File size: 1,703 Bytes
7fabc4d 68b227a 35f9b0f 68b227a 5ea3aa3 628b754 68b227a 782b6a4 68b227a 5f79b82 68b227a 5f79b82 68b227a 54d2ac1 68b227a |
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 83 84 85 86 87 88 89 90 91 92 |
base_model: mistralai/Mixtral-8x7B-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: tatsu-lab/alpaca
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./qlora-out
## You can optionally freeze the entire model and unfreeze a subset of parameters
unfrozen_parameters:
# - lm_head.*
# - model.embed_tokens.*
# - model.layers.2[0-9]+.block_sparse_moe.gate.*
# - model.layers.2[0-9]+.block_sparse_moe.experts.*
# - model.layers.3[0-9]+.block_sparse_moe.gate.*
# - model.layers.3[0-9]+.block_sparse_moe.experts.*
model_config:
output_router_logits: true
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:
#lora_target_modules:
# - gate
# - q_proj
# - k_proj
# - v_proj
# - o_proj
# - w1
# - w2
# - w3
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
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: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero2.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
|