Update README.md

README.md

@@ -27,8 +27,6 @@ tags:
 
 ## Training Details
 
-**Cutome training codes**
-
 ### Training Hyperparameters
 `attn_implementation`: flash_attention_2 \
 `bf16`: True \
@@ -39,10 +37,70 @@ tags:
 `torch_dtype`: bfloat16 \
 `num_train_epochs`: 1 \
 `max_seq_length`: 2048 \
-`warmup_ratio`: 0.1 \
+`warmup_ratio`: 0.1
 
 ### Results
 
 `init_train_loss`: 1.421 \
 `final_train_loss`: 1.192 \
 `eval_loss`: 1.2003
+
+### Training script
+
+```python
+import multiprocessing
+
+from datasets import load_dataset
+from tqdm.rich import tqdm
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from trl import (
+    ModelConfig,
+    SFTTrainer,
+    get_peft_config,
+    get_quantization_config,
+    get_kbit_device_map,
+    SFTConfig,
+    ScriptArguments
+)
+from trl.commands.cli_utils import TrlParser
+
+tqdm.pandas()
+
+if __name__ == "__main__":
+    parser = TrlParser((ScriptArguments, SFTConfig, ModelConfig))
+    args, training_args, model_config = parser.parse_args_and_config()
+
+    quantization_config = get_quantization_config(model_config)
+    model_kwargs = dict(
+        revision=model_config.model_revision,
+        trust_remote_code=model_config.trust_remote_code,
+        attn_implementation=model_config.attn_implementation,
+        torch_dtype=model_config.torch_dtype,
+        use_cache=False if training_args.gradient_checkpointing else True,
+        device_map=get_kbit_device_map() if quantization_config is not None else None,
+        quantization_config=quantization_config,
+    )
+
+    model = AutoModelForCausalLM.from_pretrained(model_config.model_name_or_path,
+                                                 **model_kwargs)
+    tokenizer = AutoTokenizer.from_pretrained(
+        model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code, use_fast=True
+    )
+    tokenizer.pad_token = tokenizer.eos_token
+
+    train_dataset = load_dataset(args.dataset_name,
+                                 split=args.dataset_train_split,
+                                 num_proc=multiprocessing.cpu_count())
+
+    trainer = SFTTrainer(
+        model=model,
+        args=training_args,
+        train_dataset=train_dataset,
+        processing_class=tokenizer,
+        peft_config=get_peft_config(model_config),
+    )
+
+    trainer.train()
+
+    trainer.save_model(training_args.output_dir)
+```