daisyshim's picture
Training completed!
868e898
raw
history blame
1.57 kB
{
"_name_or_path": "skt/kogpt2-base-v2",
"_num_labels": 1,
"activation_function": "gelu_new",
"architectures": [
"GPT2ForTokenClassification"
],
"attn_pdrop": 0.1,
"author": "Heewon Jeon(madjakarta@gmail.com)",
"bos_token_id": 0,
"created_date": "2021-04-28",
"embd_pdrop": 0.1,
"eos_token_id": 1,
"gradient_checkpointing": false,
"id2label": {
"0": "B-DT",
"1": "I-DT",
"2": "B-LC",
"3": "I-LC",
"4": "B-OG",
"5": "I-OG",
"6": "B-PS",
"7": "I-PS",
"8": "B-QT",
"9": "I-QT",
"10": "B-TI",
"11": "I-TI",
"12": "O"
},
"initializer_range": 0.02,
"label2id": {
"B-DT": 0,
"B-LC": 2,
"B-OG": 4,
"B-PS": 6,
"B-QT": 8,
"B-TI": 10,
"I-DT": 1,
"I-LC": 3,
"I-OG": 5,
"I-PS": 7,
"I-QT": 9,
"I-TI": 11,
"O": 12
},
"layer_norm_epsilon": 1e-05,
"license": "CC-BY-NC-SA 4.0",
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 3,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"torch_dtype": "float32",
"transformers_version": "4.28.1",
"use_cache": true,
"vocab_size": 51200
}