| { | |
| "_name_or_path": "/cognitive_comp/dongxiaoqun/train_model/pretrain_deltalm_parallel_labels100_3node_2B_new1/ckpt/pretrained_epoch0_step29425/", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "add_bias_logits": false, | |
| "add_final_layer_norm": false, | |
| "architectures": [ | |
| "DeltalmForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "classifier_dropout": 0.0, | |
| "d_model": 768, | |
| "decoder_attention_heads": 12, | |
| "decoder_ffn_dim": 3072, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 6, | |
| "decoder_start_token_id": 2, | |
| "dropout": 0.1, | |
| "early_stopping": true, | |
| "encoder_attention_heads": 12, | |
| "encoder_ffn_dim": 3072, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 12, | |
| "encoder_normalize_before": false, | |
| "eos_token_id": 2, | |
| "forced_bos_token_id": 0, | |
| "forced_eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "ignore_index": -100, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "max_length": 512, | |
| "max_position_embeddings": 512, | |
| "model_type": "Deltalm", | |
| "no_repeat_ngram_size": 3, | |
| "normalize_before": false, | |
| "num_beams": 5, | |
| "num_hidden_layers": 6, | |
| "pad_token_id": 1, | |
| "scale_embedding": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.20.1", | |
| "use_cache": true, | |
| "vocab_size": 250001 | |
| } | |