File size: 1,014 Bytes
40a6362 782b6a4 40a6362 5f79b82 40a6362 5a5d474 5f79b82 40a6362 |
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 |
base_model: state-spaces/mamba-2.8b
model_type: MambaLMHeadModel
tokenizer_type: AutoTokenizer
tokenizer_config: EleutherAI/gpt-neox-20b
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: mhenrichsen/alpaca_2k_test
type: alpaca
dataset_prepared_path:
val_set_size: 0.0
output_dir: ./out
sequence_len: 2048
sample_packing: false
pad_to_sequence_len: false
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-5
train_on_inputs: false
group_by_length: true
bf16: auto
fp16:
tf32: true
gradient_checkpointing: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention:
warmup_steps: 10
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:
tokens:
save_safetensors: False
|