{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.001221971039286369, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00012219710392863688, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00012219710392863688, "eval_loss": NaN, "eval_runtime": 82.8196, "eval_samples_per_second": 41.609, "eval_steps_per_second": 20.804, "step": 1 }, { "epoch": 0.00024439420785727376, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.00036659131178591066, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.00036659131178591066, "eval_loss": NaN, "eval_runtime": 82.6319, "eval_samples_per_second": 41.703, "eval_steps_per_second": 20.852, "step": 3 }, { "epoch": 0.0004887884157145475, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0006109855196431845, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0007331826235718213, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0007331826235718213, "eval_loss": NaN, "eval_runtime": 82.3595, "eval_samples_per_second": 41.841, "eval_steps_per_second": 20.92, "step": 6 }, { "epoch": 0.0008553797275004583, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.000977576831429095, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.001099773935357732, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.001099773935357732, "eval_loss": NaN, "eval_runtime": 82.2387, "eval_samples_per_second": 41.902, "eval_steps_per_second": 20.951, "step": 9 }, { "epoch": 0.001221971039286369, "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": 324298258513920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }