{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0010923589491506909, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00021847178983013817, "grad_norm": 0.11381302773952484, "learning_rate": 1e-05, "loss": 10.3772, "step": 1 }, { "epoch": 0.00021847178983013817, "eval_loss": 10.374558448791504, "eval_runtime": 22.9819, "eval_samples_per_second": 335.481, "eval_steps_per_second": 167.74, "step": 1 }, { "epoch": 0.00043694357966027634, "grad_norm": 0.12134013324975967, "learning_rate": 2e-05, "loss": 10.3567, "step": 2 }, { "epoch": 0.00043694357966027634, "eval_loss": 10.374534606933594, "eval_runtime": 15.0909, "eval_samples_per_second": 510.905, "eval_steps_per_second": 255.453, "step": 2 }, { "epoch": 0.0006554153694904145, "grad_norm": 0.10446050763130188, "learning_rate": 3e-05, "loss": 10.3829, "step": 3 }, { "epoch": 0.0008738871593205527, "grad_norm": 0.10591564327478409, "learning_rate": 4e-05, "loss": 10.3775, "step": 4 }, { "epoch": 0.0008738871593205527, "eval_loss": 10.374430656433105, "eval_runtime": 15.4309, "eval_samples_per_second": 499.645, "eval_steps_per_second": 249.823, "step": 4 }, { "epoch": 0.0010923589491506909, "grad_norm": 0.11212324351072311, "learning_rate": 5e-05, "loss": 10.3745, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "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": 517236326400.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }