| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2591815320041972, | |
| "global_step": 12000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.7687216869069928, | |
| "eval_f1": 0.7665424923390772, | |
| "eval_loss": 0.9364227652549744, | |
| "eval_runtime": 684.6631, | |
| "eval_samples_per_second": 197.963, | |
| "eval_steps_per_second": 0.774, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.994774396642183e-06, | |
| "loss": 1.2511, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8296492496569228, | |
| "eval_f1": 0.8293241244922317, | |
| "eval_loss": 0.8166272044181824, | |
| "eval_runtime": 684.0816, | |
| "eval_samples_per_second": 198.131, | |
| "eval_steps_per_second": 0.775, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.989538300104932e-06, | |
| "loss": 0.8696, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.846795732562086, | |
| "eval_f1": 0.8476031571339556, | |
| "eval_loss": 0.7674374580383301, | |
| "eval_runtime": 684.9072, | |
| "eval_samples_per_second": 197.892, | |
| "eval_steps_per_second": 0.774, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.98429171038825e-06, | |
| "loss": 0.8001, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.8562469565730644, | |
| "eval_f1": 0.8555885462291756, | |
| "eval_loss": 0.7412897348403931, | |
| "eval_runtime": 685.4288, | |
| "eval_samples_per_second": 197.742, | |
| "eval_steps_per_second": 0.773, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.97906610703043e-06, | |
| "loss": 0.7653, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.8584087119479408, | |
| "eval_f1": 0.8589656756888883, | |
| "eval_loss": 0.7346311807632446, | |
| "eval_runtime": 1253.8639, | |
| "eval_samples_per_second": 108.096, | |
| "eval_steps_per_second": 0.423, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.8606590033791262, | |
| "eval_f1": 0.8613764873641668, | |
| "eval_loss": 0.7210016846656799, | |
| "eval_runtime": 749.1336, | |
| "eval_samples_per_second": 180.926, | |
| "eval_steps_per_second": 0.707, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.973840503672613e-06, | |
| "loss": 0.7517, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.8668491493160589, | |
| "eval_f1": 0.8662439909072627, | |
| "eval_loss": 0.7115087509155273, | |
| "eval_runtime": 748.5848, | |
| "eval_samples_per_second": 181.059, | |
| "eval_steps_per_second": 0.708, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.968604407135362e-06, | |
| "loss": 0.7386, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.8676090837993773, | |
| "eval_f1": 0.8684186652379281, | |
| "eval_loss": 0.7080894708633423, | |
| "eval_runtime": 748.8743, | |
| "eval_samples_per_second": 180.989, | |
| "eval_steps_per_second": 0.708, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.963389296956978e-06, | |
| "loss": 0.7238, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.8690256607003202, | |
| "eval_f1": 0.8697884276426098, | |
| "eval_loss": 0.7015646696090698, | |
| "eval_runtime": 666.7136, | |
| "eval_samples_per_second": 203.293, | |
| "eval_steps_per_second": 0.795, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.958153200419727e-06, | |
| "loss": 0.7216, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.8712390621080435, | |
| "eval_f1": 0.8724240607774923, | |
| "eval_loss": 0.6999966502189636, | |
| "eval_runtime": 666.1677, | |
| "eval_samples_per_second": 203.459, | |
| "eval_steps_per_second": 0.796, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.87027992149803, | |
| "eval_f1": 0.8704618561200863, | |
| "eval_loss": 0.6968262195587158, | |
| "eval_runtime": 666.1311, | |
| "eval_samples_per_second": 203.47, | |
| "eval_steps_per_second": 0.796, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.952906610703044e-06, | |
| "loss": 0.7123, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.8710250999719635, | |
| "eval_f1": 0.8710228151932407, | |
| "eval_loss": 0.6919674277305603, | |
| "eval_runtime": 666.6562, | |
| "eval_samples_per_second": 203.31, | |
| "eval_steps_per_second": 0.795, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.94766002098636e-06, | |
| "loss": 0.708, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.8743452020835485, | |
| "eval_f1": 0.8736511770234788, | |
| "eval_loss": 0.6875823736190796, | |
| "eval_runtime": 666.8888, | |
| "eval_samples_per_second": 203.239, | |
| "eval_steps_per_second": 0.795, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.94242392444911e-06, | |
| "loss": 0.705, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.8718293024834364, | |
| "eval_f1": 0.8721073032565451, | |
| "eval_loss": 0.6912590861320496, | |
| "eval_runtime": 666.9048, | |
| "eval_samples_per_second": 203.234, | |
| "eval_steps_per_second": 0.795, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.937208814270725e-06, | |
| "loss": 0.6986, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.8746108102524753, | |
