2021-02-13 14:58:05 +00:00
|
|
|
{
|
|
|
|
|
"_name_or_path": "/tmp/mnli_distil_output/checkpoint-6000",
|
|
|
|
|
"activation": "gelu",
|
|
|
|
|
"architectures": [
|
|
|
|
|
"DistilBertForSequenceClassification"
|
|
|
|
|
],
|
|
|
|
|
"attention_dropout": 0.1,
|
|
|
|
|
"dim": 768,
|
|
|
|
|
"dropout": 0.1,
|
|
|
|
|
"finetuning_task": "mnli",
|
|
|
|
|
"hidden_dim": 3072,
|
|
|
|
|
"id2label": {
|
2021-02-13 18:18:16 +00:00
|
|
|
"0": "CONTRADICTION",
|
|
|
|
|
"1": "NEUTRAL",
|
|
|
|
|
"2": "ENTAILMENT"
|
2021-02-13 14:58:05 +00:00
|
|
|
},
|
|
|
|
|
"initializer_range": 0.02,
|
|
|
|
|
"label2id": {
|
|
|
|
|
"LABEL_0": 0,
|
|
|
|
|
"LABEL_1": 1,
|
|
|
|
|
"LABEL_2": 2
|
|
|
|
|
},
|
|
|
|
|
"max_position_embeddings": 512,
|
|
|
|
|
"model_type": "distilbert",
|
|
|
|
|
"n_heads": 12,
|
|
|
|
|
"n_layers": 6,
|
|
|
|
|
"pad_token_id": 0,
|
|
|
|
|
"qa_dropout": 0.1,
|
|
|
|
|
"seq_classif_dropout": 0.2,
|
|
|
|
|
"sinusoidal_pos_embds": false,
|
|
|
|
|
"tie_weights_": true,
|
|
|
|
|
"transformers_version": "4.3.2",
|
|
|
|
|
"vocab_size": 30522,
|
|
|
|
|
"xla_device": true
|
|
|
|
|
}
|
