5b67ea98a6
* WIP Add training callback to send predictions to WandB table * WIP improve wandb table reporting callback * WIP improve wandb table reporting callback (cont) * Add VSCode launching for debugging * Add tiny llama example * WIP attempt to improve post-eval prediction generation for table * WIP attempt to improve post-eval prediction generation for table - part 2 * WIP batch generation * WIP attempt to handle sample_packing using position_ids for wandb prediction table * WIP add code for debugging * Fix sample_packing support for wandb prediction table * Clean up code for PR review * Add eval_table_size, eval_table_max_new_tokens configs & clean up code * Clean up PR, delete VSCode config, add tiny-llama example * Add eval_table_size, eval_table_max_new_tokens documentation. Fix linting/formatting
70 lines
1.2 KiB
YAML
70 lines
1.2 KiB
YAML
base_model: PY007/TinyLlama-1.1B-step-50K-105b
|
|
base_model_config: PY007/TinyLlama-1.1B-step-50K-105b
|
|
|
|
model_type: LlamaForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
is_llama_derived_model: true
|
|
|
|
load_in_8bit: true
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: mhenrichsen/alpaca_2k_test
|
|
type: alpaca
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.01
|
|
output_dir: ./lora-out
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_run_id:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 2
|
|
num_epochs: 3
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
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
|
|
|
|
warmup_steps: 10
|
|
eval_steps: 20
|
|
eval_table_size: 5
|
|
save_steps:
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
bos_token: "<s>"
|
|
eos_token: "</s>"
|
|
unk_token: "<unk>"
|