| "eval_f1": 0.8755518143887745, | |
| "eval_loss": 0.6850203275680542, | |
| "eval_runtime": 670.2388, | |
| "eval_samples_per_second": 202.223, | |
| "eval_steps_per_second": 0.791, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.8748395283979401, | |
| "eval_f1": 0.8750168188156892, | |
| "eval_loss": 0.6849112510681152, | |
| "eval_runtime": 670.7573, | |
| "eval_samples_per_second": 202.067, | |
| "eval_steps_per_second": 0.79, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.93196222455404e-06, | |
| "loss": 0.6986, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.8763077513317299, | |
| "eval_f1": 0.8766362923981238, | |
| "eval_loss": 0.6798161864280701, | |
| "eval_runtime": 669.9612, | |
| "eval_samples_per_second": 202.307, | |
| "eval_steps_per_second": 0.791, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 9.926715634837356e-06, | |
| "loss": 0.6948, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.8761897032566512, | |
| "eval_f1": 0.8771094350236266, | |
| "eval_loss": 0.6797441840171814, | |
| "eval_runtime": 670.6385, | |
| "eval_samples_per_second": 202.103, | |
| "eval_steps_per_second": 0.79, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.921469045120673e-06, | |
| "loss": 0.694, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.8757765349938763, | |
| "eval_f1": 0.875946128594897, | |
| "eval_loss": 0.6784085631370544, | |
| "eval_runtime": 670.4256, | |
| "eval_samples_per_second": 202.167, | |
| "eval_steps_per_second": 0.791, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.916232948583422e-06, | |
| "loss": 0.6907, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.8782776785846036, | |
| "eval_f1": 0.8778960944609727, | |
| "eval_loss": 0.6746197938919067, | |
| "eval_runtime": 670.9876, | |
| "eval_samples_per_second": 201.998, | |
| "eval_steps_per_second": 0.79, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.8770529298056634, | |
| "eval_f1": 0.8765354326008715, | |
| "eval_loss": 0.6747441291809082, | |
| "eval_runtime": 1255.3569, | |
| "eval_samples_per_second": 107.968, | |
| "eval_steps_per_second": 0.422, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 9.911007345225604e-06, | |
| "loss": 0.6879, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 9.905781741867787e-06, | |
| "loss": 0.6875, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.8780932284672933, | |
| "eval_f1": 0.879247713093542, | |
| "eval_loss": 0.6763164401054382, | |
| "eval_runtime": 687.9898, | |
| "eval_samples_per_second": 197.006, | |
| "eval_steps_per_second": 0.77, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.900545645330536e-06, | |
| "loss": 0.686, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.8796352314480071, | |
| "eval_f1": 0.8798913903465643, | |
| "eval_loss": 0.6714671850204468, | |
| "eval_runtime": 688.5552, | |
| "eval_samples_per_second": 196.844, | |
| "eval_steps_per_second": 0.77, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.895309548793285e-06, | |
| "loss": 0.6828, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_accuracy": 0.8783293246174505, | |
| "eval_f1": 0.8770525463818627, | |
| "eval_loss": 0.6699363589286804, | |
| "eval_runtime": 734.0798, | |
| "eval_samples_per_second": 184.637, | |
| "eval_steps_per_second": 0.722, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 9.890073452256035e-06, | |
| "loss": 0.679, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_accuracy": 0.8791187711195384, | |
| "eval_f1": 0.8798211781418543, | |
| "eval_loss": 0.6693193912506104, | |
| "eval_runtime": 733.9523, | |
| "eval_samples_per_second": 184.669, | |
| "eval_steps_per_second": 0.722, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 9.884837355718784e-06, | |
| "loss": 0.679, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_accuracy": 0.8803435198984787, | |
| "eval_f1": 0.8801011265002094, | |
| "eval_loss": 0.6679297685623169, | |
| "eval_runtime": 684.5882, | |
| "eval_samples_per_second": 197.985, | |
| "eval_steps_per_second": 0.774, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 9.8795907660021e-06, | |
| "loss": 0.678, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_accuracy": 0.8807862001800233, | |
| "eval_f1": 0.8812929844052909, | |
| "eval_loss": 0.6662477254867554, | |
| "eval_runtime": 684.0407, | |
| "eval_samples_per_second": 198.143, | |
| "eval_steps_per_second": 0.775, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 9.874354669464849e-06, | |
| "loss": 0.6767, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_accuracy": 0.8794138913072349, | |
| "eval_f1": 0.8799114820136512, | |
| "eval_loss": 0.6668325662612915, | |
| "eval_runtime": 685.344, | |
| "eval_samples_per_second": 197.766, | |
| "eval_steps_per_second": 0.773, | |
| "step": 12000 | |
| } | |
| ], | |
| "max_steps": 953000, | |
| "num_train_epochs": 100, | |
| "total_flos": 5.0440310829817606e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |