{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.06938421509106678, "eval_steps": 5, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003469210754553339, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.003469210754553339, "eval_loss": NaN, "eval_runtime": 22.6773, "eval_samples_per_second": 5.38, "eval_steps_per_second": 2.69, "step": 1 }, { "epoch": 0.006938421509106678, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.010407632263660017, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.013876843018213356, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.017346053772766695, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.017346053772766695, "eval_loss": NaN, "eval_runtime": 20.9817, "eval_samples_per_second": 5.815, "eval_steps_per_second": 2.907, "step": 5 }, { "epoch": 0.020815264527320035, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.024284475281873375, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.027753686036426712, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.031222896790980052, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.03469210754553339, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 }, { "epoch": 0.03469210754553339, "eval_loss": NaN, "eval_runtime": 20.7355, "eval_samples_per_second": 5.884, "eval_steps_per_second": 2.942, "step": 10 }, { "epoch": 0.03816131830008673, "grad_norm": NaN, "learning_rate": 0.00019781476007338058, "loss": 0.0, "step": 11 }, { "epoch": 0.04163052905464007, "grad_norm": NaN, "learning_rate": 0.0001913545457642601, "loss": 0.0, "step": 12 }, { "epoch": 0.045099739809193407, "grad_norm": NaN, "learning_rate": 0.00018090169943749476, "loss": 0.0, "step": 13 }, { "epoch": 0.04856895056374675, "grad_norm": NaN, "learning_rate": 0.00016691306063588583, "loss": 0.0, "step": 14 }, { "epoch": 0.05203816131830009, "grad_norm": NaN, "learning_rate": 0.00015000000000000001, "loss": 0.0, "step": 15 }, { "epoch": 0.05203816131830009, "eval_loss": NaN, "eval_runtime": 20.8048, "eval_samples_per_second": 5.864, "eval_steps_per_second": 2.932, "step": 15 }, { "epoch": 0.055507372072853424, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 16 }, { "epoch": 0.05897658282740677, "grad_norm": NaN, "learning_rate": 0.00011045284632676536, "loss": 0.0, "step": 17 }, { "epoch": 0.062445793581960105, "grad_norm": NaN, "learning_rate": 8.954715367323468e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.06591500433651344, "grad_norm": NaN, "learning_rate": 6.909830056250527e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.06938421509106678, "grad_norm": NaN, "learning_rate": 5.000000000000002e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.06938421509106678, "eval_loss": NaN, "eval_runtime": 21.1637, "eval_samples_per_second": 5.765, "eval_steps_per_second": 2.882, "step": 20 } ], "logging_steps": 1, "max_steps": 25, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 2, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 2 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 6584578552627200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }