| { |
| "model_args": { |
| "model_name_or_path": "BAAI/bge-reranker-v2-m3", |
| "num_labels": null, |
| "classifier_dropout": 0.1, |
| "max_length": 512, |
| "config_name": null, |
| "tokenizer_name": null, |
| "cache_dir": null |
| }, |
| "data_args": { |
| "dataset_name": "hotchpotch/wip-msmarco-context-relevance", |
| "subset": "msmarco-ja-minimal", |
| "teacher_column": null, |
| "datasets": [ |
| { |
| "dataset_name": "hotchpotch/msmarco-context-relevance", |
| "subset": "freq2", |
| "teacher_column": "teacher_scores.gte-reranker-modernbert-base" |
| }, |
| { |
| "dataset_name": "hotchpotch/natural-questions-context-relevance", |
| "subset": "nodup_freq2", |
| "teacher_column": "teacher_scores.gte-reranker-modernbert-base", |
| "items": 6 |
| }, |
| { |
| "dataset_name": "hotchpotch/gooaq-context-relevance-130k", |
| "subset": "default", |
| "teacher_column": "teacher_scores.gte-reranker-modernbert-base", |
| "items": 6 |
| }, |
| { |
| "dataset_name": "zc277584121/dureader-context-relevance-with-think", |
| "subset": "default" |
| }, |
| { |
| "dataset_name": "zc277584121/chinese_wiki_0_300k-context-relevance-with-think", |
| "subset": "default" |
| } |
| ], |
| "items": null, |
| "max_train_samples": null, |
| "max_eval_samples": null, |
| "validation_split": null, |
| "validation_split_samples": null, |
| "validation_split_name": "validation", |
| "preprocessing_num_workers": null, |
| "filter_zero_relevance_max_items": null, |
| "filter_zero_relevance_max_items_reverse": false, |
| "filter_keep_first_item": false, |
| "upsample_factor": null |
| }, |
| "training_args": { |
| "output_dir": "./output/bilingual-chinese-english-m3-v10_20251213_152447", |
| "overwrite_output_dir": true, |
| "do_train": true, |
| "do_eval": true, |
| "do_predict": false, |
| "eval_strategy": "steps", |
| "prediction_loss_only": false, |
| "per_device_train_batch_size": 2, |
| "per_device_eval_batch_size": 8, |
| "per_gpu_train_batch_size": null, |
| "per_gpu_eval_batch_size": null, |
| "gradient_accumulation_steps": 32, |
| "eval_accumulation_steps": null, |
| "eval_delay": 0, |
| "torch_empty_cache_steps": null, |
| "learning_rate": 5e-05, |
| "weight_decay": 0.01, |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.999, |
| "adam_epsilon": 1e-08, |
| "max_grad_norm": 1.0, |
| "num_train_epochs": 3, |
| "max_steps": -1, |
| "lr_scheduler_type": "cosine", |
| "lr_scheduler_kwargs": {}, |
| "warmup_ratio": 0.1, |
| "warmup_steps": 0, |
| "log_level": "passive", |
| "log_level_replica": "warning", |
| "log_on_each_node": true, |
| "logging_dir": "trainer_output/runs/Dec13_15-24-45_nvidiadgx", |
| "logging_strategy": "steps", |
| "logging_first_step": false, |
| "logging_steps": 363, |
| "logging_nan_inf_filter": true, |
| "save_strategy": "steps", |
| "save_steps": 500, |
| "save_total_limit": 3, |
| "save_safetensors": true, |
| "save_on_each_node": false, |
| "save_only_model": false, |
| "restore_callback_states_from_checkpoint": false, |
| "no_cuda": false, |
| "use_cpu": false, |
| "use_mps_device": false, |
| "seed": 42, |
| "data_seed": null, |
| "jit_mode_eval": false, |
| "bf16": true, |
| "fp16": false, |
| "fp16_opt_level": "O1", |
| "half_precision_backend": "auto", |
| "bf16_full_eval": false, |
| "fp16_full_eval": false, |
| "tf32": null, |
| "local_rank": 7, |
| "ddp_backend": null, |
| "tpu_num_cores": null, |
| "tpu_metrics_debug": false, |
| "debug": [], |
| "dataloader_drop_last": false, |
| "eval_steps": 1815, |
| "dataloader_num_workers": 4, |
| "dataloader_prefetch_factor": null, |
| "past_index": -1, |
| "run_name": "bilingual-chinese-english-m3-v10-20251213_152447", |
| "disable_tqdm": false, |
| "remove_unused_columns": false, |
| "label_names": null, |
| "load_best_model_at_end": true, |
| "metric_for_best_model": "eval_loss", |
| "greater_is_better": false, |
| "ignore_data_skip": false, |
| "fsdp": [], |
| "fsdp_min_num_params": 0, |
| "fsdp_config": { |
| "min_num_params": 0, |
| "xla": false, |
| "xla_fsdp_v2": false, |
| "xla_fsdp_grad_ckpt": false |
| }, |
| "fsdp_transformer_layer_cls_to_wrap": null, |
| "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)", |
| "parallelism_config": null, |
| "deepspeed": null, |
| "label_smoothing_factor": 0.0, |
| "optim": "adafactor", |
| "optim_args": null, |
| "adafactor": false, |
| "group_by_length": false, |
| "length_column_name": "length", |
| "report_to": [ |
| "wandb" |
| ], |
| "project": "huggingface", |
| "trackio_space_id": "trackio", |
| "ddp_find_unused_parameters": null, |
| "ddp_bucket_cap_mb": null, |
| "ddp_broadcast_buffers": null, |
| "dataloader_pin_memory": true, |
| "dataloader_persistent_workers": false, |
| "skip_memory_metrics": true, |
| "use_legacy_prediction_loop": false, |
| "push_to_hub": false, |
| "resume_from_checkpoint": null, |
| "hub_model_id": null, |
| "hub_strategy": "every_save", |
| "hub_token": null, |
| "hub_private_repo": null, |
| "hub_always_push": false, |
| "hub_revision": null, |
| "gradient_checkpointing": false, |
| "gradient_checkpointing_kwargs": null, |
| "include_inputs_for_metrics": false, |
| "include_for_metrics": [], |
| "eval_do_concat_batches": true, |
| "fp16_backend": "auto", |
| "push_to_hub_model_id": null, |
| "push_to_hub_organization": null, |
| "push_to_hub_token": null, |
| "mp_parameters": "", |
| "auto_find_batch_size": false, |
| "full_determinism": false, |
| "torchdynamo": null, |
| "ray_scope": "last", |
| "ddp_timeout": 1800, |
| "torch_compile": false, |
| "torch_compile_backend": null, |
| "torch_compile_mode": null, |
| "include_tokens_per_second": false, |
| "include_num_input_tokens_seen": "no", |
| "neftune_noise_alpha": null, |
| "optim_target_modules": null, |
| "batch_eval_metrics": false, |
| "eval_on_start": false, |
| "use_liger_kernel": false, |
| "liger_kernel_config": null, |
| "eval_use_gather_object": false, |
| "average_tokens_across_devices": true, |
| "ranking_weight": 0.0, |
| "pruning_weight": 1.0, |
| "use_teacher_scores": true, |
| "sentence_level_pruning": true, |
| "eval_datasets": { |
| "config": "configs/eval_datasets/bilingual_nano.yaml", |
| "threshold": 0.1, |
| "batch_size": 32 |
| }, |
| "distributed_state": "Distributed environment: DistributedType.MULTI_GPU Backend: nccl\nNum processes: 8\nProcess index: 7\nLocal process index: 7\nDevice: cuda:7\n", |
| "deepspeed_plugin": null |
| } |
| } |
