diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index f7bfd855c2..d2b457a9cd 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -985,7 +985,7 @@ class FastLlamaModel: debug_info = """debug_info = \\ f"==((====))== Unsloth - Free Apache OSS license | Num GPUs = {args.world_size}\\n"\\ - f" \\\\\\ /| Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,}\\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"\\ / 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):,}' diff --git a/unsloth/models/mistral.py b/unsloth/models/mistral.py index ac9b9fad1f..b591a1da92 100644 --- a/unsloth/models/mistral.py +++ b/unsloth/models/mistral.py @@ -390,7 +390,7 @@ class FastMistralModel(FastLlamaModel): debug_info = """debug_info = \\ f"==((====))== Unsloth - Free Apache OSS license | Num GPUs = {args.world_size}\\n"\\ - f" \\\\\\ /| Num examples = {num_examples:,} | Num Epochs = {num_train_epochs:,}\\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"\\ / 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):,}'