without torch.distributed.run

Not using distributed mode
2023-07-21 12:01:49,218 [INFO]
=====  Running Parameters    =====
2023-07-21 12:01:49,218 [INFO] {
    "amp": true,
    "batch_size_eval": 1,
    "batch_size_train": 3,
    "device": "cuda",
    "dist_url": "env://",
    "distributed": false,
    "evaluate": false,
    "init_lr": 5e-06,
    "iters_per_inner_epoch": 40,
    "lr_sched": "constant_lr",
    "max_iters": 40,
    "min_lr": 0,
    "num_workers": 4,
    "output_dir": "train_output",
    "resume_ckpt_path": null,
    "runner": "runner_iter",
    "seed": 42,
    "task": "text-to-image-generation",
    "train_splits": [
        "train"
    ],
    "weight_decay": 0.01,
    "world_size": 1
}
2023-07-21 12:01:49,218 [INFO]
======  Dataset Attributes  ======
2023-07-21 12:01:49,218 [INFO]
======== blip_diffusion_finetune =======
2023-07-21 12:01:49,219 [INFO] {
    "build_info": {
        "images": {
            "storage": "train_images"
        },
        "subject_text": "feigin"
    },
    "data_type": "images",
    "kw_processor": {
        "inp_vis_processor": {
            "name": "blip_diffusion_inp_image_train"
        },
        "tgt_vis_processor": {
            "name": "blip_diffusion_tgt_image_train"
        }
    },
    "text_processor": {
        "eval": {
            "name": "blip_caption"
        },
        "train": {
            "name": "blip_caption"
        }
    }
}
2023-07-21 12:01:49,219 [INFO]
======  Model Attributes  ======
2023-07-21 12:01:49,219 [INFO] {
    "arch": "blip_diffusion",
    "load_finetuned": false,
    "load_pretrained": true,
    "model_type": "base",
    "pretrained": "https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP-Diffusion/blip-diffusion.tar.gz",
    "qformer_cross_attention_freq": 1,
    "qformer_num_query_token": 16,
    "qformer_train": false,
    "sd_pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5",
    "sd_train_text_encoder": false,
    "vae_half_precision": true,
    "vit_model": "clip_L"
}
/workspace/LAVIS/lavis/datasets/builders/base_dataset_builder.py:164: UserWarning:
                The specified path /export/home/.cache/lavis/train_images for visual inputs does not exist.
                Please provide a correct path to the visual inputs or
                refer to datasets/download_scripts/README.md for downloading instructions.

  warnings.warn(
2023-07-21 12:01:49,222 [INFO] Building datasets...
2023-07-21 12:01:52,190 [INFO] freeze vision encoder
Cannot initialize model with low cpu memory usage because `accelerate` was not found in the environment. Defaulting to `low_cpu_mem_usage=False`. It is strongly recommended to install `accelerate` for faster and less memory-intense model loading. You can do so with:
```
pip install accelerate
```
.
Cannot initialize model with low cpu memory usage because `accelerate` was not found in the environment. Defaulting to `low_cpu_mem_usage=False`. It is strongly recommended to install `accelerate` for faster and less memory-intense model loading. You can do so with:
```
pip install accelerate
```
.
/usr/local/lib/python3.10/dist-packages/diffusers/configuration_utils.py:215: FutureWarning: It is deprecated to pass a pretrained model name or path to `from_config`.If you were trying to load a scheduler, please use <class 'diffusers.schedulers.scheduling_ddpm.DDPMScheduler'>.from_pretrained(...) instead. Otherwise, please make sure to pass a configuration dictionary instead. This functionality will be removed in v1.0.0.
  deprecate("config-passed-as-path", "1.0.0", deprecation_message, standard_warn=False)
2023-07-21 12:02:04,271 [INFO] Loading pretrained model from /root/.cache/torch/hub/checkpoints/blip-diffusion
No ctx_embeddings_cache found in /root/.cache/torch/hub/checkpoints/blip-diffusion
2023-07-21 12:02:06,932 [INFO] Start training, max_iters=40, in total 1 inner epochs.
2023-07-21 12:02:08,532 [INFO] dataset_ratios not specified, datasets will be concatenated (map-style datasets) or chained (webdataset.DataPipeline).
2023-07-21 12:02:08,533 [INFO] Loaded 2200000 records for train split from the dataset.
2023-07-21 12:02:08,579 [INFO] number of trainable parameters: 859520964
2023-07-21 12:02:08,580 [INFO] Start training epoch 0, 40 iters per inner epoch.
Traceback (most recent call last):
  File "/workspace/LAVIS/train.py", line 103, in <module>
    main()
  File "/workspace/LAVIS/train.py", line 99, in main
    runner.train()
  File "/workspace/LAVIS/lavis/runners/runner_iter.py", line 99, in train
    train_stats = self.train_iters(self.cur_epoch, start_iters)
  File "/workspace/LAVIS/lavis/runners/runner_iter.py", line 145, in train_iters
    return self.task.train_iters(
  File "/workspace/LAVIS/lavis/tasks/base_task.py", line 144, in train_iters
    return self._train_inner_loop(
  File "/workspace/LAVIS/lavis/tasks/base_task.py", line 222, in _train_inner_loop
    loss, loss_dict = self.train_step(model=model, samples=samples)
  File "/workspace/LAVIS/lavis/tasks/base_task.py", line 64, in train_step
    output = model(samples)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 363, in _forward_unimplemented
    raise NotImplementedError(f"Module [{type(self).__name__}] is missing the required \"forward\" function")
NotImplementedError: Module [BlipDiffusion] is missing the required "forward" function