multipack sampler support from openchat

Feat: Set push to hub as private by default

README.md

@@ -195,6 +195,10 @@ Have dataset(s) in one of the following format (JSONL recommended):
   ```json
   {"message_1": "...", "message_2": "..."}
   ```
+- `alpaca_w_system.load_open_orca`: support for open orca datasets with included system prompts, instruct
+  ```json
+  {"system_prompt": "...", "question": "...", "response": "..."}
+  ```
 - `context_qa`: in context question answering from an article
   ```json
   {"article": "...", "question": "...", "answer": "..."}
@@ -233,7 +237,7 @@ Have dataset(s) in one of the following format (JSONL recommended):
 #### How to add custom prompts
 
   1. Add your method to a file in [prompt_strategies](src/axolotl/prompt_strategies). Please see other files as example.
-  2. Use your custom file name as the dataset type.
+  2. Use your custom file name as the dataset type `<prompt_strategies_file>.load_<load_fn>`.
 
 Optionally, download some datasets, see [data/README.md](data/README.md)
 
@@ -251,10 +255,18 @@ See sample configs in [configs](configs) folder or [examples](examples) for quic
 
 - dataset
   ```yaml
+  sequence_len: 2048 # max token length for prompt
+
+  # huggingface repo
   datasets:
-    - path: vicgalle/alpaca-gpt4 # local or huggingface repo
+    - path: vicgalle/alpaca-gpt4
+      type: alpaca # format from earlier
+
+  # local
+  datasets:
+    - path: json
+      data_files: data.jsonl # or json
       type: alpaca # format from earlier
-  sequence_len: 2048 # max token length / prompt
   ```
 
 - loading
@@ -293,6 +305,8 @@ base_model_ignore_patterns:
 # if the base_model repo on hf hub doesn't include configuration .json files,
 # you can set that here, or leave this empty to default to base_model
 base_model_config: ./llama-7b-hf
+# you can specify to choose a specific model revision from huggingface hub
+model_revision:
 # Optional tokenizer configuration override in case you want to use a different tokenizer
 # than the one defined in the base model
 tokenizer_config:
@@ -324,10 +338,10 @@ tf32: true # require >=ampere
 
 # a list of one or more datasets to finetune the model with
 datasets:
-  # this can be either a hf dataset, or relative path
+  # hf dataset repo | "json" for local dataset, make sure to fill data_files
   - path: vicgalle/alpaca-gpt4
   # The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection]
-    type: alpaca # format OR format:prompt_style (chat/instruct)
+    type: alpaca # format | format:<prompt_style> (chat/instruct) | <prompt_strategies>.load_<load_fn>
     data_files: # path to source data files
     shards: # number of shards to split data into
 
@@ -336,6 +350,8 @@ datasets:
 dataset_prepared_path: data/last_run_prepared
 # push prepared dataset to hub
 push_dataset_to_hub: # repo path
+# push checkpoints to hub
+hub_model_id: # repo path
 # whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
 # required to be true when used in combination with `push_dataset_to_hub`
 hf_use_auth_token: # boolean
@@ -397,6 +413,9 @@ logging_steps:
 save_steps:
 eval_steps:
 
+# save model as safetensors (require safetensors package)
+save_safetensors:
+
 # whether to mask out or include the human's prompt from the training labels
 train_on_inputs: false
 # don't use this, leads to wonky training (according to someone on the internet)

docker/Dockerfile-base

@@ -97,4 +97,4 @@ RUN cd /workspace/builds/bitsandbytes && python3 setup.py install
 RUN git lfs install --skip-repo
 RUN pip3 install awscli && \
     # The base image ships with `pydantic==1.8.2` which is not working
-    pip3 install -U --no-cache-dir pydantic
+    pip3 install -U --no-cache-dir pydantic==1.10.10

requirements.txt

@@ -1,7 +1,6 @@
 peft @ git+https://github.com/huggingface/peft.git
 transformers @ git+https://github.com/huggingface/transformers.git
 bitsandbytes>=0.39.0
-accelerate
 addict
 fire
 PyYAML==6.0
@@ -18,3 +17,4 @@ evaluate==0.4.0
 rouge-score==0.1.2
 scipy
 scikit-learn==1.2.2
+numba

