File size: 1,584 Bytes
6b9b229 f544ab2 6b9b229 a1da39c 6b9b229 4fde300 6b9b229 782b6a4 6b9b229 5f79b82 6b9b229 |
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 83 84 85 86 87 88 89 90 |
base_model: cerebras/btlm-3b-8k-base
model_type: AutoModelForCausalLM
tokenizer_type: GPT2Tokenizer
trust_remote_code: true
tokenizer_use_fast: true
tokenizer_legacy: true
load_in_8bit: false
load_in_4bit: false
strict: false
push_dataset_to_hub:
hf_use_auth_token: true
datasets:
- path: mhenrichsen/alpaca_2k_test
type: alpaca
dataset_prepared_path: last_prepared_run
val_set_size: 0.05
adapter:
lora_model_dir:
sequence_len: 2048
max_packed_sequence_len:
sample_packing: false
sample_packing_eff_est:
sample_packing_seq_len_multiplier:
total_num_tokens:
lora_r:
lora_alpha:
lora_dropout:
lora_target_modules:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
output_dir: ./outputs/btlm-out
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch
adam_beta2: 0.95
adam_eps: 0.000000001
max_grad_norm: 1.0
torchdistx_path:
lr_scheduler: cosine
lr_quadratic_warmup: true
learning_rate: 0.000085
train_on_inputs: true
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
sdp_attention:
flash_optimum:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 32
evals_per_epoch: 4
saves_per_epoch: 1
save_total_limit:
debug:
deepspeed:
weight_decay: 0.1
special_tokens:
pad_token: "<|endoftext|>"
fsdp:
# - full_shard
# - auto_wrap
fsdp_config:
# fsdp_state_dict_type: FULL_STATE_DICT
# fsdp_transformer_layer_cls_to_wrap: BTLMBlock
|