|
base_model: anon8231489123/vicuna-13b-GPTQ-4bit-128g |
|
base_model_config: anon8231489123/vicuna-13b-GPTQ-4bit-128g |
|
model_type: LlamaForCausalLM |
|
tokenizer_type: LlamaTokenizer |
|
load_in_8bit: false |
|
load_4bit: true |
|
gptq_groupsize: 128 |
|
gptq_model_v1: false |
|
datasets: |
|
- path: data/alpaca_reflect_pruned.jsonl |
|
type: reflection |
|
dataset_prepared_path: data/last_run_prepared |
|
val_set_size: 0.04 |
|
adapter: |
|
lora_model_dir: |
|
sequence_len: 2048 |
|
max_packed_sequence_len: 2048 |
|
lora_r: 8 |
|
lora_alpha: 16 |
|
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: ./vicuna-reflect |
|
batch_size: 8 |
|
micro_batch_size: 2 |
|
num_epochs: 3 |
|
learning_rate: 0.00003 |
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: true |
|
tf32: true |
|
gradient_checkpointing: false |
|
early_stopping_patience: 3 |
|
resume_from_checkpoint: |
|
local_rank: |
|
flash_attention: true |
|
|
|
|