src/axolotl/prompt_strategies/alpaca_w_system.py

@@ -75,10 +75,46 @@ class SystemDataPrompter(AlpacaPrompter):
         yield res
 
 
+class OpenOrcaPromptTokenizingStrategy(InstructionWSystemPromptTokenizingStrategy):
+    """
+    Tokenizing strategy for OpenOrca datasets
+    """
+
+    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str, str]:
+        return (
+            prompt["question"],
+            "",
+            prompt["response"],
+            prompt["system_prompt"],
+        )
+
+
 def load(tokenizer, cfg):
+    return load_chat(tokenizer, cfg)
+
+
+def load_instruct(tokenizer, cfg):
+    return InstructionWSystemPromptTokenizingStrategy(
+        SystemDataPrompter(PromptStyle.INSTRUCT.value),
+        tokenizer,
+        cfg.train_on_inputs,
+        cfg.sequence_len,
+    )
+
+
+def load_chat(tokenizer, cfg):
     return InstructionWSystemPromptTokenizingStrategy(
         SystemDataPrompter(PromptStyle.CHAT.value),
         tokenizer,
         cfg.train_on_inputs,
         cfg.sequence_len,
     )
+
+
+def load_open_orca(tokenizer, cfg):
+    return OpenOrcaPromptTokenizingStrategy(
+        SystemDataPrompter(PromptStyle.INSTRUCT.value),
+        tokenizer,
+        cfg.train_on_inputs,
+        cfg.sequence_len,
+    )

src/axolotl/prompt_tokenizers.py

@@ -440,7 +440,7 @@ def parse_tokenized_to_result(
     result: Dict[str, List[int]],
     current_len: int,
     res: Dict[str, List[int]],
-    labels: list[int],
+    labels: List[int],
     pad_token_id: Union[int, None] = None,
 ) -> Tuple[Dict[str, List[int]], int]:
     """

src/axolotl/utils/data.py

@@ -102,13 +102,26 @@ def load_tokenized_prepared_datasets(
                 pass
 
             # prefer local dataset, even if hub exists
-            if Path(d.path).exists():
+            local_path = Path(d.path)
-                ds = load_dataset(
+            if local_path.exists():
-                    "json",
+                if local_path.is_dir():
-                    data_files=d.path,
+                    ds = load_dataset(
-                    streaming=False,
+                        d.path,
-                    split=None,
+                        data_files=d.data_files,
-                )
+                        streaming=False,
+                        split=None,
+                    )
+                elif local_path.is_file():
+                    ds = load_dataset(
+                        "json",
+                        data_files=d.path,
+                        streaming=False,
+                        split=None,
+                    )
+                else:
+                    raise ValueError(
+                        "unhandled dataset load: local path exists, but is neither a directory or a file"
+                    )
             elif ds_from_hub:
                 if d.data_files:
                     ds = load_dataset(

src/axolotl/utils/models.py

@@ -154,6 +154,8 @@ def load_model(
         )
 
     model_kwargs = {}
+    if cfg.model_revision:
+        model_kwargs["revision"] = cfg.model_revision
     if cfg.adapter == "qlora" and cfg.load_in_4bit:
         model_kwargs["quantization_config"] = BitsAndBytesConfig(
             load_in_4bit=True,
@@ -202,7 +204,7 @@ def load_model(
                 else True,
             )
             load_in_8bit = False
-        elif cfg.is_llama_derived_model:
+        elif cfg.is_llama_derived_model and not cfg.trust_remote_code:
             from transformers import LlamaForCausalLM
 
             config = LlamaConfig.from_pretrained(base_model_config)
@@ -241,7 +243,7 @@ def load_model(
         #         device=cfg.device,
         #     )
         #     model.train() # sets to train instead of eval mode
-        elif model_type:
+        elif model_type and not cfg.trust_remote_code:
             model = getattr(transformers, model_type).from_pretrained(
                 base_model,
                 load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,

src/axolotl/utils/sampler.py

@@ -0,0 +1,173 @@
+# pylint: skip-file
+
