philschmid's picture
philschmid HF staff
Training in progress, epoch 1
1388447
{
"_name_or_path": "xlm-roberta-large",
"architectures": [
"XLMRobertaForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "social",
"1": "transport",
"10": "audio",
"11": "lists",
"12": "qa",
"13": "cooking",
"14": "takeaway",
"15": "music",
"16": "alarm",
"17": "weather",
"2": "calendar",
"3": "play",
"4": "news",
"5": "datetime",
"6": "recommendation",
"7": "email",
"8": "iot",
"9": "general"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"alarm": "16",
"audio": "10",
"calendar": "2",
"cooking": "13",
"datetime": "5",
"email": "7",
"general": "9",
"iot": "8",
"lists": "11",
"music": "15",
"news": "4",
"play": "3",
"qa": "12",
"recommendation": "6",
"social": "0",
"takeaway": "14",
"transport": "1",
"weather": "17"
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.17.0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}