diff --git a/examples/causal_language_modeling/peft_prefix_tuning_clm.ipynb b/examples/causal_language_modeling/peft_prefix_tuning_clm.ipynb
index eb25c0c20a..cf36d219e2 100644
--- a/examples/causal_language_modeling/peft_prefix_tuning_clm.ipynb
+++ b/examples/causal_language_modeling/peft_prefix_tuning_clm.ipynb
@@ -1180,9 +1180,9 @@
     "            tokenizer.batch_decode(torch.argmax(outputs.logits, -1).detach().cpu().numpy(), skip_special_tokens=True)\n",
     "        )\n",
     "\n",
-    "    eval_epoch_loss = eval_loss / len(train_dataloader)\n",
+    "    eval_epoch_loss = eval_loss / len(eval_dataloader)\n",
     "    eval_ppl = torch.exp(eval_epoch_loss)\n",
-    "    train_epoch_loss = total_loss / len(eval_dataloader)\n",
+    "    train_epoch_loss = total_loss / len(train_dataloader)\n",
     "    train_ppl = torch.exp(train_epoch_loss)\n",
     "    print(f\"{epoch=}: {train_ppl=} {train_epoch_loss=} {eval_ppl=} {eval_epoch_loss=}\")"
    ]
@@ -1345,7 +1345,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5 (v3.10.5:f377153967, Jun  6 2022, 12:36:10) [Clang 13.0.0 (clang-1300.0.29.30)]"
+   "version": "3.10.5"
   },
   "vscode": {
    "interpreter": {
diff --git a/examples/causal_language_modeling/peft_prompt_tuning_clm.ipynb b/examples/causal_language_modeling/peft_prompt_tuning_clm.ipynb
index e5ba39b9e4..e289206110 100644
--- a/examples/causal_language_modeling/peft_prompt_tuning_clm.ipynb
+++ b/examples/causal_language_modeling/peft_prompt_tuning_clm.ipynb
@@ -1022,9 +1022,9 @@
     "            tokenizer.batch_decode(torch.argmax(outputs.logits, -1).detach().cpu().numpy(), skip_special_tokens=True)\n",
     "        )\n",
     "\n",
-    "    eval_epoch_loss = eval_loss / len(train_dataloader)\n",
+    "    eval_epoch_loss = eval_loss / len(eval_dataloader)\n",
     "    eval_ppl = torch.exp(eval_epoch_loss)\n",
-    "    train_epoch_loss = total_loss / len(eval_dataloader)\n",
+    "    train_epoch_loss = total_loss / len(train_dataloader)\n",
     "    train_ppl = torch.exp(train_epoch_loss)\n",
     "    print(f\"{epoch=}: {train_ppl=} {train_epoch_loss=} {eval_ppl=} {eval_epoch_loss=}\")"
    ]
@@ -1185,7 +1185,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5 (v3.10.5:f377153967, Jun  6 2022, 12:36:10) [Clang 13.0.0 (clang-1300.0.29.30)]"
+   "version": "3.10.5"
   },
   "vscode": {
    "interpreter": {
diff --git a/examples/conditional_generation/peft_lora_seq2seq.ipynb b/examples/conditional_generation/peft_lora_seq2seq.ipynb
index f22d3c66b1..6cbd4f1cb9 100644
--- a/examples/conditional_generation/peft_lora_seq2seq.ipynb
+++ b/examples/conditional_generation/peft_lora_seq2seq.ipynb
@@ -324,9 +324,9 @@
     "            tokenizer.batch_decode(torch.argmax(outputs.logits, -1).detach().cpu().numpy(), skip_special_tokens=True)\n",
     "        )\n",
     "\n",
-    "    eval_epoch_loss = eval_loss / len(train_dataloader)\n",
+    "    eval_epoch_loss = eval_loss / len(eval_dataloader)\n",
     "    eval_ppl = torch.exp(eval_epoch_loss)\n",
-    "    train_epoch_loss = total_loss / len(eval_dataloader)\n",
+    "    train_epoch_loss = total_loss / len(train_dataloader)\n",
     "    train_ppl = torch.exp(train_epoch_loss)\n",
