Spaces:
Runtime error
Runtime error
File size: 10,093 Bytes
b87a3ce |
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 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 |
import gradio as gr
import logging
import os
import threading
import time
import transformers
from transformers.trainer import TRAINING_ARGS_NAME
from typing import Any, Dict, Generator, List, Tuple
from llmtuner.extras.callbacks import LogCallback
from llmtuner.extras.constants import DEFAULT_MODULE, TRAINING_STAGES
from llmtuner.extras.logging import LoggerHandler
from llmtuner.extras.misc import torch_gc
from llmtuner.tuner import run_exp
from llmtuner.webui.common import get_model_path, get_save_dir, load_config
from llmtuner.webui.locales import ALERTS
from llmtuner.webui.utils import gen_cmd, get_eval_results, update_process_bar
class Runner:
def __init__(self):
self.aborted = False
self.running = False
self.logger_handler = LoggerHandler()
self.logger_handler.setLevel(logging.INFO)
logging.root.addHandler(self.logger_handler)
transformers.logging.add_handler(self.logger_handler)
def set_abort(self):
self.aborted = True
self.running = False
def _initialize(
self, lang: str, model_name: str, dataset: List[str]
) -> str:
if self.running:
return ALERTS["err_conflict"][lang]
if not model_name:
return ALERTS["err_no_model"][lang]
if not get_model_path(model_name):
return ALERTS["err_no_path"][lang]
if len(dataset) == 0:
return ALERTS["err_no_dataset"][lang]
self.aborted = False
self.logger_handler.reset()
self.trainer_callback = LogCallback(self)
return ""
def _finalize(
self, lang: str, finish_info: str
) -> str:
self.running = False
torch_gc()
if self.aborted:
return ALERTS["info_aborted"][lang]
else:
return finish_info
def _parse_train_args(
self,
lang: str,
model_name: str,
checkpoints: List[str],
finetuning_type: str,
quantization_bit: str,
template: str,
system_prompt: str,
training_stage: str,
dataset_dir: str,
dataset: List[str],
cutoff_len: int,
learning_rate: str,
num_train_epochs: str,
max_samples: str,
compute_type: str,
batch_size: int,
gradient_accumulation_steps: int,
lr_scheduler_type: str,
max_grad_norm: str,
val_size: float,
logging_steps: int,
save_steps: int,
warmup_steps: int,
flash_attn: bool,
rope_scaling: bool,
lora_rank: int,
lora_dropout: float,
lora_target: str,
resume_lora_training: bool,
dpo_beta: float,
reward_model: str,
output_dir: str
) -> Tuple[str, str, List[str], str, Dict[str, Any]]:
if checkpoints:
checkpoint_dir = ",".join(
[get_save_dir(model_name, finetuning_type, ckpt) for ckpt in checkpoints]
)
else:
checkpoint_dir = None
output_dir = get_save_dir(model_name, finetuning_type, output_dir)
user_config = load_config()
cache_dir = user_config.get("cache_dir", None)
args = dict(
stage=TRAINING_STAGES[training_stage],
model_name_or_path=get_model_path(model_name),
do_train=True,
overwrite_cache=False,
cache_dir=cache_dir,
checkpoint_dir=checkpoint_dir,
finetuning_type=finetuning_type,
quantization_bit=int(quantization_bit) if quantization_bit in ["8", "4"] else None,
template=template,
system_prompt=system_prompt,
dataset_dir=dataset_dir,
dataset=",".join(dataset),
cutoff_len=cutoff_len,
learning_rate=float(learning_rate),
num_train_epochs=float(num_train_epochs),
max_samples=int(max_samples),
per_device_train_batch_size=batch_size,
gradient_accumulation_steps=gradient_accumulation_steps,
lr_scheduler_type=lr_scheduler_type,
max_grad_norm=float(max_grad_norm),
logging_steps=logging_steps,
save_steps=save_steps,
warmup_steps=warmup_steps,
flash_attn=flash_attn,
rope_scaling="linear" if rope_scaling else None,
lora_rank=lora_rank,
lora_dropout=lora_dropout,
lora_target=lora_target or DEFAULT_MODULE.get(model_name.split("-")[0], "q_proj,v_proj"),
resume_lora_training=(
False if TRAINING_STAGES[training_stage] in ["rm", "ppo", "dpo"] else resume_lora_training
),
output_dir=output_dir
)
args[compute_type] = True
if args["stage"] == "ppo":
args["reward_model"] = reward_model
val_size = 0
if args["stage"] == "dpo":
