{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.000241796061142164, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.20898030571082e-05, "eval_loss": NaN, "eval_runtime": 2905.1112, "eval_samples_per_second": 8.991, "eval_steps_per_second": 4.496, "step": 1 }, { "epoch": 3.62694091713246e-05, "grad_norm": NaN, "learning_rate": 8.999999999999999e-05, "loss": 0.0, "step": 3 }, { "epoch": 7.25388183426492e-05, "grad_norm": NaN, "learning_rate": 0.00017999999999999998, "loss": 0.0, "step": 6 }, { "epoch": 9.67184244568656e-05, "eval_loss": NaN, "eval_runtime": 2904.6713, "eval_samples_per_second": 8.993, "eval_steps_per_second": 4.497, "step": 8 }, { "epoch": 0.0001088082275139738, "grad_norm": NaN, "learning_rate": 0.00027, "loss": 0.0, "step": 9 }, { "epoch": 0.0001450776366852984, "grad_norm": NaN, "learning_rate": 0.00029265847744427303, "loss": 0.0, "step": 12 }, { "epoch": 0.000181347045856623, "grad_norm": NaN, "learning_rate": 0.00025606601717798207, "loss": 0.0, "step": 15 }, { "epoch": 0.0001934368489137312, "eval_loss": NaN, "eval_runtime": 2909.2231, "eval_samples_per_second": 8.979, "eval_steps_per_second": 4.49, "step": 16 }, { "epoch": 0.0002176164550279476, "grad_norm": NaN, "learning_rate": 0.0001963525491562421, "loss": 0.0, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 8261771609505792.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }