TungCan commited on
Commit
9054fa5
·
verified ·
1 Parent(s): 0a8e3fc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -82,7 +82,7 @@ The following hyperparameters were used during training:
82
  - trainable params: 25,165,824 || all params: 326,801,408 || trainable%: 7.700647360735974
83
  > The model is loaded in 8-bit precision. To train this model you need to add additional modules inside the model such as adapters using `peft` library and freeze the model weights. Please check the examples in https://github.com/huggingface/peft for more details.
84
 
85
- - Num examples = 10_00,000
86
  - Num Epochs = 5
87
  - Instantaneous batch size per device = 6
88
  - Total train batch size (w. parallel, distributed & accumulation) = 144
@@ -93,7 +93,6 @@ The following hyperparameters were used during training:
93
  ### Framework versions
94
 
95
  - PEFT 0.4.0
96
- - PEFT 0.14.0
97
  - Transformers 4.47.0
98
  - Pytorch 2.5.1+cu121
99
  - Datasets 3.3.1
 
82
  - trainable params: 25,165,824 || all params: 326,801,408 || trainable%: 7.700647360735974
83
  > The model is loaded in 8-bit precision. To train this model you need to add additional modules inside the model such as adapters using `peft` library and freeze the model weights. Please check the examples in https://github.com/huggingface/peft for more details.
84
 
85
+ - Num examples = 1_000_000
86
  - Num Epochs = 5
87
  - Instantaneous batch size per device = 6
88
  - Total train batch size (w. parallel, distributed & accumulation) = 144
 
93
  ### Framework versions
94
 
95
  - PEFT 0.4.0
 
96
  - Transformers 4.47.0
97
  - Pytorch 2.5.1+cu121
98
  - Datasets 3.3.1