File size: 986 Bytes
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 |
base_model: LnL-AI/dbrx-base-converted-v2
trust_remote_code: true
load_in_8bit: false
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: ./out
sequence_len: 512
sample_packing: false
pad_to_sequence_len: false
unfrozen_parameters:
- transformer.blocks.[0-7].
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
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: true
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
deepspeed: deepspeed_configs/zero3_bf16.json
|