{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "learning_rate": 2e-05, "loss": 1.5991, "step": 100 }, { "epoch": 1.0, "eval_accuracy": 0.638, "eval_loss": 0.7116702795028687, "eval_macro_f1": 0.633566150420083, "eval_runtime": 89.1695, "eval_samples_per_second": 5.607, "eval_steps_per_second": 0.561, "step": 100 }, { "epoch": 2.0, "learning_rate": 2e-05, "loss": 0.6537, "step": 200 }, { "epoch": 2.0, "eval_accuracy": 0.618, "eval_loss": 1.2388803958892822, "eval_macro_f1": 0.5674015555424694, "eval_runtime": 89.196, "eval_samples_per_second": 5.606, "eval_steps_per_second": 0.561, "step": 200 }, { "epoch": 3.0, "learning_rate": 2e-05, "loss": 0.3544, "step": 300 }, { "epoch": 3.0, "eval_accuracy": 0.708, "eval_loss": 0.6158359050750732, "eval_macro_f1": 0.7078317110655739, "eval_runtime": 89.1778, "eval_samples_per_second": 5.607, "eval_steps_per_second": 0.561, "step": 300 }, { "epoch": 4.0, "learning_rate": 2e-05, "loss": 0.1829, "step": 400 }, { "epoch": 4.0, "eval_accuracy": 0.708, "eval_loss": 1.6795860528945923, "eval_macro_f1": 0.7078317110655739, "eval_runtime": 89.1817, "eval_samples_per_second": 5.607, "eval_steps_per_second": 0.561, "step": 400 }, { "epoch": 5.0, "learning_rate": 2e-05, "loss": 0.1188, "step": 500 }, { "epoch": 5.0, "eval_accuracy": 0.704, "eval_loss": 1.4835941791534424, "eval_macro_f1": 0.7039242045963766, "eval_runtime": 89.1768, "eval_samples_per_second": 5.607, "eval_steps_per_second": 0.561, "step": 500 }, { "epoch": 6.0, "learning_rate": 2e-05, "loss": 0.0924, "step": 600 }, { "epoch": 6.0, "eval_accuracy": 0.698, "eval_loss": 2.3937265872955322, "eval_macro_f1": 0.6914223590045407, "eval_runtime": 89.1641, "eval_samples_per_second": 5.608, "eval_steps_per_second": 0.561, "step": 600 }, { "epoch": 7.0, "learning_rate": 2e-05, "loss": 0.0913, "step": 700 }, { "epoch": 7.0, "eval_accuracy": 0.706, "eval_loss": 1.8895695209503174, "eval_macro_f1": 0.7053765768365863, "eval_runtime": 89.2883, "eval_samples_per_second": 5.6, "eval_steps_per_second": 0.56, "step": 700 }, { "epoch": 8.0, "learning_rate": 2e-05, "loss": 0.1357, "step": 800 }, { "epoch": 8.0, "eval_accuracy": 0.714, "eval_loss": 2.458871603012085, "eval_macro_f1": 0.7132832080200502, "eval_runtime": 89.4099, "eval_samples_per_second": 5.592, "eval_steps_per_second": 0.559, "step": 800 }, { "epoch": 9.0, "learning_rate": 2e-05, "loss": 0.0432, "step": 900 }, { "epoch": 9.0, "eval_accuracy": 0.742, "eval_loss": 3.152550220489502, "eval_macro_f1": 0.7390681699576441, "eval_runtime": 89.2296, "eval_samples_per_second": 5.604, "eval_steps_per_second": 0.56, "step": 900 }, { "epoch": 10.0, "learning_rate": 2e-05, "loss": 0.0491, "step": 1000 }, { "epoch": 10.0, "eval_accuracy": 0.754, "eval_loss": 3.035457134246826, "eval_macro_f1": 0.7527886644558337, "eval_runtime": 89.2033, "eval_samples_per_second": 5.605, "eval_steps_per_second": 0.561, "step": 1000 } ], "logging_steps": 100, "max_steps": 1000, "num_train_epochs": 10, "save_steps": 500, "total_flos": 3.913814800576512e+17, "trial_name": null, "trial_params": null }