| { | |
| "timestamp": "2025-05-23T10:59:16.351549", | |
| "model_name": "unsloth/gemma-3-12b-it-unsloth-bnb-4bit", | |
| "task": "", | |
| "subtask": "", | |
| "dataset_size": 6920, | |
| "training_time_seconds": 185.18492698669434, | |
| "peak_gpu_memory_gb": 24.986, | |
| "memory_usage_percent": 63.259, | |
| "hyperparameters": { | |
| "output_dir": "unsloth_training_checkpoints", | |
| "do_train": false, | |
| "do_eval": false, | |
| "do_predict": false, | |
| "eval_strategy": "no", | |
| "prediction_loss_only": false, | |
| "per_device_train_batch_size": 2, | |
| "per_device_eval_batch_size": 4, | |
| "gradient_accumulation_steps": 4, | |
| "eval_accumulation_steps": 2, | |
| "eval_delay": 0, | |
| "torch_empty_cache_steps": 250, | |
| "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": 3.0, | |
| "max_steps": 30, | |
| "lr_scheduler_type": "linear", | |
| "warmup_ratio": 0.1, | |
| "warmup_steps": 5, | |
| "log_level": "passive", | |
| "log_level_replica": "warning", | |
| "log_on_each_node": true, | |
| "logging_dir": "unsloth_training_checkpoints/runs/May23_10-57-04_jupyter-alvaro-2ealonso", | |
| "logging_strategy": "steps", | |
| "logging_first_step": false, | |
| "logging_steps": 1, | |
| "logging_nan_inf_filter": false, | |
| "save_strategy": "no", | |
| "save_steps": 500, | |
| "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": 3407, | |
| "data_seed": 3407, | |
| "jit_mode_eval": false, | |
| "use_ipex": false, | |
| "bf16": false, | |
| "fp16": false, | |
| "fp16_opt_level": "O1", | |
| "half_precision_backend": "auto", | |
| "bf16_full_eval": false, | |
| "fp16_full_eval": false, | |
| "local_rank": 0, | |
| "tpu_metrics_debug": false, | |
| "dataloader_drop_last": false, | |
| "dataloader_num_workers": 0, | |
| "past_index": -1, | |
| "run_name": "unsloth_training_checkpoints", | |
| "disable_tqdm": false, | |
| "remove_unused_columns": true, | |
| "load_best_model_at_end": false, | |
| "ignore_data_skip": false, | |
| "fsdp_min_num_params": 0, | |
| "fsdp_config": { | |
| "min_num_params": 0, | |
| "xla": false, | |
| "xla_fsdp_v2": false, | |
| "xla_fsdp_grad_ckpt": false | |
| }, | |
| "tp_size": 0, | |
| "accelerator_config": { | |
| "split_batches": false, | |
| "even_batches": true, | |
| "use_seedable_sampler": true, | |
| "non_blocking": false, | |
| "use_configured_state": false | |
| }, | |
| "label_smoothing_factor": 0.0, | |
| "optim": "adamw_8bit", | |
| "adafactor": false, | |
| "group_by_length": false, | |
| "length_column_name": "length", | |
| "dataloader_pin_memory": true, | |
| "dataloader_persistent_workers": false, | |
| "skip_memory_metrics": true, | |
| "use_legacy_prediction_loop": false, | |
| "push_to_hub": false, | |
| "hub_strategy": "every_save", | |
| "hub_always_push": false, | |
| "gradient_checkpointing": false, | |
| "include_inputs_for_metrics": false, | |
| "eval_do_concat_batches": true, | |
| "fp16_backend": "auto", | |
| "_n_gpu": 1, | |
| "auto_find_batch_size": false, | |
| "full_determinism": false, | |
| "ray_scope": "last", | |
| "ddp_timeout": 1800, | |
| "torch_compile": false, | |
| "include_tokens_per_second": false, | |
| "include_num_input_tokens_seen": false, | |
| "batch_eval_metrics": false, | |
| "eval_on_start": false, | |
| "use_liger_kernel": false, | |
| "eval_use_gather_object": false, | |
| "average_tokens_across_devices": false, | |
| "use_liger": false, | |
| "dataset_text_field": "text", | |
| "dataset_num_proc": 96, | |
| "packing": false, | |
| "unsloth_num_chunks": -1 | |
| }, | |
| "train_loss": 0.29300599644581476, | |
| "learning_rate": 0.0, | |
| "epoch": 0, | |
| "steps_per_second": 3.205 | |
| } |