{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.008334297951151754, "eval_steps": 9, "global_step": 18, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004630165528417641, "eval_loss": 2.0430142879486084, "eval_runtime": 144.8645, "eval_samples_per_second": 25.113, "eval_steps_per_second": 3.141, "step": 1 }, { "epoch": 0.0013890496585252923, "grad_norm": 0.5597144961357117, "learning_rate": 1.5e-05, "loss": 2.1021, "step": 3 }, { "epoch": 0.0027780993170505846, "grad_norm": 0.5732973217964172, "learning_rate": 3e-05, "loss": 1.9359, "step": 6 }, { "epoch": 0.004167148975575877, "grad_norm": 0.6314367055892944, "learning_rate": 4.5e-05, "loss": 2.0411, "step": 9 }, { "epoch": 0.004167148975575877, "eval_loss": 2.0033884048461914, "eval_runtime": 146.5734, "eval_samples_per_second": 24.82, "eval_steps_per_second": 3.104, "step": 9 }, { "epoch": 0.005556198634101169, "grad_norm": 0.7915438413619995, "learning_rate": 4.993910125649561e-05, "loss": 2.1273, "step": 12 }, { "epoch": 0.0069452482926264615, "grad_norm": 0.6669667959213257, "learning_rate": 4.962019382530521e-05, "loss": 1.8469, "step": 15 }, { "epoch": 0.008334297951151754, "grad_norm": 0.5791904926300049, "learning_rate": 4.9031542398457974e-05, "loss": 1.7498, "step": 18 }, { "epoch": 0.008334297951151754, "eval_loss": 1.7797669172286987, "eval_runtime": 146.5915, "eval_samples_per_second": 24.817, "eval_steps_per_second": 3.104, "step": 18 } ], "logging_steps": 3, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 9, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.0061434545242112e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }