ml-prototype/config.yaml at main · small-thinking/ml-prototype · GitHub

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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
# lightning.pytorch==2.0.6
seed_everything: 42
trainer:
  accelerator: auto
  strategy: auto
  devices: auto
  num_nodes: 1
  precision: 32-true
  logger: null
  callbacks: null
  fast_dev_run: false
  max_epochs: 10
  min_epochs: null
  max_steps: -1
  min_steps: null
  max_time: null
  limit_train_batches: null
  limit_val_batches: null
  limit_test_batches: null
  limit_predict_batches: null
  overfit_batches: 0.0
  val_check_interval: null
  check_val_every_n_epoch: 1
  num_sanity_val_steps: null
  log_every_n_steps: null
  enable_checkpointing: null
  enable_progress_bar: null
  enable_model_summary: null
  accumulate_grad_batches: 1
  gradient_clip_val: null
  gradient_clip_algorithm: null
  deterministic: null
  benchmark: null
  inference_mode: true
  use_distributed_sampler: true
  profiler: null
  detect_anomaly: false
  barebones: false
  plugins: null
  sync_batchnorm: false
  reload_dataloaders_every_n_epochs: 0
  default_root_dir: null
ckpt_path: null
model:
  class_path: lm.model.LanguageModel
  init_args:
    model:
      class_path: lm.module.BaseModel
      init_args:
        config:
          vocab_size: 64
          embed_dim: 32
    loss:
      class_path: torch.nn.CrossEntropyLoss
      init_args:
        weight: null
        size_average: null
        ignore_index: -100
        reduce: null
        reduction: mean
        label_smoothing: 0.0
data:
  class_path: lm.data_module.InMemoryDataModule
  init_args:
    config:
      data_path: /Users/yjiang/Downloads/test_data.txt
      batch_size: 128
      context_size: 16
optimizer:
  class_path: torch.optim.AdamW
  init_args:
    lr: 0.0001
    betas:
    - 0.9
    - 0.999
    eps: 1.0e-08
    weight_decay: 0.01
    amsgrad: false
    maximize: false
    foreach: null
    capturable: false
    differentiable: false
    fused: null