From d7965b0446b13649b9097a0540bbf9bfdbadbc95 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Sun, 1 Dec 2024 02:30:21 -0800 Subject: [PATCH] Update llama.py --- unsloth/models/llama.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 718f573d2f..f22cf315a1 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -1708,8 +1708,8 @@ class FastLlamaModel: debug_info = """debug_info = \\ f"==((====))== Unsloth - 2x faster free finetuning | Num GPUs = {args.world_size}\\n"\\ - f" {chr(92)}{chr(92)} /| Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,}\\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)}{chr(92)} /| Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,}\\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)} / 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)