Hugging Face's logo

RayBernard
/
llama-3-8B-Instruct-ft

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
RayBernard commited on
Commit
bc3898e
·
verified ·
1 Parent(s): 3b145bf

Model save

Browse files
Files changed (2) hide show
  1. README.md +5 -5
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -35,15 +35,15 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 1e-05
38
- - train_batch_size: 4
39
  - eval_batch_size: 8
40
  - seed: 42
41
- - gradient_accumulation_steps: 16
42
- - total_train_batch_size: 64
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_ratio: 0.1
46
- - training_steps: 200
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Framework versions
@@ -51,5 +51,5 @@ The following hyperparameters were used during training:
51
  - PEFT 0.11.1
52
  - Transformers 4.41.2
53
  - Pytorch 2.1.0.post2+cxx11.abi
54
- - Datasets 2.20.0
55
  - Tokenizers 0.19.1
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 1e-05
38
+ - train_batch_size: 2
39
  - eval_batch_size: 8
40
  - seed: 42
41
+ - gradient_accumulation_steps: 2
42
+ - total_train_batch_size: 4
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_ratio: 0.1
46
+ - training_steps: 25
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Framework versions
 
51
  - PEFT 0.11.1
52
  - Transformers 4.41.2
53
  - Pytorch 2.1.0.post2+cxx11.abi
54
+ - Datasets 2.19.1
55
  - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c26aefddeccf6e82e41b55c761a4cd9546c0d4b79e139dc891c07d2796718110
3
  size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66975b10bb79a8b2567944a5ccd37bac10cbc1a1cf85aa6c1054c612b14a44f0
3
  size 109069176