ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme

Browse Source 
Former-commit-id: a1477208471039d3578980f929f1ca8c2a07aa96
This commit is contained in:
hiyouga
2024-06-24 18:22:12 +08:00
parent 4513a2cc75
commit 4c89aca243
5 changed files with 85 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/llamafactory/train/ppo/trainer.py
View File

@@ -202,18 +202,18 @@ class CustomPPOTrainer(PPOTrainer, Trainer):
if self.is_world_process_zero():
logger.info("***** Running training *****")
logger.info(" Num examples = {}".format(num_examples))
logger.info(" Num Epochs = {}".format(num_train_epochs))
logger.info(" Instantaneous batch size per device = {}".format(self.args.per_device_train_batch_size))
logger.info(" Num examples = {:,}".format(num_examples))
logger.info(" Num Epochs = {:,}".format(num_train_epochs))
logger.info(" Instantaneous batch size per device = {:,}".format(self.args.per_device_train_batch_size))
logger.info(
" Total train batch size (w. parallel, buffer, distributed & accumulation) = {}".format(
" Total train batch size (w. parallel, buffer, distributed & accumulation) = {:,}".format(
total_train_batch_size
)
)
logger.info(" Gradient Accumulation steps = {}".format(self.args.gradient_accumulation_steps))
logger.info(" Num optimization epochs per batch = {}".format(self.finetuning_args.ppo_epochs))
logger.info(" Total training steps = {}".format(max_steps))
logger.info(" Number of trainable parameters = {}".format(count_parameters(self.model)[0]))
logger.info(" Gradient Accumulation steps = {:,}".format(self.args.gradient_accumulation_steps))
logger.info(" Num optimization epochs per batch = {:,}".format(self.finetuning_args.ppo_epochs))
logger.info(" Total training steps = {:,}".format(max_steps))
logger.info(" Number of trainable parameters = {:,}".format(count_parameters(self.model)[0]))
dataiter = iter(self.dataloader)
loss_meter = AverageMeter()