+from typing import Any, List, Optional
+
+import numba
+import numpy as np
+import torch.distributed as dist
+from torch.utils.data import Sampler
+
+
+@numba.njit
+def ffd_check(a: np.ndarray, c: int, n: int):
+    # First-fit-decreasing bin packing
+    # Check if a[] could fit in n bins with capacity c
+    # https://en.wikipedia.org/wiki/First-fit-decreasing_bin_packing
+
+    a = np.sort(a)[::-1]
+    bins = np.full((n,), c, dtype=a.dtype)
+    for size in a:
+        not_found = True
+        for idx in range(n):
+            if bins[idx] >= size:
+                bins[idx] -= size
+                not_found = False
+                break
+
+        if not_found:
+            return False
+
+    return True
+
+
+@numba.njit
+def ffd_with_result(a: np.ndarray, c: int, start_index: int):
+    # First-fit-decreasing bin packing (with result return)
+
+    indices = np.argsort(a)[::-1]
+    a = a[indices]
+
+    bins: List[int] = []
+    bins_result: List[Any] = []
+    for a_id, size in enumerate(a):
+        add_new = True
+        for idx in range(len(bins)):
+            if bins[idx] >= size:
+                bins[idx] -= size
+                bins_result[idx].append(indices[a_id] + start_index)
+                add_new = False
+                break
+
+        if add_new:
+            bins.append(c - size)
+            bins_result.append([indices[a_id] + start_index])
+
+    return bins_result
+
+
+@numba.njit
+def allocate(
+    lengths: np.ndarray, lengths_cumsum: np.ndarray, rank: int, c: int, n: int
+):
+    # Dynamic batch allocator, similar to Multifit
+    # https://en.wikipedia.org/wiki/Multifit_algorithm
+    # ~99.5% efficiency on OpenChat training set (12 * 2048 ctx len)
+
+    s = 0
+    start_index = 0
+    result = []
+
+    while True:
+        # binary search [l, r)
+        left = 1
+        right = 1 + np.searchsorted(lengths_cumsum[start_index:], s + c * n, "right")
+
+        while right - left > 1:
+            m = (left + right) // 2
+            if ffd_check(lengths[start_index : start_index + m], c, n):
+                left = m
+            else:
+                right = m
+
+        # use length l
+        batch = ffd_with_result(
+            lengths[start_index : start_index + left], c, start_index
+        )
+        assert len(batch) <= n
+        if len(batch) < n:
+            break
+
+        start_index += left
+        s = lengths_cumsum[start_index - 1]
+
+        # add local rank
+        result.append(batch[rank])
+
+    return result, s, len(result) * c * n
+
+
+class MultipackDistributedBatchSampler(Sampler):
+    """Unpadded length sampling using Multipack.
+    Approximate (at most ~1.22x) the optimal solution of the identical-machines scheduling problem, which is NP-hard.
+    """
+
+    def __init__(
+        self,
+        batch_max_length: int,
+        lengths: List[int],
+        num_replicas: Optional[int] = None,
+        rank: Optional[int] = None,
+        seed: int = 0,
+    ):
+        # Get rank
+        if num_replicas is None:
+            if not dist.is_available():
+                raise RuntimeError("Requires distributed package to be available")
+            num_replicas = dist.get_world_size()
+        if rank is None:
+            if not dist.is_available():
+                raise RuntimeError("Requires distributed package to be available")
+            rank = dist.get_rank()
+
+        self.num_replicas = num_replicas
+        self.rank = rank
+        self.seed = seed
+
+        self.batch_max_length = batch_max_length
+        self.lengths = lengths
+        assert isinstance(self.lengths, np.ndarray)
+
+        self.epoch = 0
+
+        # statistics
+        self.eff_total_used = 0
+        self.eff_total_slots = 0
+
+    def set_epoch(self, epoch: int):
+        self.epoch = epoch
+
+    def generate_batches(self, set_stats=False):
+        indices = np.random.default_rng(seed=self.seed + self.epoch).permutation(
+            len(self.lengths)
+        )
+
+        lengths = self.lengths[indices]
+        lengths_cumsum = np.cumsum(lengths)
+
+        batches, total_used, total_slots = allocate(
+            lengths=lengths,
+            lengths_cumsum=lengths_cumsum,
+            rank=self.rank,
+            c=self.batch_max_length,
+            n=self.num_replicas,
+        )
+
+        batches = [indices[batch] for batch in batches]
+
+        # statistics
+        if set_stats:
+            self.eff_total_used += total_used
+            self.eff_total_slots += total_slots
+
+        return batches
+
+    def __iter__(self):
+        batches = self.generate_batches(set_stats=True)
+        return iter(batches)
+
+    def num_batches(self):
+        batches = self.generate_batches()
+        return len(batches)
+
+    def efficiency(self):
+        return self.eff_total_used / self.eff_total_slots

src/axolotl/utils/schedulers.py

@@ -1,6 +1,9 @@
 """Module for custom LRScheduler class"""
+import math
+from functools import partial
 
-from torch.optim.lr_scheduler import LRScheduler
+from torch.optim import Optimizer
+from torch.optim.lr_scheduler import LambdaLR, LRScheduler
 
 
 class InterpolatingLogScheduler(LRScheduler):
@@ -42,3 +45,58 @@ class InterpolatingLogScheduler(LRScheduler):
             lrs = [self.max_lr for base_lr in self.base_lrs]
 
         return lrs
+
+
+def _get_cosine_schedule_with_quadratic_warmup_lr_lambda(
+    current_step: int,
+    *,
+    num_warmup_steps: int,
+    num_training_steps: int,
+    num_cycles: float
+):
+    if current_step < num_warmup_steps:
+        return (float(current_step) / float(max(1, num_warmup_steps))) ** 2
+    progress = float(current_step - num_warmup_steps) / float(
+        max(1, num_training_steps - num_warmup_steps)
+    )
+    return max(
+        0.0, 0.5 * (1.0 + math.cos(math.pi * float(num_cycles) * 2.0 * progress))
+    )
+
+
+def get_cosine_schedule_with_quadratic_warmup(
+    optimizer: Optimizer,
+    num_warmup_steps: int,
+    num_training_steps: int,
+    num_cycles: float = 0.5,
+    last_epoch: int = -1,
+):
+    """
+    Create a schedule with a learning rate that decreases following the values of the cosine function between the
+    initial lr set in the optimizer to 0, after a warmup period during which it increases linearly between 0 and the
+    initial lr set in the optimizer.
+
+    Args:
+        optimizer ([`~torch.optim.Optimizer`]):
+            The optimizer for which to schedule the learning rate.
+        num_warmup_steps (`int`):
+            The number of steps for the warmup phase.
+        num_training_steps (`int`):
+            The total number of training steps.
+        num_cycles (`float`, *optional*, defaults to 0.5):
+            The number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0
+            following a half-cosine).
+        last_epoch (`int`, *optional*, defaults to -1):
+            The index of the last epoch when resuming training.
+
+    Return:
+        `torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
+    """
+
+    lr_lambda = partial(
+        _get_cosine_schedule_with_quadratic_warmup_lr_lambda,
+        num_warmup_steps=num_warmup_steps,
+        num_training_steps=num_training_steps,
+        num_cycles=num_cycles,
+    )
+    return LambdaLR(optimizer, lr_lambda, last_epoch)

src/axolotl/utils/trainer.py

@@ -5,25 +5,185 @@ import logging
 import math
 import os
 import sys
+from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Optional
 
 import bitsandbytes as bnb
+import numpy as np
 import torch.cuda
 import transformers
 from torch import nn
 from torch.optim.lr_scheduler import OneCycleLR
-from transformers import EarlyStoppingCallback, Trainer
+from torch.utils.data import Dataset
+from transformers import EarlyStoppingCallback, Trainer, TrainingArguments
 from transformers.trainer_pt_utils import get_parameter_names
 
 from axolotl.utils.callbacks import (
     SaveBetterTransformerModelCallback,
     SavePeftModelCallback,
 )
-from axolotl.utils.schedulers import InterpolatingLogScheduler
+from axolotl.utils.sampler import MultipackDistributedBatchSampler
+from axolotl.utils.schedulers import (
+    InterpolatingLogScheduler,
+    get_cosine_schedule_with_quadratic_warmup,
+)
+
+IGNORE_LABEL_ID = -100
 
 
-class OneCycleLRSchedulerTrainer(Trainer):
+def _find_multiple(val1, val2):
+    return (-(val1 // -val2)) * val2
+
+
+def batch_to_tensor(batch, pad_id=0, dtype=torch.long, loss_dtype=torch.bfloat16):
+    # Pad an unused item to reach multiple of 64, for faster GEMM
+    pad_cur_len = sum(list(batch["length"]))
+    pad_len = _find_multiple(pad_cur_len, 64) - pad_cur_len
+
+    if pad_len > 0:
+        assert pad_len < 64
+
+        batch["input_ids"].append([pad_id] * pad_len)
+        batch["labels"].append([pad_id] * pad_len)
+        batch["attention_mask"].append([0] * pad_len)
+        batch["length"].append(pad_len)
+
+    # seqlen
+    batch_lengths = torch.tensor(list(batch["length"]), dtype=torch.int32, device="cpu")
+
+    max_seqlen = torch.max(batch_lengths)
+    cu_seqlens = torch.nn.functional.pad(
+        batch_lengths.cumsum(-1, dtype=torch.int32), (1, 0)
+    )
+
+    # nz elements
+    nz_num = cu_seqlens[-1]
+    nz_input_ids = torch.zeros((nz_num,), dtype=dtype, pin_memory=True, device="cpu")
+    nz_position_ids = torch.zeros((nz_num,), dtype=dtype, pin_memory=True, device="cpu")
+    nz_shifted_label_ids = torch.zeros(
+        (nz_num,), dtype=dtype, pin_memory=True, device="cpu"
+    )
+    nz_shifted_loss_weights = torch.zeros(
+        (nz_num,), dtype=loss_dtype, pin_memory=True, device="cpu"
+    )
+
+    index = 0
+    for token_list, length, labels_list in zip(
+        batch["input_ids"], batch["length"], batch["labels"]
+    ):
+        tokens = torch.tensor(token_list, dtype=dtype, device="cpu")
+        position_ids = torch.arange(length, dtype=dtype, device="cpu")
+
+        # Input IDs & shifted labels
+        # shifted_label_ids = torch.where(masks, tokens, IGNORE_LABEL_ID)
+        shifted_label_ids = labels_list
+        shifted_label_ids = torch.nn.functional.pad(
+            shifted_label_ids[1:], (0, 1), "constant", IGNORE_LABEL_ID
+        )
+
+        nz_input_ids[index : index + length] = tokens
+        nz_position_ids[index : index + length] = position_ids
+        nz_shifted_label_ids[index : index + length] = shifted_label_ids
+
+        # Loss weights
+        mask_count = sum(1 for label in labels_list[1:] if label != IGNORE_LABEL_ID)
+        loss_weight = (
+            1 / mask_count if mask_count > 0 else 0
+        )  # Avoid division by zero for paddings
+
+        nz_shifted_loss_weights[index : index + length] = loss_weight
+
+        index += length
+
+    # inputs
+    return {
+        "max_seqlen": max_seqlen,
+        "cu_seqlens": cu_seqlens,
+        "nz_input_ids": nz_input_ids,
+        "nz_position_ids": nz_position_ids,
+        "nz_shifted_label_ids": nz_shifted_label_ids,
+        "nz_shifted_loss_weights": nz_shifted_loss_weights,
+    }
+
+
+@dataclass
+class AxolotlTrainingArguments(TrainingArguments):
+    """
+    Extend the base TrainingArguments for axolotl helpers
+    """
+
+    lr_quadratic_warmup: bool = field(
+        default=False,
+        metadata={"help": "Use quadratic warmup for cosine scheduling."},
+    )
+    sample_packing: bool = field(
+        default=True,
+        metadata={"help": "Use sample packing for efficient training."},
+    )
+    max_seq_length: int = field(
+        default=2048,
+        metadata={"help": "The maximum sequence length the model can handle"},
+    )
+
+
+class AxolotlTrainer(Trainer):
+    """
+    Extend the base Trainer for axolotl helpers
+    """
+
+    args = None  # type: AxolotlTrainingArguments
+
+    def create_scheduler(
+        self, num_training_steps: int, optimizer: torch.optim.Optimizer = None
+    ):
+        """
+        Setup the scheduler. The optimizer of the trainer must have been set up either before this method is called or
+        passed as an argument.
+
+        Args:
+            num_training_steps (int): The number of training steps to do.
+            optimizer (torch.optim.Optimizer): The training optimizer
+        """
+
+        # fmt: off
+        if self.lr_scheduler is None:  # type: ignore  # pylint: disable=access-member-before-definition
+            # fmt: on
+            if (
+                self.args.lr_scheduler_type == "cosine"
+                and self.args.lr_quadratic_warmup is True
+            ):
+                self.lr_scheduler = get_cosine_schedule_with_quadratic_warmup(  # pylint: disable=attribute-defined-outside-init
+                    optimizer,
+                    num_warmup_steps=self.args.get_warmup_steps(num_training_steps),
+                    num_training_steps=num_training_steps,
+                )
+            else:
+                return super().create_scheduler(num_training_steps, optimizer)
+        return self.lr_scheduler
+
+    def _get_train_sampler(self) -> Optional[torch.utils.data.Sampler]:
+        lengths = np.array([len(sample["input_ids"]) for sample in self.train_dataset])
+        return MultipackDistributedBatchSampler(
+            batch_max_length=self.args.per_device_train_batch_size
+            * self.args.max_seq_length,
+            lengths=lengths,
+            seed=self.args.seed,
+        )
+
+    def _get_eval_sampler(
+        self, eval_dataset: Dataset
+    ) -> Optional[torch.utils.data.Sampler]:
+        lengths = np.array([len(sample["input_ids"]) for sample in eval_dataset])
+        return MultipackDistributedBatchSampler(
+            batch_max_length=self.args.per_device_eval_batch_size
+            * self.args.max_seq_length,
+            lengths=lengths,
+            seed=self.args.seed,
+        )
+
+
+class OneCycleLRSchedulerTrainer(AxolotlTrainer):
     """
     Trainer subclass that uses the OneCycleLR scheduler
     """
@@ -103,6 +263,9 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
         if cfg.fsdp_config:
             training_arguments_kwargs["fsdp_config"] = dict(cfg.fsdp_config)
 
+    if cfg.lr_quadratic_warmup is not None:
+        training_arguments_kwargs["lr_quadratic_warmup"] = cfg.lr_quadratic_warmup
+
     # deepspeed
     if (
         os.environ.get("ACCELERATE_USE_DEEPSPEED") == "true"
@@ -124,11 +287,16 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
     if cfg.max_grad_norm:
         training_arguments_kwargs["max_grad_norm"] = cfg.max_grad_norm
 
-    if cfg.push_to_hub_model_id:
+    if cfg.hub_model_id:
-        training_arguments_kwargs["push_to_hub_model_id"] = cfg.push_to_hub_model_id
+        training_arguments_kwargs["hub_model_id"] = cfg.hub_model_id
         training_arguments_kwargs["push_to_hub"] = True
+        training_arguments_kwargs["hub_private_repo"] = True
 
-    training_args = transformers.TrainingArguments(
+    if cfg.save_safetensors:
+        training_arguments_kwargs["save_safetensors"] = cfg.save_safetensors
+
+    training_args = AxolotlTrainingArguments(  # pylint: disable=unexpected-keyword-arg
+        max_steps=total_num_steps * cfg.num_epochs,
         per_device_train_batch_size=cfg.micro_batch_size,
         per_device_eval_batch_size=cfg.eval_batch_size
         if cfg.eval_batch_size is not None
@@ -278,7 +446,7 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
     trainer_cls = (
         OneCycleLRSchedulerTrainer
         if cfg.lr_scheduler == "one_cycle" and (cfg.fsdp or cfg.adapter == "qlora")
-        else transformers.Trainer
+        else AxolotlTrainer
     )
     trainer = trainer_cls(
         model=model,

src/axolotl/utils/validation.py

@@ -87,11 +87,16 @@ def validate_config(cfg):
             "You probably want to disable group_by_length as it will force a streamed dataset to download completely."
         )
 
-    if any([cfg.adamw_beta1, cfg.adamw_beta2, cfg.adamw_epsilon]) and (
+    if any([cfg.adam_beta1, cfg.adam_beta2, cfg.adam_epsilon]) and (
         not cfg.optimizer or "adamw" not in cfg.optimizer
     ):
         logging.warning("adamw hyperparameters found, but no adamw optimizer set")
 
+    if cfg.push_to_hub_model_id:
+        raise ValueError(
+            "push_to_hub_model_id is deprecated. Please use hub_model_id instead."
+        )
+
     # TODO
     # MPT 7b
     # https://github.com/facebookresearch/bitsandbytes/issues/25

tests/test_validation.py

@@ -268,7 +268,7 @@ class ValidationTest(unittest.TestCase):
         cfg = DictDefault(
             {
                 "optimizer": None,
-                "adamw_epsilon": 0.0001,
+                "adam_epsilon": 0.0001,
             }
         )
 
@@ -283,7 +283,7 @@ class ValidationTest(unittest.TestCase):
         cfg = DictDefault(
             {
                 "optimizer": "adafactor",
-                "adamw_beta1": 0.0001,
+                "adam_beta1": 0.0001,
             }
         )
 
@@ -298,9 +298,9 @@ class ValidationTest(unittest.TestCase):
         cfg = DictDefault(
             {
                 "optimizer": "adamw_bnb_8bit",
-                "adamw_beta1": 0.0001,
+                "adam_beta1": 0.9,
-                "adamw_beta2": 0.0001,
+                "adam_beta2": 0.99,
-                "adamw_epsilon": 0.0001,
+                "adam_epsilon": 0.0001,
             }
         )