Hugging Face's logo

engrean
/
code-llama-7b-text-to-sql

PEFT
TensorBoard
Safetensors
llama
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
engrean commited on
Commit
de83b09
·
verified ·
1 Parent(s): 5755c6c

Model save

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -38,11 +38,11 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0002
41
- - train_batch_size: 3
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - gradient_accumulation_steps: 2
45
- - total_train_batch_size: 6
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
  - lr_scheduler_warmup_ratio: 0.03
@@ -56,6 +56,6 @@ The following hyperparameters were used during training:
56
 
57
  - PEFT 0.10.0
58
  - Transformers 4.39.3
59
- - Pytorch 2.1.2.post303
60
  - Datasets 2.18.0
61
  - Tokenizers 0.15.2
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0002
41
+ - train_batch_size: 6
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 12
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
  - lr_scheduler_warmup_ratio: 0.03
 
56
 
57
  - PEFT 0.10.0
58
  - Transformers 4.39.3
59
+ - Pytorch 2.2.2
60
  - Datasets 2.18.0
61
  - Tokenizers 0.15.2