File size: 1,248 Bytes
a943bbf | 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 | base_model: Qwen/Qwen2.5-7B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: ugaoo/multimedqa_and_wrongonesqwen
type: alpaca
val_set_size: 0
output_dir: ./out/Qwen_Qwen2.5_7B_Instruct_ugaoo_multimedqa_and_wrongonesqwen
sequence_len: 4000
sample_packing: true
pad_to_sequence_len: true
adapter: qlora
lora_r: 256
lora_alpha: 512
lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- up_proj
- down_proj
- gate_proj
wandb_project: testsearch
wandb_entity:
wandb_watch:
wandb_name: Qwen_Qwen2.5_7B_Instruct_ugaoo_multimedqa_and_wrongonesqwen
wandb_log_model:
gradient_accumulation_steps: 3
micro_batch_size: 4
num_epochs: 6
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 5e-6
train_on_inputs: false
group_by_length: false
bf16: auto
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 100
evals_per_epoch: 6
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
save_total_limit: 6 |