fixes to accelerator so that iterable pretraining datasets work (#1759)

* fixes to accelerator so that iterable pretraining datasets work

* fix the pretraining test params

* split batches, not dispatch batches needs to be set

* update c4 datasets

* set epochs in pretrain config test

* need to set both split_batches and dispatch_batches to false for pretraining

* fix bool val in comment

tests/e2e/test_llama_pretrain.py

@@ -0,0 +1,67 @@
+"""
+E2E tests for llama pretrain
+"""
+
+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 TestPretrainLlama(unittest.TestCase):
+    """
+    Test case for Llama models w pretraining
+    """
+
+    @with_temp_dir
+    def test_pretrain_w_sample_packing(self, temp_dir):
+        # pylint: disable=duplicate-code
+        cfg = DictDefault(
+            {
+                "base_model": "JackFram/llama-68m",
+                "tokenizer_type": "LlamaTokenizer",
+                "flash_attention": True,
+                "sequence_len": 1024,
+                "sample_packing": True,
+                "special_tokens": {
+                    "unk_token": "<unk>",
+                    "bos_token": "<s>",
+                    "eos_token": "</s>",
+                },
+                "pretraining_dataset": [
+                    {
+                        "path": "allenai/c4",
+                        "name": "en",
+                        "type": "pretrain",
+                    }
+                ],
+                "max_steps": 5,
+                "num_epochs": 1,
+                "micro_batch_size": 1,
+                "gradient_accumulation_steps": 1,
+                "val_set_size": 0.0,
+                "output_dir": temp_dir,
+                "learning_rate": 0.00001,
+                "optimizer": "adamw_torch",
+                "lr_scheduler": "cosine",
+                "save_safetensors": True,
+                "bf16": "auto",
+            }
+        )
+        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) / "model.safetensors").exists()

tests/test_packed_pretraining.py

@@ -24,7 +24,7 @@ class TestPretrainingPacking(unittest.TestCase):
     def test_packing_stream_dataset(self):
         # pylint: disable=duplicate-code
         dataset = load_dataset(
-            "c4",
+            "allenai/c4",
             "en",
             streaming=True,
         )["train"]
@@ -33,7 +33,7 @@ class TestPretrainingPacking(unittest.TestCase):
             {
                 "pretraining_dataset": [
                     {
-                        "path": "c4",
+                        "path": "allenai/c4",
                         "name": "en",
                         "type": "pretrain",
                     }