squadtrainTraXLv1-1 / config.json
Wonder-Griffin's picture
Training in progress, step 500
cd80e4b verified
{
"_name_or_path": "Wonder-Griffin/squadtrainTraXL",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dropout": 0.1,
"dynamic_routing": true,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"ff_expansion_factor": 4,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4"
},
"initializer_range": 0.02,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4
},
"layer_norm_epsilon": 1e-05,
"max_computation_steps": 5,
"max_len": 256,
"memory_size": 256,
"model_type": "gpt2",
"n_embd": 128,
"n_head": 4,
"n_inner": null,
"n_layer": 4,
"n_positions": 1024,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"rnn_units": 128,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"sparse_attention": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 60000
}