{ "best_metric": null, "best_model_checkpoint": null, "epoch": 7.861635220125786, "eval_steps": 500, "global_step": 2500, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.5864516129032258, "eval_loss": 0.2008386254310608, "eval_runtime": 1.3601, "eval_samples_per_second": 2279.22, "eval_steps_per_second": 47.79, "step": 318 }, { "epoch": 1.5723270440251573, "grad_norm": 0.5175672173500061, "learning_rate": 1.606918238993711e-05, "loss": 0.3218, "step": 500 }, { "epoch": 2.0, "eval_accuracy": 0.8258064516129032, "eval_loss": 0.09898000210523605, "eval_runtime": 1.3658, "eval_samples_per_second": 2269.659, "eval_steps_per_second": 47.59, "step": 636 }, { "epoch": 3.0, "eval_accuracy": 0.8777419354838709, "eval_loss": 0.06669934839010239, "eval_runtime": 1.2565, "eval_samples_per_second": 2467.123, "eval_steps_per_second": 51.73, "step": 954 }, { "epoch": 3.1446540880503147, "grad_norm": 0.47839590907096863, "learning_rate": 1.2138364779874214e-05, "loss": 0.1144, "step": 1000 }, { "epoch": 4.0, "eval_accuracy": 0.8932258064516129, "eval_loss": 0.051668863743543625, "eval_runtime": 1.2584, "eval_samples_per_second": 2463.451, "eval_steps_per_second": 51.653, "step": 1272 }, { "epoch": 4.716981132075472, "grad_norm": 0.32125934958457947, "learning_rate": 8.207547169811321e-06, "loss": 0.0737, "step": 1500 }, { "epoch": 5.0, "eval_accuracy": 0.9048387096774193, "eval_loss": 0.04295943304896355, "eval_runtime": 1.2626, "eval_samples_per_second": 2455.311, "eval_steps_per_second": 51.482, "step": 1590 }, { "epoch": 6.0, "eval_accuracy": 0.9125806451612903, "eval_loss": 0.03821730986237526, "eval_runtime": 1.3321, "eval_samples_per_second": 2327.068, "eval_steps_per_second": 48.793, "step": 1908 }, { "epoch": 6.289308176100629, "grad_norm": 0.2682598829269409, "learning_rate": 4.276729559748428e-06, "loss": 0.0592, "step": 2000 }, { "epoch": 7.0, "eval_accuracy": 0.9151612903225806, "eval_loss": 0.036075200885534286, "eval_runtime": 1.3604, "eval_samples_per_second": 2278.679, "eval_steps_per_second": 47.779, "step": 2226 }, { "epoch": 7.861635220125786, "grad_norm": 0.23691096901893616, "learning_rate": 3.459119496855346e-07, "loss": 0.0531, "step": 2500 } ], "logging_steps": 500, "max_steps": 2544, "num_input_tokens_seen": 0, "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 651155886807636.0, "train_batch_size": 48, "trial_name": null, "trial_params": { "alpha": 0.7723229117593493, "num_train_epochs": 8, "temperature": 11 } }