|
base_model: Neko-Institute-of-Science/LLaMA-13B-HF |
|
base_model_config: Neko-Institute-of-Science/LLaMA-13B-HF |
|
model_type: LlamaForCausalLM |
|
tokenizer_type: LlamaTokenizer |
|
load_in_8bit: true |
|
load_4bit: |
|
datasets: |
|
- path: practicaldreamer/RPGPT_PublicDomain-ShareGPT |
|
data_files: RPGPT_PublicDomain_v3-sharegpt.json |
|
type: sharegpt |
|
dataset_prepared_path: data/last_run_prepared |
|
val_set_size: 0.0025 |
|
adapter: lora |
|
lora_model_dir: |
|
sequence_len: 2048 |
|
max_packed_sequence_len: |
|
lora_r: 64 |
|
lora_alpha: 128 |
|
lora_dropout: 0.05 |
|
lora_target_modules: |
|
- q_proj |
|
- v_proj |
|
|
|
|
|
lora_fan_in_fan_out: false |
|
wandb_project: |
|
wandb_watch: |
|
wandb_run_id: |
|
wandb_log_model: checkpoint |
|
output_dir: output_dir |
|
batch_size: 128 |
|
micro_batch_size: 4 |
|
eval_batch_size: 1 |
|
num_epochs: 1 |
|
warmup_steps: 50 |
|
logging_steps: |
|
learning_rate: 0.00003 |
|
optimizer: adamw_bnb_8bit |
|
torchdistx_path: |
|
lr_scheduler: cosine |
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: true |
|
tf32: true |
|
gradient_checkpointing: true |
|
early_stopping_patience: 3 |
|
resume_from_checkpoint: |
|
auto_resume_from_checkpoints: |
|
local_rank: |
|
xformers_attention: true |
|
flash_attention: |
|
gptq_groupsize: |
|
gptq_model_v1: |
|
save_steps: 4 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
fsdp_transformer_layer_cls_to_wrap: |
|
fsdp_min_num_params: 2000 |
|
fsdp_backward_prefetch: |
|
- backward_pre |
|
limit_all_gathers: false |
|
special_tokens: |
|
pad_token: "[PAD]" |
|
bos_token: "<s>" |
|
eos_token: "</s>" |
|
unk_token: "<unk>" |
|
|
