DunnBC22's picture
Training in progress, epoch 1
7d19d84
{
"_name_or_path": "xlnet-base-cased",
"architectures": [
"XLNetForTokenClassification"
],
"attn_type": "bi",
"bi_data": false,
"bos_token_id": 1,
"clamp_len": -1,
"d_head": 64,
"d_inner": 3072,
"d_model": 768,
"dropout": 0.1,
"end_n_top": 5,
"eos_token_id": 2,
"ff_activation": "gelu",
"id2label": {
"0": "O",
"1": "B-PER",
"2": "I-PER",
"3": "B-ORG",
"4": "I-ORG",
"5": "B-LOC",
"6": "I-LOC",
"7": "B-MISC",
"8": "I-MISC"
},
"initializer_range": 0.02,
"label2id": {
"B-LOC": 5,
"B-MISC": 7,
"B-ORG": 3,
"B-PER": 1,
"I-LOC": 6,
"I-MISC": 8,
"I-ORG": 4,
"I-PER": 2,
"O": 0
},
"layer_norm_eps": 1e-12,
"mem_len": null,
"model_type": "xlnet",
"n_head": 12,
"n_layer": 12,
"pad_token_id": 5,
"reuse_len": null,
"same_length": false,
"start_n_top": 5,
"summary_activation": "tanh",
"summary_last_dropout": 0.1,
"summary_type": "last",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 250
}
},
"torch_dtype": "float32",
"transformers_version": "4.28.1",
"untie_r": true,
"use_mems_eval": true,
"use_mems_train": false,
"vocab_size": 32000
}