File size: 1,385 Bytes
157a762 |
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 |
base_model: /workspace/Mixtral-8x7B-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
model_config:
output_router_logits: true
router_aux_loss_coef: 0.02
router_z_loss_coef: 0.001
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: /workspace/ERPLogic2.json
type: alpaca
prompt_format: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.04
output_dir: ./mixtral-lora
save_safetensors: true
adapter: qlora
lora_model_dir:
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
lora_r: 128
lora_alpha: 256
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
# lora_target_modules:
wandb_project: mixtral-lora
wandb_entity: Saofiqlord
wandb_watch:
wandb_run_id:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 5
eval_batch_size: 5
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000242
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
auto_resume_from_checkpoints: true
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 25
eval_steps: 0.05
save_steps: 220
eval_table_size:
eval_table_max_new_tokens: 128
weight_decay: 0.0
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
|