| { | |
| "_n_gpu": 1, | |
| "adafactor": false, | |
| "adam_beta1": 0.9, | |
| "adam_beta2": 0.999, | |
| "adam_epsilon": 1e-08, | |
| "architectures": [ | |
| "netFoundLanguageModelling" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "auto_find_batch_size": false, | |
| "average_tokens_across_devices": true, | |
| "batch_eval_metrics": false, | |
| "bf16": true, | |
| "bf16_full_eval": false, | |
| "bos_token_id": 65537, | |
| "classifier_dropout": null, | |
| "compile": false, | |
| "dataloader_drop_last": false, | |
| "dataloader_num_workers": 64, | |
| "dataloader_persistent_workers": true, | |
| "dataloader_pin_memory": true, | |
| "dataloader_prefetch_factor": 8, | |
| "ddp_timeout": 1800, | |
| "debug": [], | |
| "direction_loss_weight": 1.0, | |
| "disable_tqdm": false, | |
| "do_eval": true, | |
| "do_predict": false, | |
| "do_train": true, | |
| "dtype": "float32", | |
| "encoder_layout": null, | |
| "eos_token_id": 65540, | |
| "eval_delay": 0, | |
| "eval_do_concat_batches": true, | |
| "eval_on_start": false, | |
| "eval_steps": 5000, | |
| "eval_strategy": "steps", | |
| "eval_use_gather_object": false, | |
| "flat": 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, | |
| "full_determinism": false, | |
| "gradient_accumulation_steps": 1, | |
| "gradient_checkpointing": false, | |
| "group_by_length": false, | |
| "half_precision_backend": "auto", | |
| "hidden_activation": "gelu_new", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 512, | |
| "hub_always_push": false, | |
| "hub_strategy": "every_save", | |
| "ignore_data_skip": true, | |
| "include_for_metrics": [], | |
| "include_inputs_for_metrics": false, | |
| "include_num_input_tokens_seen": "all", | |
| "include_tokens_per_second": true, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 768, | |
| "jit_mode_eval": false, | |
| "label_smoothing_factor": 0.0, | |
| "layer_norm_eps": 1e-12, | |
| "learning_rate": 0.0001, | |
| "length_column_name": "length", | |
| "limit_bursts": false, | |
| "load_best_model_at_end": false, | |
| "local_rank": 0, | |
| "log_level": "passive", | |
| "log_level_replica": "warning", | |
| "log_on_each_node": true, | |
| "logging_dir": "/global/homes/k/kell/scratch/ucsb_big_data/pretraining/models/netfound-small-pretrain-march2/runs/Mar02_13-55-15_nid002680", | |
| "logging_first_step": false, | |
| "logging_nan_inf_filter": true, | |
| "logging_steps": 5000, | |
| "logging_strategy": "steps", | |
| "lr_scheduler_kwargs": { | |
| "num_decay_steps": 500 | |
| }, | |
| "lr_scheduler_type": "warmup_stable_decay", | |
| "max_burst_length": 73, | |
| "max_bursts": 12, | |
| "max_grad_norm": 1.0, | |
| "max_position_embeddings": 73, | |
| "max_steps": 45000, | |
| "metaFeatures": 4, | |
| "metadata_loss_weight": 1.0, | |
| "mlm_loss_weight": 1.0, | |
| "mlm_probability": 0.3, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.1, | |
| "model_max_length": 876, | |
| "model_name_or_path": "/global/homes/k/kell/scratch/ucsb_big_data/debug_pretraining/netfound-small-pretrain-feb28-long/checkpoint-45000", | |
| "model_type": "netFound", | |
| "mp_parameters": "", | |
| "no_cuda": false, | |
| "no_direction_loss": false, | |
| "no_meta": false, | |
| "no_metadata_loss": false, | |
| "no_mlm": false, | |
| "no_swapped_bursts": false, | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 4, | |
| "num_train_epochs": 3.0, | |
| "optim": "adamw_torch_fused", | |
| "output_dir": "/global/homes/k/kell/scratch/ucsb_big_data/pretraining/models/netfound-small-pretrain-march2/", | |
| "overwrite_output_dir": false, | |
| "p": 0.0, | |
| "pad_token_id": 0, | |
| "past_index": -1, | |
| "per_device_eval_batch_size": 26, | |
| "per_device_train_batch_size": 26, | |
| "position_embedding_type": "absolute", | |
| "prediction_loss_only": false, | |
| "pretraining": true, | |
| "project": "huggingface", | |
| "push_to_hub": false, | |
| "ray_scope": "last", | |
| "remove_unused_columns": true, | |
| "rep_output_path": null, | |
| "report_to": [ | |
| "tensorboard" | |
| ], | |
| "restore_callback_states_from_checkpoint": false, | |
| "roformer": true, | |
| "rotary_value": false, | |
| "save_on_each_node": false, | |
| "save_only_model": false, | |
| "save_safetensors": true, | |
| "save_steps": 5000, | |
| "save_strategy": "steps", | |
| "seed": 42, | |
| "size": "small", | |
| "skip_memory_metrics": true, | |
| "streaming": true, | |
| "strip_payload": true, | |
| "subflow_bursts": 3, | |
| "subflow_len": -1, | |
| "swap_loss_weight": 1.0, | |
| "swap_rate": 0.5, | |
| "test_dir": "/global/homes/k/kell/scratch/ucsb_big_data/small_test", | |
| "torch_compile": false, | |
| "tpu_metrics_debug": false, | |
| "trackio_space_id": "trackio", | |
| "train_dir": "/global/homes/k/kell/scratch/ucsb_big_data/ready_train_data", | |
| "transformers_version": "4.57.3", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "use_cpu": false, | |
| "use_flash_attn": false, | |
| "use_legacy_prediction_loop": false, | |
| "use_liger_kernel": false, | |
| "use_mps_device": false, | |
| "vocab_size": 65600, | |
| "warmup_ratio": 0.0, | |
| "warmup_steps": 500, | |
| "weight_decay": 0.0 | |
| } | |