Hugging Face's logo

nanotron
/
minicpm-nanotron

nanotron
Model card Files Community
minicpm-nanotron
File size: 2,189 Bytes 
54ba632
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
84
85
86
87
88
89
90
91
92
93
 
checkpoints:
  checkpoint_interval: 10
  checkpoints_path: /fsx/thomwolf/github/textbooks-proj/brrr/models/checkpoints
  checkpoints_path_is_shared_file_system: false
  resume_checkpoint_path: null
  save_initial_state: false
data:
  dataset:
    dataset_overwrite_cache: false
    dataset_processing_num_proc_per_process: 1
    hf_dataset_config_name: null
    hf_dataset_or_datasets: HuggingFaceH4/testing_alpaca_small
    hf_dataset_splits: train
    text_column_name: completion
  num_loading_workers: 1
  seed: 42
general:
  benchmark_csv_path: null
  consumed_train_samples: null
  ignore_sanity_checks: false
  project: debug
  run: tiny_mistral
  seed: 42
  step: null
logging:
  iteration_step_info_interval: 1
  log_level: info
  log_level_replica: info
model:
  ddp_bucket_cap_mb: 25
  dtype: bfloat16
  init_method:
    std: 0.025
  make_vocab_size_divisible_by: 1
  model_config:
    attn_pdrop: 0.0
    bos_token_id: 1
    eos_token_id: 2
    hidden_act: silu
    hidden_size: 16
    initializer_range: 0.02
    intermediate_size: 64
    is_mistral_config: true
    max_position_embeddings: 256
    num_attention_heads: 4
    num_hidden_layers: 2
    num_key_value_heads: 4
    pad_token_id: null
    pretraining_tp: 1
    rms_norm_eps: 1.0e-05
    rope_theta: 10000.0
    sliding_window_size: 4096
    tie_word_embeddings: true
    use_cache: true
    vocab_size: 256
optimizer:
  accumulate_grad_in_fp32: true
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_eps: 1.0e-08
  clip_grad: 1.0
  learning_rate_scheduler:
    learning_rate: 0.0003
    lr_decay_steps: 8
    lr_decay_style: cosine
    lr_warmup_steps: 2
    lr_warmup_style: linear
    min_decay_lr: 1.0e-05
  torch_adam_is_fused: true
  weight_decay: 0.01
  zero_stage: 0
parallelism:
  dp: 2
  pp: 2
  pp_engine: 1f1b
  recompute_granularity: SELECTIVE
  tp: 2
  tp_linear_async_communication: true
  tp_mode: REDUCE_SCATTER
profiler: null
tokenizer:
  tokenizer_max_length: null
  tokenizer_name_or_path: gpt2
  tokenizer_revision: null
tokens:
  batch_accumulation_per_replica: 1
  limit_test_batches: 0
  limit_val_batches: 0
  micro_batch_size: 2
  sequence_length: 32
  train_steps: 10
  val_check_interval: -1