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 2024-12-01 02:02:31 -08:00
commit a45d642641
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

@ -1551,7 +1551,7 @@ class FastLlamaModel:
statistics = \
f"==((====))== Unsloth {__version__}: Fast {model_patcher.__name__[4:-5]} patching. Transformers:{transformers_version}.\n"\
f" \\\ /| GPU: {gpu_stats.name}. Max memory: {max_memory} GB. Platform: {platform_system}.\n"\
f"O^O/ \_/ \\ Torch: {torch.__version__}. CUDA: {gpu_stats.major}.{gpu_stats.minor}. CUDA Toolkit: {torch.version.cuda}. Triton: {triton_version}\n"\
f"O^O/ \+/ \\ Torch: {torch.__version__}. CUDA: {gpu_stats.major}.{gpu_stats.minor}. CUDA Toolkit: {torch.version.cuda}. Triton: {triton_version}\n"\
f"\ / Bfloat16 = {str(SUPPORTS_BFLOAT16).upper()}. FA [Xformers = {xformers_version}. FA2 = {HAS_FLASH_ATTENTION}]\n"\
f' "-____-" Free Apache license: http://github.com/unslothai/unsloth'
print(statistics)
@ -1709,7 +1709,7 @@ class FastLlamaModel:
debug_info = """debug_info = \\
f"==((====))== Unsloth - 2x faster free finetuning | Num GPUs = {args.world_size}\\n"\\
f" \\\\\\ /| Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,}\\n"\\
f"O^O/ \\_/ \\ Batch size per device = {self._train_batch_size:,} | Gradient Accumulation steps = {args.gradient_accumulation_steps}\\n"\\
f"O^O/ \\+/ \\ Batch size per device = {self._train_batch_size:,} | Gradient Accumulation steps = {args.gradient_accumulation_steps}\\n"\\
f"\\ / Total batch size = {total_train_batch_size:,} | Total steps = {max_steps:,}\\n"\\
f' "-____-" Number of trainable parameters = {get_model_param_count(model, trainable_only=True):,}'
logger.warning(debug_info)