File size: 1,152 Bytes
674c576
6b3f509
 
 
 
 
 
 
 
 
e50a64e
6b3f509
 
 
674c576
 
6b3f509
 
 
 
 
 
 
7019509
6b3f509
 
 
9a58e99
2ba4ae8
 
674c576
6b3f509
 
 
674c576
6b3f509
 
2ba4ae8
6b3f509
2ba4ae8
6b3f509
 
 
 
 
 
674c576
 
6b3f509
 
674c576
 
6b3f509
 
 
2ba4ae8
6b3f509
 
 
 
 
 
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
base_model: openlm-research/open_llama_3b_v2
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
push_dataset_to_hub:
datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
dataset_prepared_path:
val_set_size: 0.02
adapter:
lora_model_dir:
sequence_len: 1024
sample_packing: true
lora_r:
lora_alpha:
lora_dropout:
lora_target_modules:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:
output_dir: ./openllama-out
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.000003
train_on_inputs: false
group_by_length: false
float16: true
bf16: false
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
gptq_groupsize:
gptq_model_v1:
warmup_steps: 20
eval_steps: 0.05
save_steps:
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"