Add REX LR Scheduler (#2380)

* Update trainer_builder.py * Update base.py * Update __init__.py * Update base.py * Update base.py * Update config.qmd * Update base.py * Update base.py * Update base.py * Update base.py * Update base.py * Update base.py * Update base.py * lint * lint * lint * lint * lint * lint * Update base.py * Update base.py * lint * Update base.py * Update base.py * Move RexLR to `schedulers.py` * Remove RexLR from `base.py` * Fix tooltip formatting * lint * Create test_schedulers.py * Use a default optimizer in test * lint * lint * Add `warmup_steps` and `cosine_min_lr_ratio` to test * lint
2025-03-05 10:26:11 -05:00
parent d4de93a7bb
commit 0134093acc
6 changed files with 160 additions and 3 deletions
--- a/tests/e2e/test_schedulers.py
+++ b/tests/e2e/test_schedulers.py
@@ -0,0 +1,71 @@
+"""
+E2E tests for custom schedulers using Llama
+"""
+
+import logging
+import os
+import unittest
+
+from axolotl.cli.args import TrainerCliArgs
+from axolotl.common.datasets import load_datasets
+from axolotl.train import train
+from axolotl.utils.config import normalize_config, validate_config
+from axolotl.utils.dict import DictDefault
+
+from .utils import check_model_output_exists, with_temp_dir
+
+LOG = logging.getLogger("axolotl.tests.e2e")
+os.environ["WANDB_DISABLED"] = "true"
+
+
+class TestCustomSchedulers(unittest.TestCase):
+    """
+    Test case for Llama models using LoRA
+    """
+
+    @with_temp_dir
+    def test_rex_scheduler(self, temp_dir):
+        # pylint: disable=duplicate-code
+        cfg = DictDefault(
+            {
+                "base_model": "JackFram/llama-68m",
+                "tokenizer_type": "LlamaTokenizer",
+                "sequence_len": 1024,
+                "load_in_8bit": True,
+                "adapter": "lora",
+                "lora_r": 8,
+                "lora_alpha": 16,
+                "lora_dropout": 0.05,
+                "lora_target_linear": True,
+                "val_set_size": 0.1,
+                "special_tokens": {
+                    "unk_token": "<unk>",
+                    "bos_token": "<s>",
+                    "eos_token": "</s>",
+                },
+                "datasets": [
+                    {
+                        "path": "mhenrichsen/alpaca_2k_test",
+                        "type": "alpaca",
+                    },
+                ],
+                "num_epochs": 1,
+                "micro_batch_size": 8,
+                "gradient_accumulation_steps": 1,
+                "output_dir": temp_dir,
+                "learning_rate": 0.00001,
+                "optimizer": "adamw_hf",
+                "max_steps": 20,
+                "lr_scheduler": "rex",
+                "warmup_steps": 5,
+                "cosine_min_lr_ratio": 0.05,
+            }
+        )
+
+        cfg = validate_config(cfg)
+        normalize_config(cfg)
+        cli_args = TrainerCliArgs()
+        dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args)
+
+        train(cfg=cfg, dataset_meta=dataset_meta)
+        check_model_output_exists(temp_dir, cfg)