ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update llama.py

Browse source
This commit is contained in:
Daniel Han 2025-03-03 23:41:37 -08:00
commit 2793018ea6
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
unsloth/models/llama.py
View file

@ -1882,8 +1882,8 @@ class FastLlamaModel:
f"==((====))== Unsloth - 2x faster free finetuning | Num GPUs used = {len(set(p.device for p in model.parameters()))}\\n"\\
f" {chr(92)}{chr(92)} /| Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,} | Total steps = {max_steps:,}\\n"\\
f"O^O/ {chr(92)}_/ {chr(92)} Batch size per device = {self._train_batch_size:,} | Gradient accumulation steps = {args.gradient_accumulation_steps}\\n"\\
f"{chr(92)} / Data Parallel GPUs = {args.world_size} | Total batch size = {total_train_batch_size:,}\\n"\\
f' "-____-" Number of trainable parameters = {get_model_param_count(model, trainable_only=True):,}/{get_model_param_count(model)}'
f"{chr(92)} / Data Parallel GPUs = {args.world_size} | Total batch size ({self._train_batch_size}*{args.gradient_accumulation_steps}*{args.world_size}) = {total_train_batch_size:,}\\n"\\
f' "-____-" Trainable parameters = {get_model_param_count(model, trainable_only=True):,}/{get_model_param_count(model):,} ({get_model_param_count(model, trainable_only=True)/get_model_param_count(model)*100:.2f})'
logger.warning(debug_info)
import subprocess, re, gc
for _ in range(3):