dominguesm's picture
Training in progress, epoch 1
22d9c44
{
"_name_or_path": "xlm-roberta-base",
"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": 768,
"id2label": {
"0": "ar",
"1": "bg",
"2": "de",
"3": "el",
"4": "en",
"5": "es",
"6": "fr",
"7": "hi",
"8": "it",
"9": "ja",
"10": "nl",
"11": "pl",
"12": "pt",
"13": "ru",
"14": "sw",
"15": "th",
"16": "tr",
"17": "ur",
"18": "vi",
"19": "zh"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"ar": 0,
"bg": 1,
"de": 2,
"el": 3,
"en": 4,
"es": 5,
"fr": 6,
"hi": 7,
"it": 8,
"ja": 9,
"nl": 10,
"pl": 11,
"pt": 12,
"ru": 13,
"sw": 14,
"th": 15,
"tr": 16,
"ur": 17,
"vi": 18,
"zh": 19
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.27.0.dev0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}