Update tokenizer parameter in sfttrainer across multiple examples (#2664)

* REFAC Update tokenizer parameter to processing_class in SFTTrainer instances across multiple examples

* REFAC Replace tokenizer parameter with processing_class in Trainer instances across documentation and examples

* Refactor tokenizer parameter to processing_class in various examples

- Updated the Trainer initialization in corda_finetuning.py to use processing_class instead of tokenizer.
- Changed the execution_count to null in image_classification_peft_lora.ipynb.
- Modified the tokenizer parameter to processing_class in image_classification_peft_lora.ipynb.
- Adjusted the tokenizer parameter to processing_class in peft_bnb_whisper_large_v2_training.ipynb.
- Updated the README.md in lorafa_finetune to reflect the change from tokenizer to processing_class in Trainer initialization.

* REFAC Update tokenizer parameter to processing_class in Seq2SeqTrainer instantiation

* REFAC Replace tokenizer parameter with processing_class in README and notebook examples

Author: gapsong

docs/source/accelerate/deepspeed.md

@@ -134,7 +134,7 @@ The first thing to know is that the script uses DeepSpeed for distributed traini
 # trainer
 trainer = SFTTrainer(
     model=model,
-    tokenizer=tokenizer,
+    processing_class=tokenizer,
     args=training_args,
     train_dataset=train_dataset,
     eval_dataset=eval_dataset,

docs/source/accelerate/fsdp.md

@@ -114,7 +114,7 @@ The first thing to know is that the script uses FSDP for distributed training as
 # trainer
 trainer = SFTTrainer(
     model=model,
-    tokenizer=tokenizer,
+    processing_class=tokenizer,
     args=training_args,
     train_dataset=train_dataset,
     eval_dataset=eval_dataset,

docs/source/conceptual_guides/oft.md

@@ -123,7 +123,7 @@ trainer = SFTTrainer(
     model=model,
     train_dataset=ds['train'],
     peft_config=peft_config,
-    tokenizer=tokenizer,
+    processing_class=tokenizer,
     args=training_arguments,
     data_collator=collator,
 )

docs/source/quicktour.md

@@ -90,7 +90,7 @@ trainer = Trainer(
     args=training_args,
     train_dataset=tokenized_datasets["train"],
     eval_dataset=tokenized_datasets["test"],
-    tokenizer=tokenizer,
+    processing_class=tokenizer,
     data_collator=data_collator,
     compute_metrics=compute_metrics,
 )

docs/source/task_guides/lora_based_methods.md

@@ -281,7 +281,7 @@ trainer = Trainer(
     args,
     train_dataset=train_ds,
     eval_dataset=val_ds,
-    tokenizer=image_processor,
+    processing_class=image_processor,
     data_collator=collate_fn,
 )
 trainer.train()

examples/bone_finetuning/README.md

@@ -33,7 +33,7 @@ trainer = SFTTrainer(
     model=peft_model,
     args=training_args,
     train_dataset=dataset,
-    tokenizer=tokenizer,
+    processing_class=tokenizer,
 )
 trainer.train()
 peft_model.save_pretrained("bone-llama-2-7b")

examples/bone_finetuning/bone_finetuning.py

@@ -90,7 +90,7 @@ class ScriptArguments(SFTConfig):
     model=peft_model,
     args=script_args,
     train_dataset=dataset,
-    tokenizer=tokenizer,
+    processing_class=tokenizer,
 )
 trainer.train()
 trainer.save_state()

examples/conditional_generation/peft_prompt_tuning_seq2seq_with_generate.ipynb

@@ -447,7 +447,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "6b3a4090",
    "metadata": {
     "ExecuteTime": {
@@ -567,7 +567,7 @@
     ")\n",
     "trainer = Seq2SeqTrainer(\n",
     "    model=model,\n",
-    "    tokenizer=tokenizer,\n",
+    "    processing_class=tokenizer,\n",
     "    args=training_args,\n",
     "    train_dataset=train_dataset,\n",
     "    eval_dataset=eval_dataset,\n",

examples/corda_finetuning/README.md

@@ -114,7 +114,7 @@ trainer = SFTTrainer(
     model=peft_model,
     args=training_args,
     train_dataset=dataset,
-    tokenizer=tokenizer,
+    processing_class=tokenizer,
 )
 trainer.train()
 peft_model.save_pretrained("corda-llama-2-7b")

examples/corda_finetuning/corda_finetuning.py

@@ -266,7 +266,7 @@ def train():
         "train_dataset": train_dataset,
         "data_collator": data_collator,
     }
-    trainer = Trainer(model=model, tokenizer=tokenizer, args=script_args, **data_module)
+    trainer = Trainer(model=model, processing_class=tokenizer, args=script_args, **data_module)
     trainer.train()
     trainer.save_state()
     model.save_pretrained(os.path.join(script_args.output_dir, "ft"))