     "    print(f\"{epoch=}: {train_ppl=} {train_epoch_loss=} {eval_ppl=} {eval_epoch_loss=}\")"
    ]
@@ -473,7 +473,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.5"
   },
   "vscode": {
    "interpreter": {
diff --git a/examples/conditional_generation/peft_lora_seq2seq_accelerate_ds_zero3_offload.py b/examples/conditional_generation/peft_lora_seq2seq_accelerate_ds_zero3_offload.py
index cef97734c2..a2d0d201da 100644
--- a/examples/conditional_generation/peft_lora_seq2seq_accelerate_ds_zero3_offload.py
+++ b/examples/conditional_generation/peft_lora_seq2seq_accelerate_ds_zero3_offload.py
@@ -217,7 +217,7 @@ def collate_fn(examples):
                 tracemalloc.cpu_peaked + b2mb(tracemalloc.cpu_begin)
             )
         )
-        train_epoch_loss = total_loss / len(eval_dataloader)
+        train_epoch_loss = total_loss / len(train_dataloader)
         train_ppl = torch.exp(train_epoch_loss)
         accelerator.print(f"{epoch=}: {train_ppl=} {train_epoch_loss=}")
 
diff --git a/examples/conditional_generation/peft_lora_seq2seq_accelerate_fsdp.py b/examples/conditional_generation/peft_lora_seq2seq_accelerate_fsdp.py
index e00b1ff588..c011dbb959 100644
--- a/examples/conditional_generation/peft_lora_seq2seq_accelerate_fsdp.py
+++ b/examples/conditional_generation/peft_lora_seq2seq_accelerate_fsdp.py
@@ -108,9 +108,9 @@ def preprocess_function(examples):
             eval_loss += loss.detach().float()
             preds = accelerator.gather_for_metrics(torch.argmax(outputs.logits, -1)).detach().cpu().numpy()
             eval_preds.extend(tokenizer.batch_decode(preds, skip_special_tokens=True))
-        eval_epoch_loss = eval_loss / len(train_dataloader)
+        eval_epoch_loss = eval_loss / len(eval_dataloader)
         eval_ppl = torch.exp(eval_epoch_loss)
-        train_epoch_loss = total_loss / len(eval_dataloader)
+        train_epoch_loss = total_loss / len(train_dataloader)
         train_ppl = torch.exp(train_epoch_loss)
         accelerator.print(f"{epoch=}: {train_ppl=} {train_epoch_loss=} {eval_ppl=} {eval_epoch_loss=}")
 
diff --git a/examples/conditional_generation/peft_prefix_tuning_seq2seq.ipynb b/examples/conditional_generation/peft_prefix_tuning_seq2seq.ipynb
index dde8fff277..aa85f9a743 100644
--- a/examples/conditional_generation/peft_prefix_tuning_seq2seq.ipynb
+++ b/examples/conditional_generation/peft_prefix_tuning_seq2seq.ipynb
@@ -360,9 +360,9 @@
     "            tokenizer.batch_decode(torch.argmax(outputs.logits, -1).detach().cpu().numpy(), skip_special_tokens=True)\n",
     "        )\n",
     "\n",
-    "    eval_epoch_loss = eval_loss / len(train_dataloader)\n",
+    "    eval_epoch_loss = eval_loss / len(eval_dataloader)\n",
     "    eval_ppl = torch.exp(eval_epoch_loss)\n",
-    "    train_epoch_loss = total_loss / len(eval_dataloader)\n",
+    "    train_epoch_loss = total_loss / len(train_dataloader)\n",
     "    train_ppl = torch.exp(train_epoch_loss)\n",
     "    print(f\"{epoch=}: {train_ppl=} {train_epoch_loss=} {eval_ppl=} {eval_epoch_loss=}\")"
    ]
@@ -503,7 +503,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5 (v3.10.5:f377153967, Jun  6 2022, 12:36:10) [Clang 13.0.0 (clang-1300.0.29.30)]"
+   "version": "3.10.5"
   },
   "vscode": {
    "interpreter": {