{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006041155370964697, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006041155370964697, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0006041155370964697, "eval_loss": NaN, "eval_runtime": 817.061, "eval_samples_per_second": 3.412, "eval_steps_per_second": 1.706, "step": 1 }, { "epoch": 0.0012082310741929395, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0018123466112894091, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0018123466112894091, "eval_loss": NaN, "eval_runtime": 744.7441, "eval_samples_per_second": 3.744, "eval_steps_per_second": 1.872, "step": 3 }, { "epoch": 0.002416462148385879, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0030205776854823484, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.0036246932225788182, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.0036246932225788182, "eval_loss": NaN, "eval_runtime": 744.9399, "eval_samples_per_second": 3.743, "eval_steps_per_second": 1.871, "step": 6 }, { "epoch": 0.004228808759675288, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.004832924296771758, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.005437039833868227, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.005437039833868227, "eval_loss": NaN, "eval_runtime": 744.6642, "eval_samples_per_second": 3.744, "eval_steps_per_second": 1.872, "step": 9 }, { "epoch": 0.006041155370964697, "grad_norm": NaN, "learning_rate": 0.0001, "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": 8.386012766011392e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }