File size: 1,100 Bytes
94f5e41
4818380
 
94f5e41
 
 
 
 
 
 
 
4818380
94f5e41
 
 
 
 
 
 
4818380
94f5e41
 
 
4818380
 
 
94f5e41
4818380
 
 
 
94f5e41
 
 
 
4818380
94f5e41
 
4818380
 
 
 
 
 
 
 
 
 
 
 
 
165da58
4818380
 
 
 
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
base_model: stabilityai/stablelm-base-alpha-3b
base_model_config: stabilityai/stablelm-base-alpha-3b
load_in_8bit: false
datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.04
adapter:
lora_model_dir:
sequence_len: 4096
max_packed_sequence_len: 4096
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
lora_fan_in_fan_out: false
wandb_project: stable-alpaca-3b
wandb_watch:
wandb_run_id:
wandb_log_model: checkpoint
output_dir: ./stable-alpaca-3b
batch_size: 2
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.0000002
train_on_inputs: false
group_by_length: false
bf16: true
tf32: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention: true
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 100
eval_steps: 50
save_steps: 200
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
#tokens:
#  pad_token: "[PAD]"
#  bos_token: "<s>"
#  eos_token: "</s>"
#  unk_token: "<unk>"