| { | |
| "_name_or_path": "/home/xinyu402/projects/rrg-bengioy-ad/xinyu402/scZero_ckpts/240202_181731/checkpoint-40000", | |
| "architectures": [ | |
| "PrototypeContrastiveForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.02, | |
| "bert_objective": "plm", | |
| "classifier_dropout": null, | |
| "contrastive_dropout": null, | |
| "data_branch": "frac100", | |
| "gradient_checkpointing": false, | |
| "hidden_act": "relu", | |
| "hidden_dropout_prob": 0.02, | |
| "hidden_size": 256, | |
| "initialize_decoder_as_identity": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 512, | |
| "layer_norm_eps": 1e-12, | |
| "learnable_logits_scale": null, | |
| "max_length": null, | |
| "max_position_embeddings": 2048, | |
| "min_position": null, | |
| "model_type": "bert", | |
| "moving_avg_ratio": 0.9, | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 6, | |
| "output_hidden_states": true, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "scale_grad_by_freq": true, | |
| "tau": 0.01, | |
| "tie_word_embeddings": 0, | |
| "torch_dtype": "float32", | |
| "total_logging_steps": 40, | |
| "transformers_version": "4.32.1", | |
| "truth_use_decoder": null, | |
| "type_vocab_size": null, | |
| "use_abspos_embed": true, | |
| "use_cache": true, | |
| "vocab_size": 25427 | |
| } | |