GPT-2-Base / config.json
stonedsmv's picture
Training in progress, epoch 1
879bc6f verified
{
"_name_or_path": "gpt2",
"activation_function": "gelu_new",
"architectures": [
"GPT2ForSequenceClassification"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"id2label": {
"0": "science/technology",
"1": "travel",
"2": "politics",
"3": "sports",
"4": "health",
"5": "entertainment",
"6": "geography"
},
"initializer_range": 0.02,
"label2id": {
"entertainment": 5,
"geography": 6,
"health": 4,
"politics": 2,
"science/technology": 0,
"sports": 3,
"travel": 1
},
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"problem_type": "single_label_classification",
"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": "4.44.0",
"use_cache": true,
"vocab_size": 50257
}