基础模型:
- zerofata/L3.3-GeneticLemonade-Unleashed-70B
库名称: transformers
许可证: llama3
基因柠檬水释放版 v3
尝试调整这些设置，它们不是"最佳"设置，只是一个稳定的基准。值得注意的是，该模型支持比其他L3模型通常推荐更高的温度值。
推荐采样器
>
温度:
0.9 - 1.2
>
最小P:
0.03 - 0.04
>
顶部P:
0.9 - 1.0
>
干燥:
0.8, 1.75, 4
指令
使用Llama-3-Instruct-Names模板，但需要取消勾选"系统与用户相同"。
模型首先使用290万token的小型合成数据集(约750个对话)进行SFT训练。主要是RP数据，包含少量随机指令/助手数据和创意写作。
然后使用SFT数据集中约1100个高质量样本进行DPO训练，这些样本展示了出色的指令遵循能力。拒绝样本来自另一个已知指令遵循能力较差的Llama 3.3微调模型生成。
Axolotl配置
两者均未针对成本/性能效率进行优化，效果可能因人而异。
SFT 1*H200
base_model: zerofata/L3.3-GeneticLemonade-Unleashed-70B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
special_tokens:
pad_token: "<|finetune_right_pad_id|>"
chat_template: llama3
datasets:
- path: ./dataset.jsonl
type: chat_template
split: train
chat_template_strategy: tokenizer
field_messages: messages
message_property_mappings:
role: role
content: content
roles:
user: ["user"]
assistant: ["assistant"]
system: ["system"]
test_datasets:
- path: ./validate_dataset.jsonl
type: chat_template
split: train
chat_template_strategy: tokenizer
field_messages: messages
message_property_mappings:
role: role
content: content
roles:
user: ["user"]
assistant: ["assistant"]
system: ["system"]
dataset_prepared_path:
train_on_inputs: false
adapter: qlora
load_in_4bit: true
lora_r: 64
lora_alpha: 128
lora_dropout: 0.1
lora_target_linear: true
num_epochs: 2
micro_batch_size: 4
gradient_accumulation_steps: 2
learning_rate: 1.5e-5
optimizer: paged_adamw_8bit
lr_scheduler: rex
warmup_ratio: 0.05
weight_decay: 0.01
max_grad_norm: 1.0
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
bf16: auto
flash_attention: true
gradient_checkpointing: true
evaluation_strategy: steps
eval_steps: 5
save_strategy: steps
save_steps: 5
save_total_limit: 5
load_best_model_at_end: true
metric_for_best_model: eval_loss
greater_is_better: false
early_stopping_patience: 5
output_dir: ./output_model
logging_steps: 2
save_safetensors: true
wandb_project: project_name
DPO 2*H200
base_model: ApocalypseParty/unleashed-fulldata30
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
special_tokens: {}
chat_template: tokenizer_default
rl: dpo
rl_beta: 0.07
datasets:
- path: ./dpo_cleaned-v3_deduplicated.jsonl
type: chat_template.default
field_messages: conversation
field_chosen: chosen
field_rejected: rejected
message_property_mappings:
role: role
content: content
roles:
system: ["system"]
user: ["user"]
assistant: ["assistant"]
dataset_prepared_path:
train_on_inputs: false
adapter: qlora
load_in_4bit: true
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
num_epochs: 1
micro_batch_size: 4
gradient_accumulation_steps: 2
learning_rate: 2e-6
optimizer: adamw_8bit
lr_scheduler: cosine
warmup_steps: 5
weight_decay: 0.01
max_grad_norm: 1.0
sequence_len: 4096
pad_to_sequence_len: true
bf16: auto
tf32: false
flash_attention: true
gradient_checkpointing: offload
deepspeed: deepspeed_configs/zero1.json
save_steps: 10
save_total_limit: 10
load_best_model_at_end: true
metric_for_best_model: eval_loss
greater_is_better: false
output_dir: ./dpo_model
logging_steps: 2
save_safetensors: true
wandb_project: project_name
Transformers%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20none;%20}%20.st1%20{%20fill:%20%235ce6cf;%20}%20.st2%20{%20fill:%20%230080ff;%20}%20.st3%20{%20clip-path:%20url(%23clippath);%20}%20%3c/style%3e%3cclipPath%20id='clippath'%3e%3crect%20class='st0'%20y='0'%20width='120'%20height='32'/%3e%3c/clipPath%3e%3c/defs%3e%3cg%20class='st3'%3e%3cg%3e%3cpath%20class='st1'%20d='M22.4,32H3.2c-1,0-2-.5-2.6-1.4-.6-.9-.7-2-.4-2.9L9.8,2.1C10.3.8,11.5,0,12.8,0s2.5.8,3,2.1l9.6,25.6c.4,1,.2,2.1-.4,2.9-.6.9-1.6,1.4-2.6,1.4ZM7.8,25.6h10l-5-13.3-5,13.3Z'/%3e%3cpath%20class='st2'%20d='M33.6,32c-1.3,0-2.5-.8-3-2.1L21,4.3c-.6-1.7.2-3.5,1.9-4.1,1.7-.6,3.5.2,4.1,1.9l9.6,25.6c.6,1.7-.2,3.5-1.9,4.1-.4.1-.8.2-1.1.2h0Z'/%3e%3cpath%20d='M71.8,9.1h-6.9v4.6h6.9c2.5,0,4.6,2,4.6,4.6h-6.9c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h2.3c1.7,0,3.2-.4,4.6-1.2v1.2h4.6v-13.7c0-5-4.1-9.1-9.1-9.1h0ZM71.8,27.4h-2.3c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h6.9c0,2.5-2,4.6-4.6,4.6h0Z'/%3e%3cpath%20d='M52.3,9.1h-4.6V0h-4.6V32h9.1c5,0,9.1-4.1,9.1-9.1v-4.6c0-5.1-4.1-9.1-9.1-9.1h0ZM56.9,22.9c0,2.5-2,4.6-4.6,4.6h-4.6v-13.7h4.6c2.5,0,4.6,2,4.6,4.6v4.6h0Z'/%3e%3cpath%20d='M110.9,13.7h9.1v-4.6h-9.1c-5.1,0-9.1,4.1-9.1,9.1v4.6c0,5.1,4.1,9.1,9.1,9.1h9.1v-4.6h-9.1c-2.5,0-4.6-2-4.6-4.6h13.7v-4.6h-13.7c0-2.5,2-4.6,4.6-4.6h0Z'/%3e%3cpath%20d='M93.6,18.3h-4.6c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h10.3v-4.6h-10.3c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h4.6c1.3,0,2.3,1,2.3,2.3s-1,2.3-2.3,2.3h-10.3v4.6h10.3c3.8,0,6.9-3.1,6.9-6.9s-3.1-6.9-6.9-6.9Z'/%3e%3c/g%3e%3c/g%3e%3c/svg%3e)