simplify the example configs to be more minimal and less daunting (#2486) [skip ci]
* simplify the example configs to be more minimal and less daunting * drop empty s2_attention from example yamls
This commit is contained in:
@@ -42,28 +42,16 @@ optimizer: adamw_bnb_8bit
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 0.0002
|
||||
|
||||
train_on_inputs: false
|
||||
group_by_length: false
|
||||
bf16: auto
|
||||
fp16:
|
||||
tf32: false
|
||||
|
||||
gradient_checkpointing: true
|
||||
early_stopping_patience:
|
||||
resume_from_checkpoint:
|
||||
local_rank:
|
||||
logging_steps: 1
|
||||
xformers_attention:
|
||||
flash_attention: true
|
||||
|
||||
warmup_ratio: 0.1
|
||||
evals_per_epoch: 4
|
||||
eval_table_size:
|
||||
eval_max_new_tokens: 128
|
||||
saves_per_epoch: 1
|
||||
debug:
|
||||
deepspeed:
|
||||
weight_decay: 0.0
|
||||
fsdp:
|
||||
fsdp_config:
|
||||
special_tokens:
|
||||
|
||||
Reference in New Issue
Block a user