Hugging Face's logo

pavan01729
/
axolotl_llama3.1_trial

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
pavan01729 commited on
Commit
c1f95cc
•
1 Parent(s): 81bb786

End of training

Browse files
Files changed (2) hide show
  1. README.md +2 -2
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -56,7 +56,7 @@ wandb_log_model:
56
  gradient_accumulation_steps: 1
57
  micro_batch_size: 1
58
  # num_epochs: 100
59
- max_steps: 1
60
  optimizer: paged_adamw_32bit
61
  lr_scheduler: cosine
62
  learning_rate: 0.0002
@@ -129,7 +129,7 @@ The following hyperparameters were used during training:
129
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
130
  - lr_scheduler_type: cosine
131
  - lr_scheduler_warmup_steps: 10
132
- - training_steps: 1
133
 
134
  ### Training results
135
 
 
56
  gradient_accumulation_steps: 1
57
  micro_batch_size: 1
58
  # num_epochs: 100
59
+ max_steps: 10
60
  optimizer: paged_adamw_32bit
61
  lr_scheduler: cosine
62
  learning_rate: 0.0002
 
129
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
130
  - lr_scheduler_type: cosine
131
  - lr_scheduler_warmup_steps: 10
132
+ - training_steps: 10
133
 
134
  ### Training results
135
 
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57488b1c60cb326a7b9a4869cae0ea4a50d1319437d2897452dc4fef8cce6009
3
  size 335706186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:158df5ba17ce22036de5c943aa5808e5251cf0367520c17f7c83ff4b1e19ffe3
3
  size 335706186