File size: 1,480 Bytes
0852336 |
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 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 |
#Mistral-7b
base_model: NousResearch/Meta-Llama-3-8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: m-a-p/COIG-CQIA
data_files: COIG-CQIA-full.jsonl
type: alpaca:chatml
chat_template: chatml
dataset_prepared_path: cqia #Path to json dataset file in huggingface
val_set_size: 0.05
output_dir: ./llama3-cqia-out
adapter: qlora
lora_model_dir:
sequence_len: 5120
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project: llama3-cqia
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 2
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens:
saves_per_epoch: 1
debug: true
deepspeed:
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
eos_token: "<|im_end|>"
pad_token: "<|end_of_text|>"
tokens:
- "<|im_start|>"
- "<|im_end|>" |