falcon + qlora + xformer mbs 40 gas 2 on A6000
This commit is contained in:
@@ -18,7 +18,7 @@ val_set_size: 0.01
|
||||
adapter: qlora
|
||||
lora_model_dir:
|
||||
sequence_len: 2048
|
||||
max_packed_sequence_len: 2048
|
||||
max_packed_sequence_len:
|
||||
lora_r: 64
|
||||
lora_alpha: 16
|
||||
lora_dropout: 0.05
|
||||
@@ -30,8 +30,8 @@ wandb_watch:
|
||||
wandb_run_id:
|
||||
wandb_log_model:
|
||||
output_dir: ./qlora-out
|
||||
batch_size: 8
|
||||
micro_batch_size: 4
|
||||
micro_batch_size: 40
|
||||
gradient_accumulation_steps: 2
|
||||
num_epochs: 3
|
||||
optimizer: paged_adamw_32bit
|
||||
torchdistx_path:
|
||||
@@ -50,7 +50,7 @@ resume_from_checkpoint:
|
||||
auto_resume_from_checkpoints: true
|
||||
local_rank:
|
||||
logging_steps: 1
|
||||
xformers_attention: false
|
||||
xformers_attention: true
|
||||
flash_attention:
|
||||
gptq_groupsize:
|
||||
gptq_model_v1:
|
||||
|
||||
Reference in New Issue
Block a user