{ "best_metric": 0.7031258940696716, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0030845157310302285, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00030845157310302283, "eval_loss": 0.8441849946975708, "eval_runtime": 64.7567, "eval_samples_per_second": 21.079, "eval_steps_per_second": 10.547, "step": 1 }, { "epoch": 0.0009253547193090684, "grad_norm": 0.08122389763593674, "learning_rate": 0.00012, "loss": 0.5338, "step": 3 }, { "epoch": 0.0015422578655151142, "eval_loss": 0.8161515593528748, "eval_runtime": 68.3304, "eval_samples_per_second": 19.976, "eval_steps_per_second": 9.996, "step": 5 }, { "epoch": 0.001850709438618137, "grad_norm": 0.10917606204748154, "learning_rate": 0.0001992114701314478, "loss": 0.5386, "step": 6 }, { "epoch": 0.0027760641579272056, "grad_norm": 0.13072222471237183, "learning_rate": 0.00018763066800438636, "loss": 0.5337, "step": 9 }, { "epoch": 0.0030845157310302285, "eval_loss": 0.7031258940696716, "eval_runtime": 69.8286, "eval_samples_per_second": 19.548, "eval_steps_per_second": 9.781, "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": 668839830355968.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }