calculator_model_test / config.json
macbeeth's picture
Training in progress, step 240
672f28d verified
{
"architectures": [
"EncoderDecoderModel"
],
"decoder": {
"_name_or_path": "",
"add_cross_attention": true,
"architectures": null,
"attention_probs_dropout_prob": 0.1,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"dtype": null,
"eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 256,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 1024,
"is_decoder": true,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 4,
"num_hidden_layers": 4,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"problem_type": null,
"return_dict": true,
"tie_word_embeddings": true,
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 52
},
"decoder_start_token_id": 2,
"dtype": "float32",
"encoder": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_probs_dropout_prob": 0.1,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"dtype": null,
"eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 256,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 1024,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 4,
"num_hidden_layers": 4,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"problem_type": null,
"return_dict": true,
"tie_word_embeddings": true,
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 52
},
"eos_token_id": 0,
"is_encoder_decoder": true,
"model_type": "encoder-decoder",
"pad_token_id": 3,
"transformers_version": "5.2.0",
"unk_token_id": null,
"use_cache": false
}