# Trainer() shows no log for validation loss when using PEFT
**URL:**
**Author:**  [@AnahitaTabrizian](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAnahitaTabrizian)%5C
**Post date:** [April 17, 2024, 8:23pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrainer-shows-no-log-for-validation-loss-when-using-peft%2F82298%2F1 "2024-04-17T20:23:33Z")
I modified the code from the notebook provided in this course.([Fine-tuning a model with the Trainer API](https://huggingface.co/learn/nlp-course/en/chapter3/3)).The following code produces validation loss while training and uses the compute metric when I am not using PEFT. But when I am using PEFT, it is showing “no log” as validation loss and skips the compute metric. what can be the problem?
```auto
from peft import LoraConfig , prepare_model_for_kbit_training , get_peft_model
lora_config = LoraConfig(
r=8,
target_modules=["query", "key","value"],
bias="none",
lora_alpha=16,
lora_dropout=0.1
)
```
```auto
from transformers import AutoModelForSequenceClassification
model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2)
```
```auto
model = prepare_model_for_kbit_training(model,use_gradient_checkpointing=False)
model = get_peft_model(model, lora_config)
```
```auto
def compute_metrics(eval_preds):
metric = evaluate.load("glue", "mrpc")
logits, labels = eval_preds
predictions = np.argmax(logits, axis=-1)
return metric.compute(predictions=predictions, references=labels)
```
```auto
training_args = TrainingArguments("test-trainer",
report_to = 'wandb',
evaluation_strategy="epoch",
disable_tqdm=False,
per_device_train_batch_size=4,
per_device_eval_batch_size=4,
gradient_accumulation_steps=16,
save_steps=10,
logging_steps=10,
max_grad_norm=0.3,
num_train_epochs=3,
warmup_ratio=0.03,
)
trainer = Trainer(
model,
training_args,
train_dataset=tokenized_datasets["train"],
eval_dataset=tokenized_datasets["validation"],
data_collator=data_collator,
tokenizer=tokenizer,
compute_metrics=compute_metrics,
)
```
---
**Author:**  [@bhargob11](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbhargob11)%5C
**Post date:** [August 15, 2024, 11:31am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrainer-shows-no-log-for-validation-loss-when-using-peft%2F82298%2F2 "2024-08-15T11:31:24Z")
I have the same issue. Do you now know why?
---
**Author:**  [@pooya-mohammadi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpooya-mohammadi)%5C
**Post date:** [September 11, 2024, 4:35pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrainer-shows-no-log-for-validation-loss-when-using-peft%2F82298%2F3 "2024-09-11T16:35:37Z")
I have the same issue could anyone solve this problem yet?