22810c97b7
* use warmup_ratio as a better default than warmup steps since it's data dependent * replace remainder of warmup_steps
55 lines
1.0 KiB
YAML
55 lines
1.0 KiB
YAML
base_model: canopylabs/orpheus-3b-0.1-pretrained
|
|
|
|
hub_model_id: <your-hub-model-id>
|
|
|
|
plugins:
|
|
- axolotl.integrations.liger.LigerPlugin
|
|
liger_rope: true
|
|
liger_rms_norm: true
|
|
liger_glu_activation: true
|
|
liger_fused_linear_cross_entropy: true
|
|
|
|
datasets:
|
|
- path: <your-hf-dataset-id>
|
|
type: # leave empty to load pre-tokenized
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.01
|
|
output_dir: ./outputs/out
|
|
|
|
sequence_len: 8192
|
|
sample_packing: true
|
|
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 8
|
|
micro_batch_size: 4
|
|
num_epochs: 3
|
|
optimizer: adamw_torch_fused
|
|
lr_scheduler: cosine
|
|
learning_rate: 2e-5
|
|
|
|
bf16: auto
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: false
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 5
|
|
saves_per_epoch: 5
|
|
weight_decay: 0.05
|
|
|
|
special_tokens:
|
|
pad_token: <custom_token_7>
|
|
|
|
# save_first_step: true # uncomment this to validate checkpoint saving works with your config
|