args["dpo_beta"] = dpo_beta
if val_size > 1e-6:
args["val_size"] = val_size
args["evaluation_strategy"] = "steps"
args["eval_steps"] = save_steps
args["load_best_model_at_end"] = True
return lang, model_name, dataset, output_dir, args
def _parse_eval_args(
self,
lang: str,
model_name: str,
checkpoints: List[str],
finetuning_type: str,
quantization_bit: str,
template: str,
system_prompt: str,
dataset_dir: str,
dataset: List[str],
cutoff_len: int,
max_samples: str,
batch_size: int,
predict: bool,
max_new_tokens: int,
top_p: float,
temperature: float
) -> Tuple[str, str, List[str], str, Dict[str, Any]]:
if checkpoints:
checkpoint_dir = ",".join(
[get_save_dir(model_name, finetuning_type, ckpt) for ckpt in checkpoints]
)
output_dir = get_save_dir(model_name, finetuning_type, "eval_" + "_".join(checkpoints))
else:
checkpoint_dir = None
output_dir = get_save_dir(model_name, finetuning_type, "eval_base")
user_config = load_config()
cache_dir = user_config.get("cache_dir", None)
args = dict(
stage="sft",
model_name_or_path=get_model_path(model_name),
do_eval=True,
overwrite_cache=False,
predict_with_generate=True,
cache_dir=cache_dir,
checkpoint_dir=checkpoint_dir,
finetuning_type=finetuning_type,
quantization_bit=int(quantization_bit) if quantization_bit in ["8", "4"] else None,
template=template,
system_prompt=system_prompt,
dataset_dir=dataset_dir,
dataset=",".join(dataset),
cutoff_len=cutoff_len,
max_samples=int(max_samples),
per_device_eval_batch_size=batch_size,
max_new_tokens=max_new_tokens,
top_p=top_p,
temperature=temperature,
output_dir=output_dir
)
if predict:
args.pop("do_eval", None)
args["do_predict"] = True
return lang, model_name, dataset, output_dir, args
def preview_train(self, *args) -> Generator[Tuple[str, Dict[str, Any]], None, None]:
lang, model_name, dataset, _, args = self._parse_train_args(*args)
error = self._initialize(lang, model_name, dataset)
if error:
yield error, gr.update(visible=False)
else:
yield gen_cmd(args), gr.update(visible=False)
def preview_eval(self, *args) -> Generator[Tuple[str, Dict[str, Any]], None, None]:
lang, model_name, dataset, _, args = self._parse_eval_args(*args)
error = self._initialize(lang, model_name, dataset)
if error:
yield error, gr.update(visible=False)
else:
yield gen_cmd(args), gr.update(visible=False)
def run_train(self, *args) -> Generator[Tuple[str, Dict[str, Any]], None, None]:
lang, model_name, dataset, output_dir, args = self._parse_train_args(*args)
error = self._initialize(lang, model_name, dataset)
if error:
yield error, gr.update(visible=False)
return
self.running = True
run_kwargs = dict(args=args, callbacks=[self.trainer_callback])
thread = threading.Thread(target=run_exp, kwargs=run_kwargs)
thread.start()
while thread.is_alive():
time.sleep(2)
if self.aborted:
yield ALERTS["info_aborting"][lang], gr.update(visible=False)
else:
yield self.logger_handler.log, update_process_bar(self.trainer_callback)
if os.path.exists(os.path.join(output_dir, TRAINING_ARGS_NAME)):
finish_info = ALERTS["info_finished"][lang]
else:
finish_info = ALERTS["err_failed"][lang]
yield self._finalize(lang, finish_info), gr.update(visible=False)
def run_eval(self, *args) -> Generator[str, None, None]:
lang, model_name, dataset, output_dir, args = self._parse_eval_args(*args)
error = self._initialize(lang, model_name, dataset)
if error:
yield error, gr.update(visible=False)
return
self.running = True
run_kwargs = dict(args=args, callbacks=[self.trainer_callback])
thread = threading.Thread(target=run_exp, kwargs=run_kwargs)
thread.start()
while thread.is_alive():
time.sleep(2)
if self.aborted:
yield ALERTS["info_aborting"][lang], gr.update(visible=False)
else:
yield self.logger_handler.log, update_process_bar(self.trainer_callback)
if os.path.exists(os.path.join(output_dir, "all_results.json")):
finish_info = get_eval_results(os.path.join(output_dir, "all_results.json"))
else:
finish_info = ALERTS["err_failed"][lang]
yield self._finalize(lang, finish_info), gr.update(visible=False)
|