config.txt

/content/drive/MyDrive/LuanVan/Bart-BRIO/brio_project-main/BRIO/main.py
Namespace(cuda=True, gpuid=[0], evaluate=False, do_reranking=False, do_generation=False, log=True, port=12355, model_pt='', config='', batch_size=1, epoch=1, report_freq=100, accumulate_step=8, margin=0.001, gold_margin=0, gold_weight=0, mle_weight=0.1, rank_weight=10, model_type='vinai/bartpho-word-base', warmup_steps=10000, normalize=True, grad_norm=0, seed=970903, no_gold=False, pretrained='./finetuned_model_v3/eval_bartpho_final', max_lr=0.002, scale=0.5, score_mode='log', datatype='diverse', dataset='cooking_bart', max_len=120, max_num=6, smooth=0.01, total_len=1024, length_penalty=2.0, do_sample=True, gen_max_len=140, gen_min_len=55, is_pegasus=False, adding=0, eval_interval=1000, num_beams=6)

BRIO(
  (model): MBartScorer(
    (model): CustomMBartModel(
      (shared): Embedding(64001, 768, padding_idx=1)
      (encoder): MBartEncoder(
        (embed_tokens): Embedding(64001, 768, padding_idx=1)
        (embed_positions): MBartLearnedPositionalEmbedding(1026, 768)
        (layers): ModuleList(
          (0-5): 6 x MBartEncoderLayer(
            (self_attn): MBartAttention(
              (k_proj): Linear(in_features=768, out_features=768, bias=True)
              (v_proj): Linear(in_features=768, out_features=768, bias=True)
              (q_proj): Linear(in_features=768, out_features=768, bias=True)
              (out_proj): Linear(in_features=768, out_features=768, bias=True)
            )
            (self_attn_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
            (activation_fn): GELUActivation()
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          )
        )
        (layernorm_embedding): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (decoder): MBartDecoder(
        (embed_tokens): Embedding(64001, 768, padding_idx=1)
        (embed_positions): MBartLearnedPositionalEmbedding(1026, 768)
        (layers): ModuleList(
          (0-5): 6 x MBartDecoderLayer(
            (self_attn): MBartAttention(
              (k_proj): Linear(in_features=768, out_features=768, bias=True)
              (v_proj): Linear(in_features=768, out_features=768, bias=True)
              (q_proj): Linear(in_features=768, out_features=768, bias=True)
              (out_proj): Linear(in_features=768, out_features=768, bias=True)
            )
            (activation_fn): GELUActivation()
            (self_attn_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
            (encoder_attn): MBartAttention(
              (k_proj): Linear(in_features=768, out_features=768, bias=True)
              (v_proj): Linear(in_features=768, out_features=768, bias=True)
              (q_proj): Linear(in_features=768, out_features=768, bias=True)
              (out_proj): Linear(in_features=768, out_features=768, bias=True)
            )
            (encoder_attn_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (final_layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
          )
        )
        (layernorm_embedding): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (layer_norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
    )
    (lm_head): Linear(in_features=768, out_features=64001, bias=False)
  )
)