config.json

{
  "_name_or_path": "pretrain_checkpoints/model-epoch_6-step_220398-udata_loss_0.0896958740234375-wiki_loss_0.140931982421875/",
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "architectures": [
    "M2M100ForConditionalGeneration"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 8192,
  "decoder_layerdrop": 0.05,
  "decoder_layers": 24,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "early_stopping": true,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 8192,
  "encoder_layerdrop": 0.05,
  "encoder_layers": 24,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "max_length": 200,
  "max_position_embeddings": 1024,
  "model_type": "m2m_100",
  "num_beams": 5,
  "num_hidden_layers": 24,
  "pad_token_id": 1,
  "scale_embedding": true,
  "torch_dtype": "float32",
  "transformers_version": "4.22.0",
  "use_cache": true,
  "vocab_size": 14341
}