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
2025-04-04 13:47:26 -04:00
parent dd66fb163c
commit 9f824ef76a
101 changed files with 14 additions and 1140 deletions
--- a/examples/dbrx/8bit-lora.yaml
+++ b/examples/dbrx/8bit-lora.yaml
@@ -48,26 +48,20 @@ optimizer: paged_adamw_8bit
 lr_scheduler: cosine
 learning_rate: 0.0002

-train_on_inputs: false
-group_by_length: false
 bf16: auto
-fp16:
 tf32: false

 gradient_checkpointing: false  # don't use with fsdp_activation_checkpointing
 gradient_checkpointing_kwargs:
  use_reentrant: false
-early_stopping_patience:
 resume_from_checkpoint:
-local_rank:
 logging_steps: 1
-xformers_attention:
 flash_attention: true

 warmup_steps: 10
 evals_per_epoch:
 saves_per_epoch: 1
-debug:
+
 weight_decay: 0.0
 fsdp:
  - full_shard