best_model_bert / best_model_config.json
ZahidAhmad's picture
Upload best_model_config.json
fae6a5f verified
{
"vocab_size": 30522,
"max_position_embeddings": 512,
"sinusoidal_pos_embds": false,
"n_layers": 6,
"n_heads": 12,
"dim": 768,
"hidden_dim": 3072,
"dropout": 0.1,
"attention_dropout": 0.1,
"activation": "gelu",
"initializer_range": 0.02,
"qa_dropout": 0.1,
"seq_classif_dropout": 0.2,
"return_dict": true,
"output_hidden_states": false,
"output_attentions": false,
"torchscript": false,
"torch_dtype": "float32",
"use_bfloat16": false,
"tf_legacy_loss": false,
"pruned_heads": {},
"tie_word_embeddings": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"architectures": [
"DistilBertForSequenceClassification"
],
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8",
"9": "LABEL_9",
"10": "LABEL_10",
"11": "LABEL_11"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7,
"LABEL_8": 8,
"LABEL_9": 9,
"LABEL_10": 10,
"LABEL_11": 11
},
"tokenizer_class": null,
"prefix": null,
"bos_token_id": null,
"pad_token_id": 0,
"eos_token_id": null,
"sep_token_id": null,
"decoder_start_token_id": null,
"task_specific_params": null,
"problem_type": null,
"_name_or_path": "distilbert-base-uncased",
"transformers_version": "4.38.2",
"model_type": "distilbert",
"tie_weights_": true
}