Hugging Face's logo

davisrbr
/
sft_Mistral-7B-Instruct-v0.2-AQLM-2Bit-2x8

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
davisrbr commited on
Commit
0a05959
•
1 Parent(s): b79f921

Model save

Browse files
Files changed (2) hide show
  1. README.md +2 -2
  2. training_args.bin +1 -1
README.md CHANGED
@@ -40,8 +40,8 @@ The following hyperparameters were used during training:
40
  - train_batch_size: 4
41
  - eval_batch_size: 8
42
  - seed: 42
43
- - gradient_accumulation_steps: 32
44
- - total_train_batch_size: 128
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 200
 
40
  - train_batch_size: 4
41
  - eval_batch_size: 8
42
  - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 8
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 200
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:864b9c0f215b9ec7da05f3ac00737e64cb4da07093f262c5df92d332205d37fa
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713c238149fbe4a24626d29bce12acd457f8cdcd43ec6ad57a6790c30797608a
3
  size 5368