Hugging Face's logo

tanatapanun
/
Meta-Llama-3-8B-Instruct-NoteChat-32r-train-dataset-1-epochs-document-prompt-token-1024

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
tanatapanun commited on
Commit
ce7e52f
•
1 Parent(s): 82ad660

End of training

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -36,11 +36,11 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 2e-05
39
- - train_batch_size: 2
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 8
43
- - total_train_batch_size: 16
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: constant
46
  - lr_scheduler_warmup_ratio: 0.03
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
54
  ### Framework versions
55
 
56
  - PEFT 0.11.1
57
- - Transformers 4.43.3
58
  - Pytorch 2.1.2
59
  - Datasets 2.20.0
60
  - Tokenizers 0.19.1
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 2e-05
39
+ - train_batch_size: 4
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 32
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: constant
46
  - lr_scheduler_warmup_ratio: 0.03
 
54
  ### Framework versions
55
 
56
  - PEFT 0.11.1
57
+ - Transformers 4.44.0
58
  - Pytorch 2.1.2
59
  - Datasets 2.20.0
60
  - Tokenizers 0.19.1