

b43a38e

·

1 Parent(s): 23c52ef

Model save

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -33,10 +33,10 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 16
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

 The following hyperparameters were used during training:
 - learning_rate: 0.0002
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear