lxyuan's picture
Training in progress, epoch 0
432680a
{
"architectures": [
"SpanMarkerModel"
],
"encoder": {
"_name_or_path": "bert-base-multilingual-cased",
"add_cross_attention": false,
"architectures": [
"BertForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"directionality": "bidi",
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "B-PER",
"2": "I-PER",
"3": "B-ORG",
"4": "I-ORG",
"5": "B-LOC",
"6": "I-LOC",
"7": "B-ANIM",
"8": "I-ANIM",
"9": "B-BIO",
"10": "I-BIO",
"11": "B-CEL",
"12": "I-CEL",
"13": "B-DIS",
"14": "I-DIS",
"15": "B-EVE",
"16": "I-EVE",
"17": "B-FOOD",
"18": "I-FOOD",
"19": "B-INST",
"20": "I-INST",
"21": "B-MEDIA",
"22": "I-MEDIA",
"23": "B-MYTH",
"24": "I-MYTH",
"25": "B-PLANT",
"26": "I-PLANT",
"27": "B-TIME",
"28": "I-TIME",
"29": "B-VEHI",
"30": "I-VEHI"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"B-ANIM": 7,
"B-BIO": 9,
"B-CEL": 11,
"B-DIS": 13,
"B-EVE": 15,
"B-FOOD": 17,
"B-INST": 19,
"B-LOC": 5,
"B-MEDIA": 21,
"B-MYTH": 23,
"B-ORG": 3,
"B-PER": 1,
"B-PLANT": 25,
"B-TIME": 27,
"B-VEHI": 29,
"I-ANIM": 8,
"I-BIO": 10,
"I-CEL": 12,
"I-DIS": 14,
"I-EVE": 16,
"I-FOOD": 18,
"I-INST": 20,
"I-LOC": 6,
"I-MEDIA": 22,
"I-MYTH": 24,
"I-ORG": 4,
"I-PER": 2,
"I-PLANT": 26,
"I-TIME": 28,
"I-VEHI": 30,
"O": 0
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"min_length": 0,
"model_type": "bert",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.30.2",
"type_vocab_size": 2,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 119549
},
"entity_max_length": 8,
"id2label": {
"0": "O",
"1": "ANIM",
"2": "BIO",
"3": "CEL",
"4": "DIS",
"5": "EVE",
"6": "FOOD",
"7": "INST",
"8": "LOC",
"9": "MEDIA",
"10": "MYTH",
"11": "ORG",
"12": "PER",
"13": "PLANT",
"14": "TIME",
"15": "VEHI"
},
"id2reduced_id": {
"0": 0,
"1": 12,
"2": 12,
"3": 11,
"4": 11,
"5": 8,
"6": 8,
"7": 1,
"8": 1,
"9": 2,
"10": 2,
"11": 3,
"12": 3,
"13": 4,
"14": 4,
"15": 5,
"16": 5,
"17": 6,
"18": 6,
"19": 7,
"20": 7,
"21": 9,
"22": 9,
"23": 10,
"24": 10,
"25": 13,
"26": 13,
"27": 14,
"28": 14,
"29": 15,
"30": 15
},
"label2id": {
"ANIM": 1,
"BIO": 2,
"CEL": 3,
"DIS": 4,
"EVE": 5,
"FOOD": 6,
"INST": 7,
"LOC": 8,
"MEDIA": 9,
"MYTH": 10,
"O": 0,
"ORG": 11,
"PER": 12,
"PLANT": 13,
"TIME": 14,
"VEHI": 15
},
"marker_max_length": 128,
"max_next_context": null,
"max_prev_context": null,
"model_max_length": 256,
"model_max_length_default": 512,
"model_type": "span-marker",
"span_marker_version": "1.2.4",
"torch_dtype": "float32",
"trained_with_document_context": false,
"transformers_version": "4.30.2",
"vocab_size": 119549
}