{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.054945054945055, "eval_steps": 5, "global_step": 18, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.05860805860805861, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.05860805860805861, "eval_loss": NaN, "eval_runtime": 10.0877, "eval_samples_per_second": 22.8, "eval_steps_per_second": 1.487, "step": 1 }, { "epoch": 0.11721611721611722, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.17582417582417584, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.23443223443223443, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.29304029304029305, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.29304029304029305, "eval_loss": NaN, "eval_runtime": 9.5734, "eval_samples_per_second": 24.025, "eval_steps_per_second": 1.567, "step": 5 }, { "epoch": 0.3516483516483517, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.41025641025641024, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.46886446886446886, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.5274725274725275, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.5860805860805861, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.5860805860805861, "eval_loss": NaN, "eval_runtime": 9.58, "eval_samples_per_second": 24.008, "eval_steps_per_second": 1.566, "step": 10 }, { "epoch": 0.6446886446886447, "grad_norm": NaN, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.7032967032967034, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.7619047619047619, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.8205128205128205, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.8791208791208791, "grad_norm": NaN, "learning_rate": 3.086582838174551e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.8791208791208791, "eval_loss": NaN, "eval_runtime": 9.5539, "eval_samples_per_second": 24.074, "eval_steps_per_second": 1.57, "step": 15 }, { "epoch": 0.9377289377289377, "grad_norm": NaN, "learning_rate": 1.4644660940672627e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.9963369963369964, "grad_norm": NaN, "learning_rate": 3.8060233744356633e-06, "loss": 0.0, "step": 17 }, { "epoch": 1.054945054945055, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 18 } ], "logging_steps": 1, "max_steps": 18, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 5, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.249522461789389e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }