WIP Add:adding smoke test dpo

tests/e2e/test_dpo_tiny_lama.py

@@ -0,0 +1,62 @@
+"""
+E2E tests for lora llama
+"""
+
+import logging
+import os
+import unittest
+from pathlib import Path
+
+from axolotl.cli import load_datasets
+from axolotl.common.cli import TrainerCliArgs
+from axolotl.train import train
+from axolotl.utils.config import normalize_config
+from axolotl.utils.dict import DictDefault
+
+from .utils import with_temp_dir
+
+LOG = logging.getLogger("axolotl.tests.e2e")
+os.environ["WANDB_DISABLED"] = "true"
+
+
+class TestLoraLlama(unittest.TestCase):
+    """
+    Test case for Llama models using LoRA
+    """
+
+    @with_temp_dir
+    def test_lora(self, temp_dir):
+        # pylint: disable=duplicate-code
+        cfg = DictDefault(
+            {
+                "base_model": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+                "tokenizer_type": "LlamaForCausalLM",
+                "sequence_len": 1024,
+                "load_in_4bit": True,
+                "adapter": "lora",
+                "lora_r": 32,
+                "lora_alpha": 16,
+                "lora_dropout": 0.05,
+                "lora_target_linear": True,
+                "val_set_size": 0.1,
+                "datasets": [
+                    {
+                        "path": "rgilla/ultrafeedback-binarized-preferences-cleaned",
+                        "type": "ultra_apply_chatml",
+                    },
+                ],
+                "max_steps": 20,
+                "micro_batch_size": 1,
+                "gradient_accumulation_steps": 1,
+                "output_dir": temp_dir,
+                "learning_rate": 0.00001,
+                "optimizer": "adamw_torch",
+                "lr_scheduler": "cosine",
+            }
+        )
+        normalize_config(cfg)
+        cli_args = TrainerCliArgs()
+        dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args)
+
+        train(cfg=cfg, cli_args=cli_args, dataset_meta=dataset_meta)
+        assert (Path(temp_dir) / "adapter_model.bin").exists()