{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0014369536582445215, "eval_steps": 3, "global_step": 6, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00023949227637408692, "grad_norm": 4.3014726638793945, "learning_rate": 2e-05, "loss": 2.4864, "step": 1 }, { "epoch": 0.00023949227637408692, "eval_loss": 3.196671962738037, "eval_runtime": 56.3772, "eval_samples_per_second": 15.609, "eval_steps_per_second": 15.609, "step": 1 }, { "epoch": 0.00047898455274817384, "grad_norm": 3.2757163047790527, "learning_rate": 4e-05, "loss": 3.3358, "step": 2 }, { "epoch": 0.0007184768291222608, "grad_norm": 2.781923294067383, "learning_rate": 6e-05, "loss": 3.3958, "step": 3 }, { "epoch": 0.0007184768291222608, "eval_loss": 3.0978620052337646, "eval_runtime": 57.0247, "eval_samples_per_second": 15.432, "eval_steps_per_second": 15.432, "step": 3 }, { "epoch": 0.0009579691054963477, "grad_norm": 2.6946146488189697, "learning_rate": 8e-05, "loss": 2.7689, "step": 4 }, { "epoch": 0.0011974613818704347, "grad_norm": 3.1957530975341797, "learning_rate": 0.0001, "loss": 2.8025, "step": 5 }, { "epoch": 0.0014369536582445215, "grad_norm": 2.734419584274292, "learning_rate": 0.00012, "loss": 1.8246, "step": 6 }, { "epoch": 0.0014369536582445215, "eval_loss": 2.6213483810424805, "eval_runtime": 57.0839, "eval_samples_per_second": 15.416, "eval_steps_per_second": 15.416, "step": 6 } ], "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": false }, "attributes": {} } }, "total_flos": 985898535616512.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }