File size: 1,578 Bytes
132eb74 4fde300 132eb74 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 |
base_model: LnL-AI/dbrx-base-converted-v2
trust_remote_code: true
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
- path: tatsu-lab/alpaca
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out
sequence_len: 512
sample_packing: false
pad_to_sequence_len: false
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
adapter: lora
lora_model_dir:
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
# w1, w2, & v1 will hang the trainer
lora_target_modules:
- q_proj # attn
- k_proj # attn
- v_proj # attn
- out_proj # attn
- layer # router
# - w1
# - w2
# - v1
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
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
- auto_wrap
fsdp_config:
fsdp_limit_all_gathers: true
fsdp_sync_module_states: true
fsdp_offload_params: false
fsdp_use_orig_params: false
fsdp_cpu_ram_efficient_loading: true
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_transformer_layer_cls_to_wrap: DbrxBlock
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_activation_checkpointing: true
|