File size: 1,561 Bytes
0564d0a 8c72d2d 0564d0a 8c72d2d 0564d0a 8c72d2d 0564d0a 8c72d2d 0564d0a |
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 93 94 95 96 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: ../upsampled_train.json
ds_type: json
type: alpaca
split: train
test_datasets:
- path: ../val.json
ds_type: json
type: alpaca
split: train
load_best_model_at_end: False
early_stopping_patience:
dataset_prepared_path:
val_set_size: 0
output_dir: ./mistral-ins-upsample-1st
adapter: qlora
lora_model_dir:
sequence_len: 4096
sample_packing: false
pad_to_sequence_len: false
lora_r: 32
lora_alpha: 16
lora_dropout: 0.15
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: fine-tune-sal
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:
gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0001
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
wandb_project: fine-tune-sal
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:
warmup_steps: 10
eval_steps: 0.05
eval_table_size:
eval_table_max_new_tokens: 128
save_steps: 0.05
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
|