{ "data_args": { "append_eos_token": false, "assets_path": null, "concat_query": false, "corpus_config": null, "corpus_name": "DylanJHJ/crux-researchy-corpus", "corpus_path": null, "corpus_split": "train", "dataset_cache_dir": null, "dataset_config": null, "dataset_name": "DylanJHJ/crux-researchy-kdnew-ext", "dataset_number_of_shards": 1, "dataset_path": null, "dataset_shard_index": 0, "dataset_split": "pos_half.neu_low.neg_zero", "encode_audio": true, "encode_image": true, "encode_is_query": false, "encode_output_path": null, "encode_text": true, "encode_video": true, "eval_corpus_name": null, "eval_dataset_name": null, "eval_dataset_split": null, "eval_group_size": 32, "exclude_title": true, "negative_passage_no_shuffle": false, "num_proc": 1, "pad_to_multiple_of": 16, "padding_side": "right", "passage_max_len": 512, "passage_prefix": "search_document: ", "positive_passage_no_shuffle": false, "query_max_len": 180, "query_postfix": "", "query_prefix": "search_query: ", "request_as_query": true, "subquery_prefix": "search_query: ", "train_group_size": 8, "train_irrelevant_size": 0, "train_yaml": null }, "model_args": { "attn_implementation": "flash_attention_2", "cache_dir": null, "config_name": null, "dtype": "float16", "lora": false, "lora_alpha": 64, "lora_dropout": 0.1, "lora_name_or_path": null, "lora_r": 16, "lora_target_modules": "q_proj,k_proj,v_proj,o_proj,down_proj,up_proj,gate_proj", "model_name_or_path": "nomic-ai/modernbert-embed-base-unsupervised", "normalize": true, "num_views": 0, "pooling": "mean", "temperature": 0.02, "tokenizer_name": null, "view_pooling": "independent", "view_start_idx": 5 }, "training_args": { "_n_gpu": 1, "accelerator_config": { "dispatch_batches": null, "even_batches": true, "gradient_accumulation_kwargs": null, "non_blocking": false, "split_batches": false, "use_configured_state": false, "use_seedable_sampler": true }, "adafactor": false, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "aggregation_strategy": "sum", "auto_find_batch_size": false, "average_tokens_across_devices": true, "batch_eval_metrics": false, "bf16": true, "bf16_full_eval": false, "contrastive_lambda": 1.0, "covdistil_lambda": 0.1, "covdistil_method": "KLD", "data_seed": null, "dataloader_drop_last": false, "dataloader_num_workers": 8, "dataloader_persistent_workers": false, "dataloader_pin_memory": true, "dataloader_prefetch_factor": null, "ddp_backend": null, "ddp_broadcast_buffers": null, "ddp_bucket_cap_mb": null, "ddp_find_unused_parameters": null, "ddp_timeout": 1800, "debug": [], "deepspeed": null, "disable_tqdm": false, "distil_temperature": 0.02, "do_eval": false, "do_predict": false, "do_train": false, "eval_accumulation_steps": null, "eval_delay": 0, "eval_do_concat_batches": true, "eval_on_start": false, "eval_steps": 500.0, "eval_strategy": "no", "eval_use_gather_object": false, "fp16": false, "fp16_backend": "auto", "fp16_full_eval": false, "fp16_opt_level": "O1", "fsdp": [], "fsdp_config": { "min_num_params": 0, "xla": false, "xla_fsdp_grad_ckpt": false, "xla_fsdp_v2": false }, "fsdp_min_num_params": 0, "fsdp_transformer_layer_cls_to_wrap": null, "full_determinism": false, "gc_p_chunk_size": 32, "gc_q_chunk_size": 4, "grad_cache": false, "gradient_accumulation_steps": 1, "gradient_checkpointing": false, "gradient_checkpointing_kwargs": null, "greater_is_better": null, "group_by_length": false, "half_precision_backend": "auto", "hub_always_push": false, "hub_model_id": null, "hub_private_repo": null, "hub_revision": null, "hub_strategy": "every_save", "hub_token": null, "ignore_data_skip": false, "include_for_metrics": [], "include_inputs_for_metrics": false, "include_num_input_tokens_seen": "no", "include_tokens_per_second": false, "jit_mode_eval": false, "label_names": null, "label_smoothing_factor": 0.0, "learning_rate": 0.0001, "length_column_name": "length", "liger_kernel_config": null, "load_best_model_at_end": false, "local_rank": 1, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "/users/judylan1/models/CoveR/unsupervised.scope-5k/runs/Apr29_21-25-08_nid007854", "logging_first_step": false, "logging_nan_inf_filter": true, "logging_steps": 10, "logging_strategy": "steps", "lr_scheduler_kwargs": {}, "lr_scheduler_type": "cosine", "max_grad_norm": 1.0, "max_steps": 5000, "metric_for_best_model": null, "mp_parameters": "", "neftune_noise_alpha": null, "no_cuda": false, "num_train_epochs": 3.0, "optim": "adamw_torch", "optim_args": null, "optim_target_modules": null, "output_dir": "/users/judylan1/models/CoveR/unsupervised.scope-5k", "overwrite_output_dir": true, "parallelism_config": null, "past_index": -1, "per_device_eval_batch_size": 8, "per_device_train_batch_size": 16, "per_gpu_eval_batch_size": null, "per_gpu_train_batch_size": null, "prediction_loss_only": true, "project": "huggingface", "push_to_hub": false, "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": null, "ray_scope": "last", "remove_unused_columns": true, "report_to": [ "tensorboard", "wandb" ], "restore_callback_states_from_checkpoint": false, "resume_from_checkpoint": null, "run_name": "unsupervised.scope-5k", "save_on_each_node": false, "save_only_model": false, "save_safetensors": true, "save_steps": 1000, "save_strategy": "steps", "save_total_limit": null, "seed": 42, "skip_memory_metrics": true, "sq_contrastive_lambda": 0.0, "tf32": null, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "torch_empty_cache_steps": null, "torchdynamo": null, "tpu_metrics_debug": false, "tpu_num_cores": null, "trackio_space_id": "trackio", "use_cpu": false, "use_crossentropy": 1.0, "use_kld": 0.0, "use_legacy_prediction_loop": false, "use_liger_kernel": false, "use_mps_device": false, "view_orthogonalize_lambda": 0.0, "view_orthogonalize_method": null, "warmup_ratio": 0.1, "warmup_steps": 500, "weight_decay": 0.01 } }