DerivedFunction1's picture
Training in progress, step 1000
9278f62
Raw
History Blame Contribute Delete
889 Bytes
{
"add_cross_attention": false,
"architectures": [
"RobertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"dtype": "float32",
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "B-NEG",
"2": "I-NEG",
"3": "B-POS",
"4": "I-POS"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"label2id": {
"B-NEG": 1,
"B-POS": 3,
"I-NEG": 2,
"I-POS": 4,
"O": 0
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"tie_word_embeddings": true,
"transformers_version": "5.9.0",
"type_vocab_size": 1,
"use_cache": false,
"vocab_size": 50265
}