noahkim's picture
Training in progress, step 500
d11626c
raw
history blame
5.27 kB
{
"_commit_hash": null,
"_name_or_path": "/content/drive/MyDrive/project/kobigbird/first_model",
"add_cross_attention": true,
"architectures": [
"EncoderDecoderModel"
],
"attention_type": "original_full",
"decoder": {
"_name_or_path": "monologg/kobigbird-bert-base",
"add_cross_attention": true,
"architectures": [
"BigBirdForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"attention_type": "block_sparse",
"bad_words_ids": null,
"block_size": 64,
"bos_token_id": 5,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 6,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"gradient_checkpointing": false,
"hidden_act": "gelu_new",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": true,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 4096,
"min_length": 0,
"model_type": "big_bird",
"no_repeat_ngram_size": 0,
"num_attention_heads": 6,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 6,
"num_random_blocks": 3,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"rescale_embeddings": false,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": 3,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": "BertTokenizer",
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float32",
"torchscript": false,
"transformers_version": "4.22.0",
"type_vocab_size": 2,
"typical_p": 1.0,
"use_bfloat16": false,
"use_bias": true,
"use_cache": true,
"vocab_size": 32500
},
"decoder_layers": 6,
"decoder_start_token_id": 2,
"encoder": {
"_name_or_path": "monologg/kobigbird-bert-base",
"add_cross_attention": false,
"architectures": [
"BigBirdForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"attention_type": "block_sparse",
"bad_words_ids": null,
"block_size": 64,
"bos_token_id": 5,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 6,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"gradient_checkpointing": false,
"hidden_act": "gelu_new",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 4096,
"min_length": 0,
"model_type": "big_bird",
"no_repeat_ngram_size": 0,
"num_attention_heads": 6,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 6,
"num_random_blocks": 3,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"rescale_embeddings": false,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": 3,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": "BertTokenizer",
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float32",
"torchscript": false,
"transformers_version": "4.22.0",
"type_vocab_size": 2,
"typical_p": 1.0,
"use_bfloat16": false,
"use_bias": true,
"use_cache": true,
"vocab_size": 32500
},
"encoder_layers": 6,
"is_decoder": true,
"is_encoder_decoder": true,
"model_type": "encoder-decoder",
"num_attention_heads": 6,
"num_hidden_layers": 6,
"pad_token_id": 0,
"torch_dtype": "float32",
"transformers_version": null,
"vocab_size": 32500
}