Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
dpo.yaml 1.03 KB
Newer Older
chenzk's avatar
v1.0  
chenzk committed
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 
base_model: Qwen/Qwen2.5-0.5B
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

chat_template: qwen_25
rl: dpo
datasets:
  - path: fozziethebeat/alpaca_messages_2k_dpo_test
    type: chat_template.default
    field_messages: conversation
    field_chosen: chosen
    field_rejected: rejected
    message_property_mappings:
      role: role
      content: content
    roles:
      system:
        - system
      user:
        - user
      assistant:
        - assistant

dataset_prepared_path:
val_set_size: 0.0
output_dir: ./outputs/dpo-out

sequence_len: 2048
sample_packing: false
pad_to_sequence_len: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: false

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0