cointegrated's picture
The second commit: train longer
7dfbda7
{
"_name_or_path": "/gd/MyDrive/models/rubert-tiny-nli-twoway",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"emb_size": 312,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 312,
"id2label": {
"0": "not_entailment",
"1": "entailment"
},
"initializer_range": 0.02,
"intermediate_size": 600,
"label2id": {
"entailment": 1,
"not_entailment": 0
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 3,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.11.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 29564
}