size mismatch for encoder.embed_tokens.weight

[Rexbalaeniceps]

Thanks for your code. An error occurred while attempting to evaluate on test dataset.

fairseq plugins loaded...
2021-11-12 08:25:29 | INFO | fairseq_cli.generate | {'_name': None, 'common': {'_name': None, 'no_progress_bar': False, 'log_interval': 100, 'log_format': None, 'tensorboard_logdir': None, 'wandb_project': None, 'azureml_logging': False, 'seed': 1, 'cpu': False, 'tpu': False, 'bf16': False, 'memory_efficient_bf16': False, 'fp16': False, 'memory_efficient_fp16': False, 'fp16_no_flatten_grads': False, 'fp16_init_scale': 128, 'fp16_scale_window': None, 'fp16_scale_tolerance': 0.0, 'min_loss_scale': 0.0001, 'threshold_loss_scale': None, 'user_dir': 'glat_plugins', 'empty_cache_freq': 0, 'all_gather_list_size': 16384, 'model_parallel_size': 1, 'quantization_config_path': None, 'profile': False, 'reset_logging': False, 'suppress_crashes': False}, 'common_eval': {'_name': None, 'path': '/data/wbxu/GLAT_Checkpoints/checkpoint_best.pt', 'post_process': 'subword_nmt', 'quiet': True, 'model_overrides': '{}', 'results_path': None}, 'distributed_training': {'_name': None, 'distributed_world_size': 1, 'distributed_rank': 0, 'distributed_backend': 'nccl', 'distributed_init_method': None, 'distributed_port': -1, 'device_id': 0, 'distributed_no_spawn': False, 'ddp_backend': 'pytorch_ddp', 'bucket_cap_mb': 25, 'fix_batches_to_gpus': False, 'find_unused_parameters': False, 'fast_stat_sync': False, 'heartbeat_timeout': -1, 'broadcast_buffers': False, 'slowmo_momentum': None, 'slowmo_algorithm': 'LocalSGD', 'localsgd_frequency': 3, 'nprocs_per_node': 2, 'pipeline_model_parallel': False, 'pipeline_balance': None, 'pipeline_devices': None, 'pipeline_chunks': 0, 'pipeline_encoder_balance': None, 'pipeline_encoder_devices': None, 'pipeline_decoder_balance': None, 'pipeline_decoder_devices': None, 'pipeline_checkpoint': 'never', 'zero_sharding': 'none', 'tpu': False}, 'dataset': {'_name': None, 'num_workers': 1, 'skip_invalid_size_inputs_valid_test': False, 'max_tokens': None, 'batch_size': 20, 'required_batch_size_multiple': 8, 'required_seq_len_multiple': 1, 'dataset_impl': None, 'data_buffer_size': 10, 'train_subset': 'train', 'valid_subset': 'valid', 'validate_interval': 1, 'validate_interval_updates': 0, 'validate_after_updates': 0, 'fixed_validation_seed': None, 'disable_validation': False, 'max_tokens_valid': None, 'batch_size_valid': 20, 'curriculum': 0, 'gen_subset': 'test', 'num_shards': 1, 'shard_id': 0}, 'optimization': {'_name': None, 'max_epoch': 0, 'max_update': 0, 'stop_time_hours': 0.0, 'clip_norm': 0.0, 'sentence_avg': False, 'update_freq': [1], 'lr': [0.25], 'stop_min_lr': -1.0, 'use_bmuf': False}, 'checkpoint': {'_name': None, 'save_dir': 'checkpoints', 'restore_file': 'checkpoint_last.pt', 'finetune_from_model': None, 'reset_dataloader': False, 'reset_lr_scheduler': False, 'reset_meters': False, 'reset_optimizer': False, 'optimizer_overrides': '{}', 'save_interval': 1, 'save_interval_updates': 0, 'keep_interval_updates': -1, 'keep_last_epochs': -1, 'keep_best_checkpoints': -1, 'no_save': False, 'no_epoch_checkpoints': False, 'no_last_checkpoints': False, 'no_save_optimizer_state': False, 'best_checkpoint_metric': 'loss', 'maximize_best_checkpoint_metric': False, 'patience': -1, 'checkpoint_suffix': '', 'checkpoint_shard_count': 1, 'load_checkpoint_on_all_dp_ranks': False, 'model_parallel_size': 1, 'distributed_rank': 0}, 'bmuf': {'_name': None, 'block_lr': 1.0, 'block_momentum': 0.875, 'global_sync_iter': 50, 'warmup_iterations': 500, 'use_nbm': False, 'average_sync': False, 'distributed_world_size': 1}, 'generation': {'_name': None, 'beam': 5, 'nbest': 1, 'max_len_a': 0.0, 'max_len_b': 200, 'min_len': 1, 'match_source_len': False, 'unnormalized': False, 'no_early_stop': False, 'no_beamable_mm': False, 'lenpen': 1.0, 'unkpen': 0.0, 'replace_unk': None, 'sacrebleu': False, 'score_reference': False, 'prefix_size': 0, 'no_repeat_ngram_size': 0, 'sampling': False, 'sampling_topk': -1, 'sampling_topp': -1.0, 'constraints': None, 'temperature': 1.0, 'diverse_beam_groups': -1, 'diverse_beam_strength': 0.5, 'diversity_rate': -1.0, 'print_alignment': None, 'print_step': False, 'lm_path': None, 'lm_weight': 0.0, 'iter_decode_eos_penalty': 0.0, 'iter_decode_max_iter': 0, 'iter_decode_force_max_iter': False, 'iter_decode_with_beam': 1, 'iter_decode_with_external_reranker': False, 'retain_iter_history': False, 'retain_dropout': False, 'retain_dropout_modules': None, 'decoding_format': None, 'no_seed_provided': False}, 'eval_lm': {'_name': None, 'output_word_probs': False, 'output_word_stats': False, 'context_window': 0, 'softmax_batch': 9223372036854775807}, 'interactive': {'_name': None, 'buffer_size': 0, 'input': '-'}, 'model': None, 'task': {'_name': 'translation_lev_modified', 'data': '/data/wbxu/DSLP-main/data-bin/wmt14.en-de_kd', 'source_lang': 'en', 'target_lang': 'de', 'load_alignments': False, 'left_pad_source': False, 'left_pad_target': False, 'max_source_positions': 1024, 'max_target_positions': 1024, 'upsample_primary': -1, 'truncate_source': False, 'num_batch_buckets': 0, 'train_subset': 'train', 'dataset_impl': None, 'required_seq_len_multiple': 1, 'eval_bleu': False, 'eval_bleu_args': '{}', 'eval_bleu_detok': 'space', 'eval_bleu_detok_args': '{}', 'eval_tokenized_bleu': False, 'eval_bleu_remove_bpe': None, 'eval_bleu_print_samples': False, 'noise': 'random_delete', 'start_p': 0.5, 'minus_p': 0.2, 'total_up': 300000}, 'criterion': {'_name': 'cross_entropy', 'sentence_avg': True}, 'optimizer': None, 'lr_scheduler': {'_name': 'fixed', 'force_anneal': None, 'lr_shrink': 0.1, 'warmup_updates': 0, 'lr': [0.25]}, 'scoring': {'_name': 'bleu', 'pad': 1, 'eos': 2, 'unk': 3}, 'bpe': None, 'tokenizer': None}
2021-11-12 08:25:29 | INFO | fairseq.tasks.translation | [en] dictionary: 39840 types
2021-11-12 08:25:29 | INFO | fairseq.tasks.translation | [de] dictionary: 39840 types
2021-11-12 08:25:29 | INFO | fairseq_cli.generate | loading model(s) from /data/wbxu/GLAT_Checkpoints/checkpoint_best.pt
/home/wbxu/anaconda3/envs/GLATEnv/lib/python3.7/site-packages/omegaconf/omegaconf.py:579: UserWarning: update() merge flag is is not specified, defaulting to False.
For more details, see https://github.com/omry/omegaconf/issues/367
  stacklevel=1,
Traceback (most recent call last):
  File "fairseq_cli/generate.py", line 408, in <module>
    cli_main()
  File "fairseq_cli/generate.py", line 404, in cli_main
    main(args)
  File "fairseq_cli/generate.py", line 49, in main
    return _main(cfg, sys.stdout)
  File "fairseq_cli/generate.py", line 102, in _main
    num_shards=cfg.checkpoint.checkpoint_shard_count,
  File "/data/wbxu/GLAT-main/fairseq/checkpoint_utils.py", line 304, in load_model_ensemble
    state,
  File "/data/wbxu/GLAT-main/fairseq/checkpoint_utils.py", line 358, in load_model_ensemble_and_task
    model.load_state_dict(state["model"], strict=strict, model_cfg=cfg.model)
  File "/data/wbxu/GLAT-main/fairseq/models/fairseq_model.py", line 115, in load_state_dict
    return super().load_state_dict(new_state_dict, strict)
  File "/home/wbxu/anaconda3/envs/GLATEnv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1052, in load_state_dict
    self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for Glat:
	size mismatch for encoder.embed_tokens.weight: copying a param with shape torch.Size([39847, 512]) from checkpoint, the shape in current model is torch.Size([39840, 512]).
	size mismatch for decoder.embed_tokens.weight: copying a param with shape torch.Size([39847, 512]) from checkpoint, the shape in current model is torch.Size([39840, 512]).
	size mismatch for decoder.output_projection.weight: copying a param with shape torch.Size([39847, 512]) from checkpoint, the shape in current model is torch.Size([39840, 512]).