File size: 1,088 Bytes
1ceb502
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
assistant_tag: assistant
bf16: true
content_tag: value
cutoff_len: 16384
dataloader_num_workers: 4
dataloader_persistent_workers: true
dataloader_pin_memory: true
dataset: mlfoundations-dev/KodCode-V1-SFT-R1
dataset_dir: ONLINE
ddp_timeout: 180000000
deepspeed: dcft/train/zero3.json
do_train: true
enable_liger_kernel: false
finetuning_type: full
formatting: sharegpt
global_batch_size: 512
gradient_accumulation_steps: 16
hub_model_id: mlfoundations-dev/KodCode-V1-SFT-R1_300k_batch_size_512
include_hp: dcft/train/hp_settings/reasoning.yaml
learning_rate: 8.0e-05
logging_steps: 1
lr_scheduler_type: cosine
messages: conversations
model_name_or_path: Qwen/Qwen2.5-7B-Instruct
neat_packing: true
num_train_epochs: 3.0
output_dir: /tmp/dcft_checkpoints/KodCode-V1-SFT-R1_300k
overwrite_cache: true
packing: false
per_device_train_batch_size: 1
plot_loss: true
preprocessing_num_workers: 16
push_to_db: true
push_to_hub: true
report_to: wandb
role_tag: from
run_name: KodCode-V1-SFT-R1_300k_batch_size_512
save_strategy: epoch
stage: sft
template: qwen25
user_tag: user
warmup_ratio: 0.1