| { |
| "output_dir": "ckpts/discrim/contrastive_models/flan_t5_large_mathqa_max_margin_100K", |
| "overwrite_output_dir": false, |
| "do_train": false, |
| "do_eval": true, |
| "do_predict": false, |
| "evaluation_strategy": "steps", |
| "prediction_loss_only": true, |
| "per_device_train_batch_size": 8, |
| "per_device_eval_batch_size": 8, |
| "per_gpu_train_batch_size": null, |
| "per_gpu_eval_batch_size": null, |
| "gradient_accumulation_steps": 2, |
| "eval_accumulation_steps": null, |
| "eval_delay": 0, |
| "learning_rate": 6e-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": 10.0, |
| "max_steps": -1, |
| "lr_scheduler_type": "cosine_with_restarts", |
| "warmup_ratio": 0.06, |
| "warmup_steps": 0, |
| "log_level": "passive", |
| "log_level_replica": "warning", |
| "log_on_each_node": true, |
| "logging_dir": "ckpts/discrim/contrastive_models/flan_t5_large_mathqa_max_margin_100K/runs/May19_20-00-50_gl1518.arc-ts.umich.edu", |
| "logging_strategy": "steps", |
| "logging_first_step": false, |
| "logging_steps": 50, |
| "logging_nan_inf_filter": true, |
| "save_strategy": "steps", |
| "save_steps": 1000, |
| "save_total_limit": 3, |
| "save_safetensors": false, |
| "save_on_each_node": false, |
| "no_cuda": false, |
| "use_mps_device": false, |
| "seed": 7, |
| "data_seed": null, |
| "jit_mode_eval": false, |
| "use_ipex": false, |
| "bf16": true, |
| "fp16": false, |
| "fp16_opt_level": "O1", |
| "half_precision_backend": "cuda_amp", |
| "bf16_full_eval": false, |
| "fp16_full_eval": false, |
| "tf32": null, |
| "local_rank": 0, |
| "xpu_backend": null, |
| "tpu_num_cores": null, |
| "tpu_metrics_debug": false, |
| "debug": [], |
| "dataloader_drop_last": false, |
| "eval_steps": 1000, |
| "dataloader_num_workers": 0, |
| "past_index": -1, |
| "run_name": "ckpts/discrim/contrastive_models/flan_t5_large_mathqa_max_margin_100K", |
| "disable_tqdm": false, |
| "remove_unused_columns": true, |
| "label_names": null, |
| "load_best_model_at_end": true, |
| "metric_for_best_model": "loss", |
| "greater_is_better": false, |
| "ignore_data_skip": false, |
| "sharded_ddp": [], |
| "fsdp": [], |
| "fsdp_min_num_params": 0, |
| "fsdp_config": { |
| "fsdp_min_num_params": 0, |
| "xla": false, |
| "xla_fsdp_grad_ckpt": false |
| }, |
| "fsdp_transformer_layer_cls_to_wrap": null, |
| "deepspeed": null, |
| "label_smoothing_factor": 0.0, |
| "optim": "adamw_hf", |
| "optim_args": null, |
| "adafactor": false, |
| "group_by_length": false, |
| "length_column_name": "length", |
| "report_to": [ |
| "wandb" |
| ], |
| "ddp_find_unused_parameters": null, |
| "ddp_bucket_cap_mb": null, |
| "dataloader_pin_memory": true, |
| "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": false, |
| "gradient_checkpointing": false, |
| "include_inputs_for_metrics": false, |
| "fp16_backend": "auto", |
| "push_to_hub_model_id": null, |
| "push_to_hub_organization": null, |
| "push_to_hub_token": null, |
| "_n_gpu": 1, |
| "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, |
| "margin": 1.0, |
| "ckpt_dir": null, |
| "loss_type": "maxmargin", |
| "fix_tokenizer": false, |
| "dev_metric": "loss" |
| } |
