Created
January 21, 2024 19:13
-
-
Save wenzhe-log10/691693e04921d52d3ff4b85edfab3ef7 to your computer and use it in GitHub Desktop.
axolotl config file for mistral-7b-instruct-v0.2 and llama-2-70b-chat
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
base_model: NousResearch/Llama-2-70b-chat-hf | |
model_type: LlamaForCausalLM | |
tokenizer_type: LlamaTokenizer | |
is_llama_derived_model: true | |
load_in_8bit: false | |
load_in_4bit: true | |
strict: false | |
datasets: | |
- path: my_data.jsonl | |
type: alpaca | |
dataset_prepared_path: | |
val_set_size: 0 | |
output_dir: ./lora-out | |
adapter: qlora | |
lora_model_dir: | |
sequence_len: 4096 | |
sample_packing: true | |
pad_to_sequence_len: true | |
lora_r: 32 | |
lora_alpha: 16 | |
lora_dropout: 0.05 | |
lora_target_linear: true | |
lora_fan_in_fan_out: | |
wandb_project: | |
wandb_entity: | |
wandb_watch: | |
wandb_run_id: | |
wandb_log_model: | |
gradient_accumulation_steps: 4 | |
micro_batch_size: 2 | |
num_epochs: 3 | |
optimizer: adamw_bnb_8bit | |
lr_scheduler: cosine | |
learning_rate: 0.0002 | |
train_on_inputs: false | |
group_by_length: false | |
bf16: true | |
fp16: false | |
tf32: false | |
gradient_checkpointing: true | |
early_stopping_patience: | |
resume_from_checkpoint: | |
local_rank: | |
logging_steps: 50 | |
xformers_attention: | |
flash_attention: true | |
warmup_steps: 10 | |
save_steps: | |
debug: | |
deepspeed: | |
weight_decay: 0.0 | |
fsdp: | |
fsdp_config: | |
special_tokens: | |
bos_token: "<s>" | |
eos_token: "</s>" | |
unk_token: "<unk>" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
base_model: mistralai/Mistral-7B-Instruct-v0.2 | |
model_type: MistralForCausalLM | |
tokenizer_type: LlamaTokenizer | |
is_mistral_derived_model: true | |
model_config: | |
sliding_window: 4096 | |
load_in_8bit: false | |
strict: false | |
datasets: | |
- path: my_data.jsonl | |
type: alpaca | |
dataset_prepared_path: | |
val_set_size: 0 | |
output_dir: ./lora-out | |
sequence_len: 4096 | |
sample_packing: true | |
eval_sample_packing: false | |
pad_to_sequence_len: true | |
adapter: lora | |
lora_model_dir: | |
lora_r: 16 | |
lora_alpha: 32 | |
lora_dropout: 0.05 | |
lora_target_linear: true | |
lora_fan_in_fan_out: | |
wandb_project: | |
wandb_entity: | |
wandb_watch: | |
wandb_run_id: | |
gradient_accumulation_steps: 1 | |
micro_batch_size: 1 | |
num_epochs: 3 | |
optimizer: adamw_bnb_8bit | |
lr_scheduler: cosine | |
learning_rate: 0.0002 | |
bf16: true | |
fp16: false | |
tf32: false | |
train_on_inputs: false | |
group_by_length: false | |
gradient_checkpointing: true | |
early_stopping_patience: | |
resume_from_checkpoint: | |
local_rank: | |
logging_steps: 50 | |
xformers_attention: | |
flash_attention: true | |
warmup_steps: 10 | |
save_steps: | |
debug: | |
deepspeed: /root/axolotl/deepspeed/zero3.json | |
weight_decay: 0.0 | |
fsdp: | |
fsdp_config: | |
special_tokens: | |
bos_token: "<s>" | |
eos_token: "</s>" | |
unk_token: "<unk>" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment