| wandb_version: 1 | |
| _wandb: | |
| desc: null | |
| value: | |
| cli_version: 0.10.33 | |
| framework: huggingface | |
| huggingface_version: 4.9.0.dev0 | |
| is_jupyter_run: false | |
| is_kaggle_kernel: false | |
| python_version: 3.8.10 | |
| t: | |
| 1: | |
| - 3 | |
| - 11 | |
| 2: | |
| - 3 | |
| - 11 | |
| 4: 3.8.10 | |
| 5: 0.10.33 | |
| 6: 4.9.0.dev0 | |
| 8: | |
| - 5 | |
| adafactor: | |
| desc: null | |
| value: true | |
| adam_beta1: | |
| desc: null | |
| value: 0.9 | |
| adam_beta2: | |
| desc: null | |
| value: 0.98 | |
| adam_epsilon: | |
| desc: null | |
| value: 1.0e-08 | |
| cache_dir: | |
| desc: null | |
| value: null | |
| config_name: | |
| desc: null | |
| value: ./ | |
| dataloader_drop_last: | |
| desc: null | |
| value: false | |
| dataloader_num_workers: | |
| desc: null | |
| value: 0 | |
| dataloader_pin_memory: | |
| desc: null | |
| value: true | |
| dataset_config_name: | |
| desc: null | |
| value: null | |
| dataset_name: | |
| desc: null | |
| value: null | |
| ddp_find_unused_parameters: | |
| desc: null | |
| value: null | |
| debug: | |
| desc: null | |
| value: [] | |
| deepspeed: | |
| desc: null | |
| value: null | |
| disable_tqdm: | |
| desc: null | |
| value: false | |
| do_eval: | |
| desc: null | |
| value: false | |
| do_predict: | |
| desc: null | |
| value: false | |
| do_train: | |
| desc: null | |
| value: false | |
| dtype: | |
| desc: null | |
| value: float32 | |
| eval_accumulation_steps: | |
| desc: null | |
| value: null | |
| eval_steps: | |
| desc: null | |
| value: 100001 | |
| evaluation_strategy: | |
| desc: null | |
| value: IntervalStrategy.NO | |
| fp16: | |
| desc: null | |
| value: false | |
| fp16_backend: | |
| desc: null | |
| value: auto | |
| fp16_full_eval: | |
| desc: null | |
| value: false | |
| fp16_opt_level: | |
| desc: null | |
| value: O1 | |
| gradient_accumulation_steps: | |
| desc: null | |
| value: 8 | |
| greater_is_better: | |
| desc: null | |
| value: null | |
| group_by_length: | |
| desc: null | |
| value: false | |
| ignore_data_skip: | |
| desc: null | |
| value: false | |
| label_names: | |
| desc: null | |
| value: null | |
| label_smoothing_factor: | |
| desc: null | |
| value: 0.0 | |
| learning_rate: | |
| desc: null | |
| value: 5.0e-05 | |
| length_column_name: | |
| desc: null | |
| value: length | |
| line_by_line: | |
| desc: null | |
| value: false | |
| load_best_model_at_end: | |
| desc: null | |
| value: false | |
| local_rank: | |
| desc: null | |
| value: -1 | |
| log_level: | |
| desc: null | |
| value: -1 | |
| log_level_replica: | |
| desc: null | |
| value: -1 | |
| log_on_each_node: | |
| desc: null | |
| value: true | |
| logging_dir: | |
| desc: null | |
| value: ./runs/Jul13_13-05-54_t1v-n-f5c06ea1-w-0 | |
| logging_first_step: | |
| desc: null | |
| value: false | |
| logging_steps: | |
| desc: null | |
| value: 500 | |
| logging_strategy: | |
| desc: null | |
| value: IntervalStrategy.STEPS | |
| lr_scheduler_type: | |
| desc: null | |
| value: SchedulerType.LINEAR | |
| max_grad_norm: | |
| desc: null | |
| value: 1.0 | |
| max_seq_length: | |
| desc: null | |
| value: 4096 | |
| max_steps: | |
| desc: null | |
| value: -1 | |
| metric_for_best_model: | |
| desc: null | |
| value: null | |
| mlm_probability: | |
| desc: null | |
| value: 0.15 | |
| model_name_or_path: | |
| desc: null | |
| value: null | |
| model_type: | |
| desc: null | |
| value: big_bird | |
| mp_parameters: | |
| desc: null | |
| value: '' | |
| no_cuda: | |
| desc: null | |
| value: false | |
| num_train_epochs: | |
| desc: null | |
| value: 5.0 | |
| output_dir: | |
| desc: null | |
| value: ./ | |
| overwrite_cache: | |
| desc: null | |
| value: false | |
| overwrite_output_dir: | |
| desc: null | |
| value: true | |
| pad_to_max_length: | |
| desc: null | |
| value: false | |
| past_index: | |
| desc: null | |
| value: -1 | |
| per_device_eval_batch_size: | |
| desc: null | |
| value: 2 | |
| per_device_train_batch_size: | |
| desc: null | |
| value: 2 | |
| per_gpu_eval_batch_size: | |
| desc: null | |
| value: null | |
| per_gpu_train_batch_size: | |
| desc: null | |
| value: null | |
| prediction_loss_only: | |
| desc: null | |
| value: false | |
| preprocessing_num_workers: | |
| desc: null | |
| value: 64 | |
| push_to_hub: | |
| desc: null | |
| value: true | |
| push_to_hub_model_id: | |
| desc: null | |
| value: '' | |
| push_to_hub_organization: | |
| desc: null | |
| value: null | |
| push_to_hub_token: | |
| desc: null | |
| value: null | |
| remove_unused_columns: | |
| desc: null | |
| value: true | |
| report_to: | |
| desc: null | |
| value: | |
| - tensorboard | |
| - wandb | |
| resume_from_checkpoint: | |
| desc: null | |
| value: null | |
| run_name: | |
| desc: null | |
| value: ./ | |
| save_on_each_node: | |
| desc: null | |
| value: false | |
| save_steps: | |
| desc: null | |
| value: 20000 | |
| save_strategy: | |
| desc: null | |
| value: IntervalStrategy.STEPS | |
| save_total_limit: | |
| desc: null | |
| value: 5 | |
| seed: | |
| desc: null | |
| value: 42 | |
| sharded_ddp: | |
| desc: null | |
| value: [] | |
| skip_memory_metrics: | |
| desc: null | |
| value: true | |
| tokenizer_name: | |
| desc: null | |
| value: ./ | |
| tpu_metrics_debug: | |
| desc: null | |
| value: false | |
| tpu_num_cores: | |
| desc: null | |
| value: null | |
| train_file: | |
| desc: null | |
| value: null | |
| train_ref_file: | |
| desc: null | |
| value: null | |
| use_fast_tokenizer: | |
| desc: null | |
| value: true | |
| use_legacy_prediction_loop: | |
| desc: null | |
| value: false | |
| validation_file: | |
| desc: null | |
| value: null | |
| validation_ref_file: | |
| desc: null | |
| value: null | |
| validation_split_percentage: | |
| desc: null | |
| value: 5 | |
| warmup_ratio: | |
| desc: null | |
| value: 0.0 | |
| warmup_steps: | |
| desc: null | |
| value: 10 | |
| weight_decay: | |
| desc: null | |
| value: 0.0095 | |