{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.026367831245880026, "eval_steps": 1, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0026367831245880024, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0026367831245880024, "eval_loss": NaN, "eval_runtime": 21.2592, "eval_samples_per_second": 7.526, "eval_steps_per_second": 3.763, "step": 1 }, { "epoch": 0.005273566249176005, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.005273566249176005, "eval_loss": NaN, "eval_runtime": 20.8256, "eval_samples_per_second": 7.683, "eval_steps_per_second": 3.841, "step": 2 }, { "epoch": 0.007910349373764008, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.007910349373764008, "eval_loss": NaN, "eval_runtime": 20.932, "eval_samples_per_second": 7.644, "eval_steps_per_second": 3.822, "step": 3 }, { "epoch": 0.01054713249835201, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.01054713249835201, "eval_loss": NaN, "eval_runtime": 20.9038, "eval_samples_per_second": 7.654, "eval_steps_per_second": 3.827, "step": 4 }, { "epoch": 0.013183915622940013, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.013183915622940013, "eval_loss": NaN, "eval_runtime": 20.9515, "eval_samples_per_second": 7.637, "eval_steps_per_second": 3.818, "step": 5 }, { "epoch": 0.015820698747528016, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.015820698747528016, "eval_loss": NaN, "eval_runtime": 21.0027, "eval_samples_per_second": 7.618, "eval_steps_per_second": 3.809, "step": 6 }, { "epoch": 0.01845748187211602, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.01845748187211602, "eval_loss": NaN, "eval_runtime": 21.0252, "eval_samples_per_second": 7.61, "eval_steps_per_second": 3.805, "step": 7 }, { "epoch": 0.02109426499670402, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.02109426499670402, "eval_loss": NaN, "eval_runtime": 21.0431, "eval_samples_per_second": 7.603, "eval_steps_per_second": 3.802, "step": 8 }, { "epoch": 0.023731048121292023, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.023731048121292023, "eval_loss": NaN, "eval_runtime": 21.0418, "eval_samples_per_second": 7.604, "eval_steps_per_second": 3.802, "step": 9 }, { "epoch": 0.026367831245880026, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.026367831245880026, "eval_loss": NaN, "eval_runtime": 21.0573, "eval_samples_per_second": 7.598, "eval_steps_per_second": 3.799, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 6495281558323200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }