| { |
| "max_seq_length": 256, |
| "question_max_seq_length": 256, |
| "RC": false, |
| "coco": false, |
| "flickr": false, |
| "aokvqa": false, |
| "grad_check": true, |
| "MJL": false, |
| "debug_run_time": false, |
| "debug_output": false, |
| "only_neighbors": false, |
| "full_kb": false, |
| "image_eval": false, |
| "embedding_column": "my_DPR_few_shot", |
| "output_ds": null, |
| "output_kb": null, |
| "embed": false, |
| "data_path": null, |
| "train_batch_size": 1, |
| "eval_batch_size": 1, |
| "viquae_dev_batch_size": 1000, |
| "transformer_model_name": "bert-base-uncased", |
| "gradient_accumulation_steps": 1, |
| "warmup_proportion": 0.1, |
| "weight_decay": 0.01, |
| "lr_decay": false, |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.999, |
| "warmup_steps": 4, |
| "adam_epsilon": 1e-08, |
| "num_train_epochs": 20, |
| "learning_rate": 5e-06, |
| "dropout": 0.5, |
| "bert_hidden_size": 768, |
| "MM": null, |
| "use_graph_P": null, |
| "use_graph_Q": null, |
| "syntactic_P": null, |
| "syntactic_Q": null, |
| "NS": false, |
| "IC_Q": false, |
| "IC_P": false, |
| "gcn_lr": 2e-05, |
| "clip_lr": null, |
| "dpr_lr": null, |
| "head_lr": 2e-06, |
| "func": "cat", |
| "graph_pooling": "mean", |
| "max_nbr_nodes": 2, |
| "num_neib": 1, |
| "neib_depth": 1, |
| "undirect": false, |
| "node_hidden_size": 128, |
| "max_num_relations": null, |
| "max_num_syntactic_relations": null, |
| "map_wikidataRelCode_to_idx": null, |
| "graph_layout": "fr", |
| "residual": false, |
| "num_gcn": null, |
| "node_alias_max_len": 32, |
| "attention": false, |
| "num_paths": 1, |
| "kg_embed": false, |
| "graph_only": false, |
| "freeze": false, |
| "sanity_run": false, |
| "scale_losses": false, |
| "check_answers": false, |
| "load_4bit": false, |
| "load_8bit": false, |
| "device_id": null, |
| "drop_last": false, |
| "disable_checkpointing": false, |
| "samples": null, |
| "sample_id": null, |
| "datasets_root_dir": "../datasets", |
| "ds": "../datasets/textee/wikievents", |
| "supp_train_ds": null, |
| "guidelines": "new_Llama-31-8B-Instruct_annotation_guidelines", |
| "num_trainable_params": null, |
| "num_all_param": null, |
| "trainable_ratio": null, |
| "train_sanity_run": false, |
| "enhanced_question": false, |
| "use_entity_type": false, |
| "filter_edges": false, |
| "draw": false, |
| "layer_norm": false, |
| "filters_3": 768, |
| "tensor_neurons": 16, |
| "output_dir": "saved_models/wikievents/GoLLIE-7B/code_generator/train/2025-09-26/19-34-03", |
| "main_dir": "/fscratch/oadjali/EEE", |
| "experiment_dir": "/fscratch/oadjali/EEE/saved_models/wikievents/GoLLIE-7B/code_generator/train/2025-09-26/19-34-03", |
| "experiment_name": null, |
| "search": null, |
| "input_key": null, |
| "train_input_key": null, |
| "train_search_run": null, |
| "val_search_run": null, |
| "test_search_run": null, |
| "no_resize": false, |
| "xlnet": false, |
| "tune_loss": false, |
| "tune_dev": true, |
| "tune_valid_loss": false, |
| "sanity_val_steps": 0, |
| "cpu": false, |
| "keep_in_memory": false, |
| "nbr_gpus": 1, |
| "N": 0, |
| "nbr_workers": 1, |
| "num_proc": 1, |
| "acc": "gpu", |
| "fast_dev_run": null, |
| "local_cache": "../my_transformers_cache", |
| "IMAGE_PATH": null, |
| "transformer_path": null, |
| "resume_from": null, |
| "answer_generator": "HiTZ/GoLLIE-7B", |
| "query_model": null, |
| "context_model": null, |
| "answer_generator_2": null, |
| "checkpoint": null, |
| "query_checkpoint": null, |
| "checkpoint_2": null, |
| "non_strict_load": true, |
| "trainer_checkpoint": null, |
| "linear_MEP_checkpoint": null, |
| "linear_MLM_checkpoint": null, |
| "config": "experiments/event_extraction/config_code_generator.json", |
| "context_checkpoint": null, |
| "grad_accum": 1, |
| "cls_token": "[CLS]", |
| "sep_token": "[SEP]", |
| "pad_token": "[PAD]", |
| "cls_token_at_end": false, |
| "mask_padding_with_zero": true, |
| "pad_on_left": false, |
| "sequence_a_segment_id": 0, |
| "pad_token_segment_id": 0, |
| "cls_token_segment_id": 0, |
| "pad_token_label_id": 0, |
| "pad_token_id": 0, |
| "past_index": -1, |
| "world_size": 1, |
| "use_lstm": false, |
| "use_entity": false, |
| "use_question_graph": false, |
| "use_question_objects": false, |
| "EFeat": null, |
| "NFeat": null, |
| "ltn": false, |
| "use_kelm": false, |
| "unshared": false, |
| "mlm": false, |
| "test": false, |
| "validate": false, |
| "eval_on_start": false, |
| "predict": null, |
| "split_dpr": false, |
| "rename_model": false, |
| "mask_rate": 0.15, |
| "pretrained_triviaq": false, |
| "error_analysis": false, |
| "debug": false, |
| "stop_debug": false, |
| "entity_linking": false, |
| "entity_linking_split": false, |
| "build_entity_paths": null, |
| "object_detection": null, |
| "update_wikidata_ids": null, |
| "update_None_ids": null, |
| "dependency_parsing": null, |
| "image_captionning": null, |
| "build_graph": false, |
| "from_bert": false, |
| "fast": false, |
| "get_examples": false, |
| "get_statistics": null, |
| "word_vocab_size": 0, |
| "char_vocab_size": 0, |
| "max_word_len": 30, |
| "device": "cuda", |
| "embedding_matrix": null, |
| "new_vocab_embeddings": null, |
| "w2v_file": "word_vector_200d.vec", |
| "word_emb_dim": 200, |
| "char_lstm": false, |
| "char_cnn": false, |
| "seed": 42, |
| "tune_batch_size": false, |
| "val_check_interval": null, |
| "model_names": null, |
| "build_hf_local_cache": true, |
| "strategy": null, |
| "monitor_metric": "mean_f1", |
| "precision": 32, |
| "no_lora": false, |
| "early_stopping": true, |
| "reduce_on_plateau": true, |
| "num_generations": 2, |
| "num_passages": 5, |
| "k_schemes": 10, |
| "use_liger_loss": false, |
| "kl_beta": 0.0, |
| "TI_alpha": 1.0, |
| "TC_alpha": 1.0, |
| "AI_alpha": 1.0, |
| "AC_alpha": 1.0, |
| "schema_retrieval_val": false, |
| "schema_retrieval_train": false, |
| "EE_2steps": false, |
| "EE_SL": false, |
| "save_ckpt": false, |
| "lora_config": { |
| "peft_type": "LORA", |
| "auto_mapping": null, |
| "base_model_name_or_path": null, |
| "revision": null, |
| "task_type": "CAUSAL_LM", |
| "inference_mode": false, |
| "r": 8, |
| "target_modules": [ |
| "q_proj", |
| "v_proj" |
| ], |
| "lora_alpha": 16, |
| "lora_dropout": 0.05, |
| "fan_in_fan_out": false, |
| "bias": "none", |
| "use_rslora": false, |
| "modules_to_save": null, |
| "init_lora_weights": true, |
| "layers_to_transform": null, |
| "layers_pattern": null, |
| "rank_pattern": {}, |
| "alpha_pattern": {}, |
| "megatron_config": null, |
| "megatron_core": "megatron.core", |
| "loftq_config": {}, |
| "use_dora": false |
| }, |
| "quantization_config": null, |
| "hf": false, |
| "slurm_scipt_path": null, |
| "enabled_args": " --train_batch_size 1\n --eval_batch_size 1\n --num_train_epochs 20\n --nbr_gpus 1\n --learning_rate 5e-6\n --grad_check\n --config experiments/event_extraction/config_code_generator.json\n --non_strict_load\n --ds ../datasets/textee/wikievents\n --answer_generator HiTZ/GoLLIE-7B\n --guidelines new_Llama-31-8B-Instruct_annotation_guidelines\n --k_schemes 10\n --num_passages 5" |
| } |
