File size: 1,053 Bytes
c530e4b e50a64e f544ab2 c530e4b 7019509 c530e4b a1da39c c530e4b 36fefcf 782b6a4 c530e4b 5f79b82 c530e4b |
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 |
base_model: EleutherAI/gpt-j-6b
load_in_8bit: false
load_in_4bit: true
strict: false
push_dataset_to_hub:
datasets:
- path: teknium/GPT4-LLM-Cleaned
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
adapter: qlora
lora_model_dir:
sequence_len: 2048
max_packed_sequence_len:
lora_r: 8
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
output_dir: ./qlora-out
gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 2
optimizer: paged_adamw_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.0001
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention: true
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
pad_token: "<|endoftext|>"
|