From e854df55098fc91ec064a3e74ca49490a9b9551d Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Mon, 3 Mar 2025 23:59:11 -0800 Subject: [PATCH] Update llama.py --- unsloth/models/llama.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 6bff0f217e..bcabbd5125 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -1882,7 +1882,7 @@ 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 ({self._train_batch_size}*{args.gradient_accumulation_steps}*{args.world_size}) = {total_train_batch_size:,}\\n"\\ + f"{chr(92)} / Data Parallel GPUs = {args.world_size} | Total batch size ({self._train_batch_size} x {args.gradient_accumulation_steps} x {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}% trained)' logger.warning(debug_info) import subprocess, re, gc