Created
March 1, 2024 19:47
-
-
Save hamelsmu/7743960b99e49662ceece418c90c4b51 to your computer and use it in GitHub Desktop.
URL for yaml
This file contains hidden or 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-v0.1 | |
model_type: MistralForCausalLM | |
tokenizer_type: LlamaTokenizer | |
is_mistral_derived_model: true | |
load_in_8bit: false | |
load_in_4bit: true | |
strict: false | |
lora_fan_in_fan_out: false | |
data_seed: 49 | |
seed: 49 | |
datasets: | |
- path: https://gist.githubusercontent.com/hamelsmu/764ebc8b63d41c6fa01af6ae43c8adba/raw/cd330fec9bef80e07949d289f639c9b1212e4419/test_data.jsonl | |
type: sharegpt | |
conversation: alpaca | |
val_set_size: 0.1 | |
output_dir: ./qlora-alpaca-out | |
adapter: qlora | |
lora_model_dir: | |
sequence_len: 896 | |
sample_packing: false | |
pad_to_sequence_len: true | |
lora_r: 32 | |
lora_alpha: 16 | |
lora_dropout: 0.05 | |
lora_target_linear: true | |
lora_fan_in_fan_out: | |
lora_target_modules: | |
- gate_proj | |
- down_proj | |
- up_proj | |
- q_proj | |
- v_proj | |
- k_proj | |
- o_proj | |
# wandb_project: hc-axolotl-mistral | |
# wandb_entity: hamelsmu | |
gradient_accumulation_steps: 4 | |
micro_batch_size: 16 | |
eval_batch_size: 16 | |
num_epochs: 3 | |
optimizer: adamw_bnb_8bit | |
lr_scheduler: cosine | |
learning_rate: 0.0002 | |
max_grad_norm: 1.0 | |
adam_beta2: 0.95 | |
adam_epsilon: 0.00001 | |
save_total_limit: 12 | |
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: 1 | |
xformers_attention: | |
flash_attention: true | |
loss_watchdog_threshold: 5.0 | |
loss_watchdog_patience: 3 | |
warmup_steps: 20 | |
evals_per_epoch: 4 | |
eval_table_size: | |
eval_table_max_new_tokens: 128 | |
saves_per_epoch: 6 | |
debug: | |
weight_decay: 0.0 | |
fsdp: | |
fsdp_config: | |
special_tokens: | |
bos_token: "<s>" | |
eos_token: "</s>" | |
unk_token: "<unk>" | |
save_safetensors: true |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment