| { | |
| "best_metric": 0.9590698631546456, | |
| "best_model_checkpoint": ".//debugged_es_gsd_ses_udpipe_8_0.1_0.00002_20_04-22-24_22-38/checkpoint-32020", | |
| "epoch": 19.99968779269435, | |
| "global_step": 32020, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6659729448491154e-05, | |
| "loss": 0.9658, | |
| "step": 1601 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9632624280173934, | |
| "eval_f1": 0.9191161314259801, | |
| "eval_loss": 0.153659850358963, | |
| "eval_precision": 0.9176029962546817, | |
| "eval_recall": 0.9206342651856134, | |
| "eval_runtime": 12.5305, | |
| "eval_samples_per_second": 127.848, | |
| "eval_steps_per_second": 16.041, | |
| "step": 1601 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.9149445145856868e-05, | |
| "loss": 0.118, | |
| "step": 3202 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9749441767540251, | |
| "eval_f1": 0.9426544669476715, | |
| "eval_loss": 0.09417378902435303, | |
| "eval_precision": 0.9387746744205094, | |
| "eval_recall": 0.9465664615765784, | |
| "eval_runtime": 12.5537, | |
| "eval_samples_per_second": 127.612, | |
| "eval_steps_per_second": 16.011, | |
| "step": 3202 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.8085587082198154e-05, | |
| "loss": 0.0727, | |
| "step": 4803 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9784228463979316, | |
| "eval_f1": 0.9501459044017919, | |
| "eval_loss": 0.07907041162252426, | |
| "eval_precision": 0.9457148701165883, | |
| "eval_recall": 0.9546186563158112, | |
| "eval_runtime": 12.5508, | |
| "eval_samples_per_second": 127.642, | |
| "eval_steps_per_second": 16.015, | |
| "step": 4803 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.702172901853944e-05, | |
| "loss": 0.0479, | |
| "step": 6404 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9803267128922317, | |
| "eval_f1": 0.9543441998393706, | |
| "eval_loss": 0.07787933200597763, | |
| "eval_precision": 0.9518938460274423, | |
| "eval_recall": 0.9568072015526283, | |
| "eval_runtime": 12.5524, | |
| "eval_samples_per_second": 127.625, | |
| "eval_steps_per_second": 16.013, | |
| "step": 6404 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.5957870954880726e-05, | |
| "loss": 0.0342, | |
| "step": 8005 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9791984957104243, | |
| "eval_f1": 0.951995205720072, | |
| "eval_loss": 0.08329462260007858, | |
| "eval_precision": 0.9528418962521717, | |
| "eval_recall": 0.9511500185819879, | |
| "eval_runtime": 12.5712, | |
| "eval_samples_per_second": 127.435, | |
| "eval_steps_per_second": 15.989, | |
| "step": 8005 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.489401289122201e-05, | |
| "loss": 0.0233, | |
| "step": 9606 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9811023622047244, | |
| "eval_f1": 0.956315778633658, | |
| "eval_loss": 0.08429370075464249, | |
| "eval_precision": 0.9539776462853385, | |
| "eval_recall": 0.9586654003386051, | |
| "eval_runtime": 12.5589, | |
| "eval_samples_per_second": 127.559, | |
| "eval_steps_per_second": 16.005, | |
| "step": 9606 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 1.3830154827563293e-05, | |
| "loss": 0.0168, | |
| "step": 11207 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9807262898107886, | |
| "eval_f1": 0.9542881840821619, | |
| "eval_loss": 0.09856697916984558, | |
| "eval_precision": 0.9512925728354534, | |
| "eval_recall": 0.9573027212288888, | |
| "eval_runtime": 12.7018, | |
| "eval_samples_per_second": 126.124, | |
| "eval_steps_per_second": 15.825, | |
| "step": 11207 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.276629676390458e-05, | |
| "loss": 0.0121, | |
| "step": 12808 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9815254436479022, | |
| "eval_f1": 0.9566986580077682, | |
| "eval_loss": 0.10770849883556366, | |
| "eval_precision": 0.9522952295229523, | |
| "eval_recall": 0.9611429987199075, | |
| "eval_runtime": 12.5218, | |
| "eval_samples_per_second": 127.937, | |
| "eval_steps_per_second": 16.052, | |
| "step": 12808 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.1702438700245863e-05, | |
| "loss": 0.0102, | |
| "step": 14409 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9800916676460218, | |
| "eval_f1": 0.9545660129106535, | |
| "eval_loss": 0.12106840312480927, | |
| "eval_precision": 0.9505015353121802, | |
| "eval_recall": 0.9586654003386051, | |
| "eval_runtime": 12.5371, | |
| "eval_samples_per_second": 127.781, | |
| "eval_steps_per_second": 16.032, | |
| "step": 14409 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 1.063858063658715e-05, | |
| "loss": 0.0073, | |
| "step": 16010 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9807732988600305, | |
| "eval_f1": 0.9554837514663813, | |
| "eval_loss": 0.12773701548576355, | |
| "eval_precision": 0.9524454291810274, | |
| "eval_recall": 0.95854152041954, | |
| "eval_runtime": 12.7247, | |
| "eval_samples_per_second": 125.897, | |
| "eval_steps_per_second": 15.796, | |
| "step": 16010 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 9.574722572928434e-06, | |
