ailab-bio/PROTAC-Splitter-EncoderDecoder-lr_cosine
07
1{2 "architectures": [3 "EncoderDecoderModel"4 ],5 "decoder": {6 "_name_or_path": "seyonec/ChemBERTa-zinc-base-v1",7 "add_cross_attention": true,8 "architectures": [9 "RobertaForMaskedLM"10 ],11 "attention_probs_dropout_prob": 0.1,12 "bad_words_ids": null,13 "begin_suppress_tokens": null,14 "bos_token_id": 0,15 "chunk_size_feed_forward": 0,16 "classifier_dropout": null,17 "cross_attention_hidden_size": null,18 "decoder_start_token_id": null,19 "diversity_penalty": 0.0,20 "do_sample": true,21 "early_stopping": false,22 "encoder_no_repeat_ngram_size": 0,23 "eos_token_id": 2,24 "exponential_decay_length_penalty": null,25 "finetuning_task": null,26 "forced_bos_token_id": null,27 "forced_eos_token_id": null,28 "hidden_act": "gelu",29 "hidden_dropout_prob": 0.1,30 "hidden_size": 768,31 "id2label": {32 "0": "LABEL_0",33 "1": "LABEL_1"34 },35 "initializer_range": 0.02,36 "intermediate_size": 3072,37 "is_decoder": true,38 "is_encoder_decoder": false,39 "label2id": {40 "LABEL_0": 0,41 "LABEL_1": 142 },43 "layer_norm_eps": 1e-05,44 "length_penalty": 1.0,45 "max_length": 512,46 "max_position_embeddings": 514,47 "min_length": 0,48 "model_type": "roberta",49 "no_repeat_ngram_size": 0,50 "num_attention_heads": 12,51 "num_beam_groups": 1,52 "num_beams": 5,53 "num_hidden_layers": 6,54 "num_return_sequences": 1,55 "output_attentions": false,56 "output_hidden_states": false,57 "output_past": true,58 "output_scores": false,59 "pad_token_id": 1,60 "position_embedding_type": "absolute",61 "prefix": null,62 "problem_type": null,63 "pruned_heads": {},64 "remove_invalid_values": false,65 "repetition_penalty": 1.0,66 "return_dict": true,67 "return_dict_in_generate": false,68 "sep_token_id": null,69 "suppress_tokens": null,70 "task_specific_params": null,71 "temperature": 1.0,72 "tf_legacy_loss": false,73 "tie_encoder_decoder": false,74 "tie_word_embeddings": true,75 "tokenizer_class": null,76 "top_k": 20,77 "top_p": 1.0,78 "torch_dtype": null,79 "torchscript": false,80 "type_vocab_size": 1,81 "typical_p": 1.0,82 "use_bfloat16": false,83 "use_cache": true,84 "vocab_size": 76785 },86 "decoder_start_token_id": 0,87 "do_sample": true,88 "encoder": {89 "_name_or_path": "seyonec/ChemBERTa-zinc-base-v1",90 "add_cross_attention": false,91 "architectures": [92 "RobertaForMaskedLM"93 ],94 "attention_probs_dropout_prob": 0.1,95 "bad_words_ids": null,96 "begin_suppress_tokens": null,97 "bos_token_id": 0,98 "chunk_size_feed_forward": 0,99 "classifier_dropout": null,100 "cross_attention_hidden_size": null,101 "decoder_start_token_id": null,102 "diversity_penalty": 0.0,103 "do_sample": true,104 "early_stopping": false,105 "encoder_no_repeat_ngram_size": 0,106 "eos_token_id": 2,107 "exponential_decay_length_penalty": null,108 "finetuning_task": null,109 "forced_bos_token_id": null,110 "forced_eos_token_id": null,111 "hidden_act": "gelu",112 "hidden_dropout_prob": 0.1,113 "hidden_size": 768,114 "id2label": {115 "0": "LABEL_0",116 "1": "LABEL_1"117 },118 "initializer_range": 0.02,119 "intermediate_size": 3072,120 "is_decoder": false,121 "is_encoder_decoder": false,122 "label2id": {123 "LABEL_0": 0,124 "LABEL_1": 1125 },126 "layer_norm_eps": 1e-05,127 "length_penalty": 1.0,128 "max_length": 512,129 "max_position_embeddings": 514,130 "min_length": 0,131 "model_type": "roberta",132 "no_repeat_ngram_size": 0,133 "num_attention_heads": 12,134 "num_beam_groups": 1,135 "num_beams": 5,136 "num_hidden_layers": 6,137 "num_return_sequences": 1,138 "output_attentions": false,139 "output_hidden_states": false,140 "output_past": true,141 "output_scores": false,142 "pad_token_id": 1,143 "position_embedding_type": "absolute",144 "prefix": null,145 "problem_type": null,146 "pruned_heads": {},147 "remove_invalid_values": false,148 "repetition_penalty": 1.0,149 "return_dict": true,150 "return_dict_in_generate": false,151 "sep_token_id": null,152 "suppress_tokens": null,153 "task_specific_params": null,154 "temperature": 1.0,155 "tf_legacy_loss": false,156 "tie_encoder_decoder": false,157 "tie_word_embeddings": true,158 "tokenizer_class": null,159 "top_k": 20,160 "top_p": 1.0,161 "torch_dtype": null,162 "torchscript": false,163 "type_vocab_size": 1,164 "typical_p": 1.0,165 "use_bfloat16": false,166 "use_cache": true,167 "vocab_size": 767168 },169 "eos_token_id": 2,170 "is_encoder_decoder": true,171 "max_length": 512,172 "model_type": "encoder-decoder",173 "num_beams": 5,174 "pad_token_id": 1,175 "top_k": 20,176 "torch_dtype": "float32",177 "transformers_version": "4.44.2",178 "vocab_size": 767179}180 