File size: 1,626 Bytes
ad3e574
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
top.booster: none
top.checkpoint_path: []
top.finetuning_type: lora
top.model_name: Qwen2-7B-Chat
top.quantization_bit: none
top.rope_scaling: none
top.template: qwen
top.visual_inputs: false
train.additional_target: ''
train.badam_mode: layer
train.badam_switch_interval: 50
train.badam_switch_mode: ascending
train.badam_update_ratio: 0.05
train.batch_size: 1
train.compute_type: fp16
train.create_new_adapter: false
train.cutoff_len: 2048
train.dataset:
- farcaster_pretrain
train.dataset_dir: data
train.ds_offload: false
train.ds_stage: none
train.freeze_extra_modules: ''
train.freeze_trainable_layers: 2
train.freeze_trainable_modules: all
train.galore_rank: 16
train.galore_scale: 0.25
train.galore_target: all
train.galore_update_interval: 200
train.gradient_accumulation_steps: 8
train.learning_rate: 2e-4
train.logging_steps: 1
train.lora_alpha: 16
train.lora_dropout: 0
train.lora_rank: 256
train.lora_target: ''
train.loraplus_lr_ratio: 0
train.lr_scheduler_type: cosine
train.max_grad_norm: '1.0'
train.max_samples: '100000'
train.neftune_alpha: 0
train.num_train_epochs: '8'
train.optim: adamw_8bit
train.packing: true
train.ppo_score_norm: false
train.ppo_whiten_rewards: false
train.pref_beta: 0.1
train.pref_ftx: 0
train.pref_loss: sigmoid
train.report_to: false
train.resize_vocab: false
train.reward_model: null
train.save_steps: 100
train.shift_attn: false
train.training_stage: Pre-Training
train.upcast_layernorm: false
train.use_badam: false
train.use_dora: false
train.use_galore: false
train.use_llama_pro: false
train.use_pissa: false
train.use_rslora: false
train.val_size: 0
train.warmup_steps: 0