Hugging Face's logo

TAUR-dev
/
testing__pvv2_lora

Safetensors
qwen2
Model card Files
xet
 Community
testing__pvv2_lora
File size: 2,911 Bytes
2203975
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
_target_: null
job:
  name: testing__pvv2_lora
  mode: local
  dry_run: false
  work_dir: null
slurm:
  time_limit: null
  constraint: null
  memory: null
  cpus_per_task: 16
  partition: null
  mail_user: null
execution:
  nodes: 1
  gpus_per_node: 2
  num_gpus: null
  hostfile: null
  secrets_file: ./secrets.env
model:
  name_or_path: Qwen/Qwen2.5-1.5B-Instruct
  finetuning_type: lora
dataset:
  name: TAUR_dev_D_SFT_C_ours_cd3arg_10responses_reflections10_formats_C_full
  dir: null
  info_json: null
  template: qwen
  cutoff_len: 16192
  val_size: 0.0
  tokenized_path: /scratch/zrs2020/.cache/llamafactory/tokenized/TAUR_dev_D_SFT_C_ours_cd3arg_10responses_reflections10_formats_C_full
  hf_hub_url: TAUR-dev/D-SFT_C-ours_cd3arg_10responses_reflections10_formats-C_full
  formatting: sharegpt
  ranking: false
  subset: null
  split: train
  folder: null
  num_samples: null
  columns:
    prompt: null
    query: null
    response: null
    history: null
    messages: conversations
    system: null
    tools: null
    images: null
    videos: null
    audios: null
    chosen: null
    rejected: null
    kto_tag: null
  tags:
    role: role
    content: content
    user: user
    assistant: assistant
    observation: null
    function: null
    system: null
output:
  experiment_dir: ./experiments
wandb:
  project: null
  run_name: testing__pvv2_lora
  entity: null
hf:
  repo_id: TAUR-dev/testing__pvv2_lora
  private: false
  upload_artifacts: true
cleanup:
  checkpoints: false
  merged: false
training:
  stage: sft
  do_train: true
  max_samples: 100000
  do_eval: false
  save_strategy: steps
  save_steps: 5
  logging_steps: 10
  fp16: false
  bf16: true
  adam_beta1: 0.9
  adam_beta2: 0.95
  overwrite_output_dir: true
  per_device_train_batch_size: 1
  gradient_accumulation_steps: 1
  gradient_checkpointing: true
  learning_rate: 1.0e-06
  lr_scheduler_type: cosine
  num_train_epochs: 2
  warmup_ratio: 0.05
  weight_decay: 0.0001
  template: qwen
  max_steps: 10
  preprocessing_num_workers: 16
  overwrite_cache: true
finetuning:
  training:
    stage: sft
    do_train: true
    finetuning_type: lora
    lora_rank: 8
    lora_alpha: 16
    lora_dropout: 0.05
    lora_target: all
    overwrite_cache: true
    preprocessing_num_workers: 16
    dataloader_num_workers: 4
    logging_steps: 10
    save_steps: 500
    plot_loss: true
    overwrite_output_dir: true
    save_only_model: false
    report_to: none
    per_device_train_batch_size: 1
    gradient_accumulation_steps: 8
    learning_rate: 0.0001
    num_train_epochs: 3.0
    lr_scheduler_type: cosine
    warmup_ratio: 0.1
    bf16: true
    ddp_timeout: 180000000
    resume_from_checkpoint: null
    val_size: 0.1
    per_device_eval_batch_size: 1
    eval_strategy: steps
    eval_steps: 500
    do_eval: true
  merge:
    export_dir: null
    export_size: 5
    export_device: cpu
    export_legacy_format: false