diff --git a/config.json b/config.json index dcab3f3..18e15e0 100644 --- a/config.json +++ b/config.json @@ -1,7 +1,9 @@ { + "_num_labels": 3, "activation_dropout": 0.0, "architectures": null, "attention_dropout": 0.0, + "bos_token_id": 0, "classif_dropout": 0.0, "d_model": 1024, "decoder_attention_heads": 16, @@ -10,10 +12,14 @@ "decoder_layers": 12, "do_sample": false, "dropout": 0.1, + "early_stopping": false, "encoder_attention_heads": 16, "encoder_ffn_dim": 4096, "encoder_layerdrop": 0.0, "encoder_layers": 12, + "eos_token_ids": [ + 2 + ], "finetuning_task": null, "id2label": { "0": "LABEL_0", @@ -22,22 +28,25 @@ }, "init_std": 0.02, "is_decoder": false, + "is_encoder_decoder": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, - "length_penalty": 1.0, + "length_penalty": 2.0, "max_length": 20, "max_position_embeddings": 1024, + "min_length": 0, "model_type": "bart", - "num_beams": 1, + "no_repeat_ngram_size": 3, + "num_beams": 4, "num_hidden_layers": 12, - "num_labels": 3, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_past": true, + "pad_token_id": 1, "pruned_heads": {}, "repetition_penalty": 1.0, "temperature": 1.0,