poteminr's picture
Training in progress, epoch 1
f74fa76 verified
{
"_name_or_path": "Tochka-AI/ruRoPEBert-classic-base-2k",
"architectures": [
"RoPEBertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"auto_map": {
"AutoConfig": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertConfig",
"AutoModel": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertModel",
"AutoModelForMaskedLM": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertForMaskedLM",
"AutoModelForSequenceClassification": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertForSequenceClassification"
},
"classifier_dropout": null,
"directionality": "bidi",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "common",
"1": "toxic"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"common": 0,
"toxic": 1
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 2048,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_type": "mean",
"problem_type": "single_label_classification",
"rope_scaling": null,
"rope_theta": 10000.0,
"torch_dtype": "float32",
"transformers_version": "4.44.2",
"type_vocab_size": 2,
"vocab_size": 120138
}