File size: 905 Bytes
409a825
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Model arguments
model_name_or_path: sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
torch_dtype: null

# Data training arguments
# For definitions, see: src/h4/training/config.py
dataset_mixer:
  HuggingFaceH4/ultrafeedback_binarized: 1.0
dataset_splits:
- train_prefs
- test_prefs
preprocessing_num_workers: 12

# DPOTrainer arguments
bf16: true
beta: 0.01
do_eval: true
evaluation_strategy: steps
eval_steps: 100
gradient_accumulation_steps: 2
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: False
learning_rate: 5.0e-7
log_level: info
logging_steps: 25
lr_scheduler_type: cosine
max_length: 1024
max_prompt_length: 512
num_train_epochs: 1
optim: adamw_torch
output_dir: ./
per_device_train_batch_size: 8
per_device_eval_batch_size: 8
push_to_hub: true
save_strategy: "steps"
save_steps: 100
save_total_limit: 1
seed: 42
warmup_ratio: 0.1
report_to:
- tensorboard
- wandb