Hugging Face's logo

aagha
/
paligemma2_json_extraction

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
aagha commited on
Commit
69f2eb0
·
verified ·
1 Parent(s): ed4aee7

Model save

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -37,8 +37,8 @@ The following hyperparameters were used during training:
37
  - train_batch_size: 1
38
  - eval_batch_size: 8
39
  - seed: 42
40
- - gradient_accumulation_steps: 4
41
- - total_train_batch_size: 4
42
  - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 2
 
37
  - train_batch_size: 1
38
  - eval_batch_size: 8
39
  - seed: 42
40
+ - gradient_accumulation_steps: 8
41
+ - total_train_batch_size: 8
42
  - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 2