{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.012077294685990338, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0012077294685990338, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0012077294685990338, "eval_loss": NaN, "eval_runtime": 21.185, "eval_samples_per_second": 16.474, "eval_steps_per_second": 8.261, "step": 1 }, { "epoch": 0.0024154589371980675, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0036231884057971015, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0036231884057971015, "eval_loss": NaN, "eval_runtime": 19.3648, "eval_samples_per_second": 18.022, "eval_steps_per_second": 9.037, "step": 3 }, { "epoch": 0.004830917874396135, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.006038647342995169, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.007246376811594203, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.007246376811594203, "eval_loss": NaN, "eval_runtime": 19.4058, "eval_samples_per_second": 17.984, "eval_steps_per_second": 9.018, "step": 6 }, { "epoch": 0.008454106280193236, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.00966183574879227, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.010869565217391304, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.010869565217391304, "eval_loss": NaN, "eval_runtime": 19.3879, "eval_samples_per_second": 18.001, "eval_steps_per_second": 9.026, "step": 9 }, { "epoch": 0.012077294685990338, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3461526803447808.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }