File size: 718 Bytes
4095c97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
cutoff_len: 1024
dataset: train
dataset_dir: data
ddp_timeout: 180000000
do_train: true
finetuning_type: lora
flash_attn: fa2
fp16: true
gradient_accumulation_steps: 8
include_num_input_tokens_seen: true
learning_rate: 5.0e-05
logging_steps: 5
lora_alpha: 16
lora_dropout: 0
lora_rank: 8
lora_target: all
lr_scheduler_type: cosine
max_grad_norm: 1.0
max_samples: 100000
model_name_or_path: Qwen/Qwen2-7B-Instruct-GPTQ-Int8
num_train_epochs: 3.0
optim: adamw_torch
output_dir: saves/Qwen2-7B-int8-Chat/lora/train_2024-06-06-20-45-21
packing: false
per_device_train_batch_size: 2
plot_loss: true
preprocessing_num_workers: 16
quantization_bit: 8
report_to: none
save_steps: 100
stage: sft
template: qwen
warmup_steps: 0