| "loss": 0.0068, | |
| "step": 17611 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9810083441062405, | |
| "eval_f1": 0.9555354647817867, | |
| "eval_loss": 0.13228633999824524, | |
| "eval_precision": 0.9509631507913787, | |
| "eval_recall": 0.9601519593673865, | |
| "eval_runtime": 12.7411, | |
| "eval_samples_per_second": 125.735, | |
| "eval_steps_per_second": 15.776, | |
| "step": 17611 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 8.51086450926972e-06, | |
| "loss": 0.0051, | |
| "step": 19212 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9815724526971442, | |
| "eval_f1": 0.95762694407251, | |
| "eval_loss": 0.12687553465366364, | |
| "eval_precision": 0.9554422887208155, | |
| "eval_recall": 0.9598216129165462, | |
| "eval_runtime": 12.7033, | |
| "eval_samples_per_second": 126.109, | |
| "eval_steps_per_second": 15.823, | |
| "step": 19212 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 7.447006445611005e-06, | |
| "loss": 0.0035, | |
| "step": 20813 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.982089552238806, | |
| "eval_f1": 0.9584635630860339, | |
| "eval_loss": 0.13741779327392578, | |
| "eval_precision": 0.9545771042391972, | |
| "eval_recall": 0.9623817979105587, | |
| "eval_runtime": 12.6726, | |
| "eval_samples_per_second": 126.414, | |
| "eval_steps_per_second": 15.861, | |
| "step": 20813 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 6.38314838195229e-06, | |
| "loss": 0.0027, | |
| "step": 22414 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9823481020096368, | |
| "eval_f1": 0.9589226973684211, | |
| "eval_loss": 0.14472806453704834, | |
| "eval_precision": 0.9548785980428285, | |
| "eval_recall": 0.9630011975058843, | |
| "eval_runtime": 12.6834, | |
| "eval_samples_per_second": 126.306, | |
| "eval_steps_per_second": 15.847, | |
| "step": 22414 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 5.319290318293575e-06, | |
| "loss": 0.003, | |
| "step": 24015 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9819015160418381, | |
| "eval_f1": 0.9580811200329422, | |
| "eval_loss": 0.1390347182750702, | |
| "eval_precision": 0.955405904816655, | |
| "eval_recall": 0.9607713589627122, | |
| "eval_runtime": 13.4492, | |
| "eval_samples_per_second": 119.115, | |
| "eval_steps_per_second": 14.945, | |
| "step": 24015 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.25543225463486e-06, | |
| "loss": 0.0025, | |
| "step": 25616 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9812433893524504, | |
| "eval_f1": 0.9562028758600799, | |
| "eval_loss": 0.1537328064441681, | |
| "eval_precision": 0.9540801644398766, | |
| "eval_recall": 0.9583350538877647, | |
| "eval_runtime": 12.9219, | |
| "eval_samples_per_second": 123.976, | |
| "eval_steps_per_second": 15.555, | |
| "step": 25616 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.191574190976145e-06, | |
| "loss": 0.0029, | |
| "step": 27217 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.982207074861911, | |
| "eval_f1": 0.9580219463487947, | |
| "eval_loss": 0.15050023794174194, | |
| "eval_precision": 0.9552882246674331, | |
| "eval_recall": 0.9607713589627122, | |
| "eval_runtime": 12.7344, | |
| "eval_samples_per_second": 125.801, | |
| "eval_steps_per_second": 15.784, | |
| "step": 27217 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 2.12771612731743e-06, | |
| "loss": 0.0022, | |
| "step": 28818 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9823245974850159, | |
| "eval_f1": 0.9589283509609449, | |
| "eval_loss": 0.14898641407489777, | |
| "eval_precision": 0.955703211517165, | |
| "eval_recall": 0.9621753313787835, | |
| "eval_runtime": 12.8609, | |
| "eval_samples_per_second": 124.563, | |
| "eval_steps_per_second": 15.629, | |
| "step": 28818 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 1.063858063658715e-06, | |
| "loss": 0.0021, | |
| "step": 30419 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.982019038664943, | |
| "eval_f1": 0.9582288369033425, | |
| "eval_loss": 0.15266422927379608, | |
| "eval_precision": 0.954070981210856, | |
| "eval_recall": 0.9624230912169137, | |
| "eval_runtime": 12.7956, | |
| "eval_samples_per_second": 125.199, | |
| "eval_steps_per_second": 15.709, | |
| "step": 30419 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0018, | |
| "step": 32020 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9824421201081208, | |
| "eval_f1": 0.9590698631546456, | |
| "eval_loss": 0.15378834307193756, | |
| "eval_precision": 0.9559028632373452, | |
| "eval_recall": 0.9622579179914936, | |
| "eval_runtime": 12.9229, | |
| "eval_samples_per_second": 123.966, | |
| "eval_steps_per_second": 15.554, | |
| "step": 32020 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 32020, | |
| "total_flos": 2.8281562629741216e+16, | |
| "train_loss": 0.06704426395528247, | |
| "train_runtime": 9262.2202, | |
| "train_samples_per_second": 27.663, | |
| "train_steps_per_second": 3.457 | |
| } | |
| ], | |
| "max_steps": 32020, | |
| "num_train_epochs": 20, | |
| "total_flos": 2.8281562629741216e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |