{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.08843537414966, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.10884353741496598, "grad_norm": 0.0, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.10884353741496598, "eval_loss": NaN, "eval_runtime": 25.2352, "eval_samples_per_second": 0.634, "eval_steps_per_second": 0.317, "step": 1 }, { "epoch": 0.21768707482993196, "grad_norm": 0.0, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.32653061224489793, "grad_norm": 0.0, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.32653061224489793, "eval_loss": NaN, "eval_runtime": 0.1076, "eval_samples_per_second": 148.701, "eval_steps_per_second": 74.35, "step": 3 }, { "epoch": 0.43537414965986393, "grad_norm": 0.0, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.54421768707483, "grad_norm": 0.0, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.6530612244897959, "grad_norm": 0.0, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.6530612244897959, "eval_loss": NaN, "eval_runtime": 0.1087, "eval_samples_per_second": 147.223, "eval_steps_per_second": 73.612, "step": 6 }, { "epoch": 0.7619047619047619, "grad_norm": 0.0, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.8707482993197279, "grad_norm": 0.0, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.9795918367346939, "grad_norm": 0.0, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.9795918367346939, "eval_loss": NaN, "eval_runtime": 0.1058, "eval_samples_per_second": 151.27, "eval_steps_per_second": 75.635, "step": 9 }, { "epoch": 1.08843537414966, "grad_norm": 0.0, "learning_rate": 0.0001, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 300278611968000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }