End of training

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: checkpoints
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# checkpoints
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2461
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| No log        | 1.0   | 418   | 2.7793          |
+| 2.9952        | 2.0   | 836   | 2.6914          |
+| 2.7684        | 3.0   | 1254  | 2.6348          |
+| 2.685         | 4.0   | 1672  | 2.5938          |
+| 2.6243        | 5.0   | 2090  | 2.5625          |
+| 2.5816        | 6.0   | 2508  | 2.5332          |
+| 2.5816        | 7.0   | 2926  | 2.5098          |
+| 2.545         | 8.0   | 3344  | 2.4902          |
+| 2.5083        | 9.0   | 3762  | 2.4707          |
+| 2.4793        | 10.0  | 4180  | 2.4551          |
+| 2.4531        | 11.0  | 4598  | 2.4395          |
+| 2.4269        | 12.0  | 5016  | 2.4238          |
+| 2.4269        | 13.0  | 5434  | 2.4102          |
+| 2.4051        | 14.0  | 5852  | 2.3945          |
+| 2.3777        | 15.0  | 6270  | 2.3848          |
+| 2.3603        | 16.0  | 6688  | 2.3711          |
+| 2.3394        | 17.0  | 7106  | 2.3613          |
+| 2.3206        | 18.0  | 7524  | 2.3516          |
+| 2.3206        | 19.0  | 7942  | 2.3398          |
+| 2.3026        | 20.0  | 8360  | 2.3301          |
+| 2.2823        | 21.0  | 8778  | 2.3203          |
+| 2.2669        | 22.0  | 9196  | 2.3105          |
+| 2.2493        | 23.0  | 9614  | 2.3027          |
+| 2.2334        | 24.0  | 10032 | 2.2930          |
+| 2.2334        | 25.0  | 10450 | 2.2852          |
+| 2.2194        | 26.0  | 10868 | 2.2754          |
+| 2.2014        | 27.0  | 11286 | 2.2695          |
+| 2.1868        | 28.0  | 11704 | 2.2598          |
+| 2.171         | 29.0  | 12122 | 2.2539          |
+| 2.1597        | 30.0  | 12540 | 2.2461          |
+
+
+### Framework versions
+
+- Transformers 4.16.1
+- Pytorch 1.10.0+cu111
+- Tokenizers 0.11.0

last-checkpoint/config.json

@@ -1,46 +0,0 @@
-{
-  "_name_or_path": "distilgpt2",
-  "_num_labels": 1,
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
-  "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 6,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
-  "torch_dtype": "float16",
-  "transformers_version": "4.16.1",
-  "use_cache": false,
-  "vocab_size": 50257
-}

last-checkpoint/global_step418/mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1e01de6ce43a3831ba72c1ac13b04f60cb557bdcc5129d42bcb95d5dc78edd81
-size 176426750

last-checkpoint/global_step418/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:36f6013451b3047bcc0050270d1638ebab4112c301a6abd3aaf403e82e58bbd9
-size 982958179

last-checkpoint/latest

@@ -1 +0,0 @@
-global_step418

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d4158ac6be6eb8a3c9e54b9d4aa678b213d42262a515e563e3f41306e60c4357
-size 176424894

last-checkpoint/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9718ad0bd253e9900a6523cdece06f611939230f60fe782f2a9cceaccc19132b
-size 14503

last-checkpoint/trainer_state.json

@@ -1,24 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.998805256869773,
-  "global_step": 418,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "eval_loss": 2.779296875,
-      "eval_runtime": 13.8161,
-      "eval_samples_per_second": 1296.528,
-      "eval_steps_per_second": 40.532,
-      "step": 418
-    }
-  ],
-  "max_steps": 12540,
-  "num_train_epochs": 30,
-  "total_flos": 1749218444181504.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:83d8354bcc1c4902bf8b8dbff4bd5a46adcf8432ce6e93a791b460f3959caf98
-size 4143

last-checkpoint/zero_to_fp32.py

@@ -1,453 +0,0 @@
-#!/usr/bin/env python
-
-# This script extracts fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints. It gets
-# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
-# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
-# application.
-#
-# example: python zero_to_fp32.py . pytorch_model.bin
-
-import argparse
-import torch
-import glob
-import math
-import os
-from collections import OrderedDict
-
-# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
-# DeepSpeed data structures it has to be available in the current python environment.
-import deepspeed
-from deepspeed.utils import logger
-
-debug = 0
-
-# load to cpu
-device = torch.device('cpu')
-
-
-def get_model_state_file(checkpoint_dir, zero_stage):
-    if not os.path.isdir(checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
-
-    # there should be only one file
-    if zero_stage == 2:
-        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
-    elif zero_stage == 3:
-        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
-
-    if not os.path.exists(file):
-        raise FileNotFoundError(f"can't find model states file at '{file}'")
-
-    return file
-
-
-def get_optim_files(checkpoint_dir):
-    # XXX: need to test that this simple glob rule works for multi-node setup too
-    optim_files = sorted(glob.glob(os.path.join(checkpoint_dir, "*_optim_states.pt")))
-
-    if len(optim_files) == 0:
-        raise FileNotFoundError(
-            f"can't find '*_optim_states.pt' files in directory '{checkpoint_dir}'")
-
-    return optim_files
-
-
-def parse_model_state(file):
-    state_dict = torch.load(file, map_location=device)
-
-    if "buffer_names" not in state_dict:
-        raise ValueError(f"{file} is not a model state checkpoint")
-    buffer_names = state_dict["buffer_names"]
-    if debug:
-        print("Found buffers:", buffer_names)
-
-    # recover just the buffers while restoring them to fp32 if they were saved in fp16
-    buffers = {
-        k: v.float()
-        for k,
-        v in state_dict["module"].items() if k in buffer_names
-    }
-    return buffers
-
-
-def parse_optim_states(files, ds_checkpoint_dir):
-
-    total_files = len(files)
-    state_dicts = []
-    for f in files:
-        state_dicts.append(torch.load(f, map_location=device))
-
-    if not "zero_stage" in state_dicts[0]['optimizer_state_dict']:
-        raise ValueError(f"{files[0]} is not a zero checkpoint")
-    zero_stage = state_dicts[0]['optimizer_state_dict']["zero_stage"]
-    world_size = state_dicts[0]['optimizer_state_dict']["partition_count"]
-    param_shapes = state_dicts[0]["param_shapes"]
-    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
-    # parameters can be different from data parallelism for non-expert parameters. So we can just
-    # use the max of the partition_count to get the dp world_size.
-
-    if type(world_size) is list:
-        world_size = max(world_size)
-
-    if world_size != total_files:
-        raise ValueError(
-            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
-            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
-        )
-
-    # the groups are named differently in each stage
-    if zero_stage == 2:
-        fp32_groups_key = "single_partition_of_fp32_groups"
-    elif zero_stage == 3:
-        fp32_groups_key = "fp32_flat_groups"
-    else:
-        raise ValueError(f"unknown zero stage {zero_stage}")
-
-    if zero_stage == 2:
-        fp32_flat_groups = [
-            state_dicts[i]['optimizer_state_dict'][fp32_groups_key]
-            for i in range(len(state_dicts))
-        ]
-    elif zero_stage == 3:
-        # if there is more than one param group, there will be multiple flattened tensors - one
-        # flattened tensor per group - for simplicity merge them into a single tensor
-        #
-        # XXX: could make the script more memory efficient for when there are multiple groups - it
-        # will require matching the sub-lists of param_shapes for each param group flattened tensor
-
-        fp32_flat_groups = [
-            torch.cat(state_dicts[i]['optimizer_state_dict'][fp32_groups_key],
-                      0) for i in range(len(state_dicts))
-        ]
-
-    return zero_stage, world_size, param_shapes, fp32_flat_groups
-
-
-def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
-    """
-    Returns fp32 state_dict reconstructed from ds checkpoint
-
-    Args:
-        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
-
-    """
-    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
-
-    optim_files = get_optim_files(ds_checkpoint_dir)
-    zero_stage, world_size, param_shapes, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
-    print(
-        f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
-
-    model_file = get_model_state_file(ds_checkpoint_dir, zero_stage)
-    buffers = parse_model_state(model_file)
-
-    if zero_stage == 2:
-        return _get_fp32_state_dict_from_zero2_checkpoint(world_size,
-                                                          param_shapes,
-                                                          fp32_flat_groups,
-                                                          buffers)
-    elif zero_stage == 3:
-        return _get_fp32_state_dict_from_zero3_checkpoint(world_size,
-                                                          param_shapes,
-                                                          fp32_flat_groups,
-                                                          buffers)
-
-
-def _get_fp32_state_dict_from_zero2_checkpoint(world_size,
-                                               param_shapes,
-                                               fp32_flat_groups,
-                                               buffers):
-
-    # Reconstruction protocol:
-    #
-    # XXX: document this
-
-    if debug:
-        for i in range(world_size):
-            for j in range(len(fp32_flat_groups[0])):
-                print(f"fp32_flat_groups[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
-
-    # XXX: memory usage doubles here (zero2)
-    num_param_groups = len(fp32_flat_groups[0])
-    merged_single_partition_of_fp32_groups = []
-    for i in range(num_param_groups):
-        merged_partitions = [sd[i] for sd in fp32_flat_groups]
-        full_single_fp32_vector = torch.cat(merged_partitions, 0)
-        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
-    avail_numel = sum([
-        full_single_fp32_vector.numel()
-        for full_single_fp32_vector in merged_single_partition_of_fp32_groups
-    ])
-
-    if debug:
-        wanted_params = sum([len(shapes) for shapes in param_shapes])
-        wanted_numel = sum(
-            [sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
-        # not asserting if there is a mismatch due to possible padding
-        print(f"Have {avail_numel} numels to process.")
-        print(f"Need {wanted_numel} numels in {wanted_params} params.")
-
-    state_dict = OrderedDict()
-
-    # buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    total_numel = 0
-    total_params = 0
-    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
-        offset = 0
-        avail_numel = full_single_fp32_vector.numel()
-        for name, shape in shapes.items():
-
-            unpartitioned_numel = shape.numel()
-            total_numel += unpartitioned_numel
-            total_params += 1
-
-            if debug:
-                print(
-                    f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} "
-                )
-            state_dict[name] = full_single_fp32_vector.narrow(
-                0,
-                offset,
-                unpartitioned_numel).view(shape)
-            offset += unpartitioned_numel
-
-        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
-        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
-        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
-        # live optimizer object, so we are checking that the numbers are within the right range
-        align_to = 2 * world_size
-
-        def zero2_align(x):
-            return align_to * math.ceil(x / align_to)
-
-        if debug:
-            print(f"original offset={offset}, avail_numel={avail_numel}")
-
-        offset = zero2_align(offset)
-        avail_numel = zero2_align(avail_numel)
-
-        if debug:
-            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
-
-        # Sanity check
-        if offset != avail_numel:
-            raise ValueError(
-                f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(
-        f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements"
-    )
-
-    return state_dict
-
-
-def zero3_partitioned_param_info(unpartitioned_numel, world_size):
-    remainder = unpartitioned_numel % world_size
-    padding_numel = (world_size - remainder) if remainder else 0
-    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
-    return partitioned_numel, padding_numel
-
-
-def _get_fp32_state_dict_from_zero3_checkpoint(world_size,
-                                               param_shapes,
-                                               fp32_flat_groups,
-                                               buffers):
-
-    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
-    # param, re-consolidating each param, while dealing with padding if any
-
-    avail_numel = fp32_flat_groups[0].numel() * world_size
-    # merge list of dicts, preserving order
-    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
-
-    if debug:
-        for i in range(world_size):
-            print(f"fp32_flat_groups[{i}].shape={fp32_flat_groups[i].shape}")
-
-        wanted_params = len(param_shapes)
-        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
-        # not asserting if there is a mismatch due to possible padding
-        print(f"Have {avail_numel} numels to process.")
-        print(f"Need {wanted_numel} numels in {wanted_params} params.")
-
-    state_dict = OrderedDict()
-
-    # buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    offset = 0
-    total_numel = 0
-    total_params = 0
-    for name, shape in param_shapes.items():
-
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-        total_params += 1
-
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"{total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-        # XXX: memory usage doubles here
-        state_dict[name] = torch.cat(
-            tuple(fp32_flat_groups[i].narrow(0,
-                                             offset,
-                                             partitioned_numel)
-                  for i in range(world_size)),
-            0).narrow(0,
-                      0,
-                      unpartitioned_numel).view(shape)
-        offset += partitioned_numel
-
-    offset *= world_size
-
-    # Sanity check
-    if offset != avail_numel:
-        raise ValueError(
-            f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(
-        f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements"
-    )
-
-    return state_dict
-
-
-def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
-    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
-    via a model hub.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
-
-    Returns:
-        - pytorch ``state_dict``
-
-    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
-    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
-    the checkpoint.
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
-        # do the training and checkpoint saving
-        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
-        model = model.cpu() # move to cpu
-        model.load_state_dict(state_dict)
-        # submit to model hub or save the model to share with others
-
-    In this example the ``model`` will no longer be usable in the deepspeed context of the same
-    application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
-
-    """
-    if tag is None:
-        latest_path = os.path.join(checkpoint_dir, 'latest')
-        if os.path.isfile(latest_path):
-            with open(latest_path, 'r') as fd:
-                tag = fd.read().strip()
-        else:
-            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
-
-    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
-
-    if not os.path.isdir(ds_checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
-
-    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
-
-
-def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
-    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-    """
-
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-    print(f"Saving fp32 state dict to {output_file}")
-    torch.save(state_dict, output_file)
-
-
-def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
-    """
-    1. Put the provided model to cpu
-    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
-    3. Load it into the provided model
-
-    Args:
-        - ``model``: the model object to update
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-
-    Returns:
-        - ``model`: modified model
-
-    Make sure you have plenty of CPU memory available before you call this function. If you don't
-    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
-    conveniently placed for you in the checkpoint folder.
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
-        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
-        # submit to model hub or save the model to share with others
-
-    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
-    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    """
-    logger.info(f"Extracting fp32 weights")
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-
-    logger.info(f"Overwriting model with fp32 weights")
-    model = model.cpu()
-    model.load_state_dict(state_dict, strict=False)
-
-    return model
-
-
-if __name__ == "__main__":
-
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "checkpoint_dir",
-        type=str,
-        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
-    parser.add_argument(
-        "output_file",
-        type=str,
-        help=
-        "path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)"
-    )
-    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
-    args = parser.parse_args()
-
-    debug = args.debug
-
-    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4158ac6be6eb8a3c9e54b9d4aa678b213d42262a515e563e3f41306e60c4357
+oid sha256:af7f9e89c13cd0bf18d5984200f49f6a1b168261eddc96ed0771abb13b96ae61
 size 176424894