training_args.json

{
  "output_dir": "/kaggle/working/muril_multilang_out",
  "overwrite_output_dir": false,
  "do_train": false,
  "do_eval": false,
  "do_predict": false,
  "eval_strategy": "no",
  "prediction_loss_only": false,
  "per_device_train_batch_size": 8,
  "per_device_eval_batch_size": 8,
  "per_gpu_train_batch_size": "None",
  "per_gpu_eval_batch_size": "None",
  "gradient_accumulation_steps": 2,
  "eval_accumulation_steps": "None",
  "eval_delay": 0,
  "torch_empty_cache_steps": "None",
  "learning_rate": 0.0002,
  "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": "linear",
  "lr_scheduler_kwargs": "{}",
  "warmup_ratio": 0.0,
  "warmup_steps": 0,
  "log_level": "passive",
  "log_level_replica": "warning",
  "log_on_each_node": true,
  "logging_dir": "/kaggle/working/muril_multilang_out/runs/Nov07_14-30-16_fa2705e791ab",
  "logging_strategy": "steps",
  "logging_first_step": false,
  "logging_steps": 50,
  "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": "None",
  "jit_mode_eval": false,
  "bf16": false,
  "fp16": true,
  "fp16_opt_level": "O1",
  "half_precision_backend": "auto",
  "bf16_full_eval": false,
  "fp16_full_eval": false,
  "tf32": "None",
  "local_rank": 0,
  "ddp_backend": "None",
  "tpu_num_cores": "None",
  "tpu_metrics_debug": false,
  "debug": "[]",
  "dataloader_drop_last": false,
  "eval_steps": "None",
  "dataloader_num_workers": 2,
  "dataloader_prefetch_factor": "None",
  "past_index": -1,
  "run_name": "None",
  "disable_tqdm": false,
  "remove_unused_columns": true,
  "label_names": "None",
  "load_best_model_at_end": false,
  "metric_for_best_model": "None",
  "greater_is_better": "None",
  "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": "None",
  "accelerator_config": "{'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}",
  "parallelism_config": "None",
  "deepspeed": "None",
  "label_smoothing_factor": 0.0,
  "optim": "adamw_torch",
  "optim_args": "None",
  "adafactor": false,
  "group_by_length": false,
  "length_column_name": "length",
  "report_to": "['tensorboard', 'wandb']",
  "project": "huggingface",
  "trackio_space_id": "trackio",
  "ddp_find_unused_parameters": "None",
  "ddp_bucket_cap_mb": "None",
  "ddp_broadcast_buffers": "None",
  "dataloader_pin_memory": true,
  "dataloader_persistent_workers": false,
  "skip_memory_metrics": true,
  "use_legacy_prediction_loop": false,
  "push_to_hub": false,
  "resume_from_checkpoint": "None",
  "hub_model_id": "None",
  "hub_strategy": "every_save",
  "hub_token": "<HUB_TOKEN>",
  "hub_private_repo": "None",
  "hub_always_push": false,
  "hub_revision": "None",
  "gradient_checkpointing": false,
  "gradient_checkpointing_kwargs": "None",
  "include_inputs_for_metrics": false,
  "include_for_metrics": "[]",
  "eval_do_concat_batches": true,
  "fp16_backend": "auto",
  "push_to_hub_model_id": "None",
  "push_to_hub_organization": "None",
  "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
  "mp_parameters": "",
  "auto_find_batch_size": false,
  "full_determinism": false,
  "torchdynamo": "None",
  "ray_scope": "last",
  "ddp_timeout": 1800,
  "torch_compile": false,
  "torch_compile_backend": "None",
  "torch_compile_mode": "None",
  "include_tokens_per_second": false,
  "include_num_input_tokens_seen": "no",
  "neftune_noise_alpha": "None",
  "optim_target_modules": "None",
  "batch_eval_metrics": false,
  "eval_on_start": false,
  "use_liger_kernel": false,
  "liger_kernel_config": "None",
  "eval_use_gather_object": false,
  "average_tokens_across_devices": true,
  "train_batch_size": 16,
  "eval_batch_size": 16
}