{ "best_metric": 1.6549012660980225, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.00016563146997929605, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.6563146997929607e-05, "eval_loss": 1.7354477643966675, "eval_runtime": 3029.7416, "eval_samples_per_second": 8.39, "eval_steps_per_second": 4.195, "step": 1 }, { "epoch": 4.968944099378882e-05, "grad_norm": 0.46449899673461914, "learning_rate": 6e-05, "loss": 1.7907, "step": 3 }, { "epoch": 8.281573498964803e-05, "eval_loss": 1.7044700384140015, "eval_runtime": 3033.6502, "eval_samples_per_second": 8.38, "eval_steps_per_second": 4.19, "step": 5 }, { "epoch": 9.937888198757764e-05, "grad_norm": 0.5845046043395996, "learning_rate": 0.00012, "loss": 1.814, "step": 6 }, { "epoch": 0.00014906832298136645, "grad_norm": 0.32533901929855347, "learning_rate": 0.00018, "loss": 1.5945, "step": 9 }, { "epoch": 0.00016563146997929605, "eval_loss": 1.6549012660980225, "eval_runtime": 3029.9283, "eval_samples_per_second": 8.39, "eval_steps_per_second": 4.195, "step": 10 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1646346004070400.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }