robbert0410_lrate10b8 / config.json
Tommert25's picture
Training in progress, epoch 1
bef1df6
{
"_name_or_path": "pdelobelle/robbert-v2-dutch-base",
"architectures": [
"RobertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "NAME",
"1": "OTH",
"2": "NL",
"3": "VAR",
"4": "ARAB",
"5": "ENG",
"6": "NON"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"ARAB": 4,
"ENG": 5,
"NL": 2,
"NON": 6,
"Name": 0,
"OTH": 1,
"VAR": 3
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.34.0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 40000
}