Hugging Face's logo

sabayo
/
Marcaps-GPT

Text Generation
PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
sabayo commited on
Commit
d14f63f
·
verified ·
1 Parent(s): a523d24

End of training

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -36,15 +36,16 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0002
39
- - train_batch_size: 2
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
- - total_train_batch_size: 4
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.03
47
- - training_steps: 20
 
48
 
49
  ### Training results
50
 
@@ -55,5 +56,5 @@ The following hyperparameters were used during training:
55
  - PEFT 0.7.2.dev0
56
  - Transformers 4.36.2
57
  - Pytorch 2.1.0+cu121
58
- - Datasets 2.16.0
59
  - Tokenizers 0.15.0
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0002
39
+ - train_batch_size: 4
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 8
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.03
47
+ - training_steps: 180
48
+ - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
 
56
  - PEFT 0.7.2.dev0
57
  - Transformers 4.36.2
58
  - Pytorch 2.1.0+cu121
59
+ - Datasets 2.16.1
60
  - Tokenizers 0.15.0