{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.020855057351407715, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0020855057351407717, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0020855057351407717, "eval_loss": NaN, "eval_runtime": 7.8285, "eval_samples_per_second": 25.803, "eval_steps_per_second": 12.902, "step": 1 }, { "epoch": 0.004171011470281543, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.006256517205422315, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.006256517205422315, "eval_loss": NaN, "eval_runtime": 6.4589, "eval_samples_per_second": 31.275, "eval_steps_per_second": 15.637, "step": 3 }, { "epoch": 0.008342022940563087, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.010427528675703858, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.01251303441084463, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.01251303441084463, "eval_loss": NaN, "eval_runtime": 6.515, "eval_samples_per_second": 31.006, "eval_steps_per_second": 15.503, "step": 6 }, { "epoch": 0.014598540145985401, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.016684045881126174, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.018769551616266946, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.018769551616266946, "eval_loss": NaN, "eval_runtime": 6.4818, "eval_samples_per_second": 31.164, "eval_steps_per_second": 15.582, "step": 9 }, { "epoch": 0.020855057351407715, "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": 2080759779164160.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }