| { | |
| "best_metric": 0.728, | |
| "best_model_checkpoint": "VT_15/checkpoint-7279", | |
| "epoch": 29.0, | |
| "eval_steps": 500, | |
| "global_step": 7279, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.398406374501992, | |
| "grad_norm": 11.727704048156738, | |
| "learning_rate": 9.867197875166003e-05, | |
| "loss": 1.0157, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.796812749003984, | |
| "grad_norm": 11.50269603729248, | |
| "learning_rate": 9.734395750332006e-05, | |
| "loss": 0.8938, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.548, | |
| "eval_f1": 0.4882155949880584, | |
| "eval_loss": 0.9423586130142212, | |
| "eval_precision": 0.5733499456903712, | |
| "eval_recall": 0.5448468191272983, | |
| "eval_runtime": 16.5911, | |
| "eval_samples_per_second": 30.137, | |
| "eval_steps_per_second": 3.797, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.1952191235059761, | |
| "grad_norm": 10.47740650177002, | |
| "learning_rate": 9.601593625498009e-05, | |
| "loss": 0.8485, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.593625498007968, | |
| "grad_norm": 12.222431182861328, | |
| "learning_rate": 9.468791500664011e-05, | |
| "loss": 0.7978, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.9920318725099602, | |
| "grad_norm": 13.02956771850586, | |
| "learning_rate": 9.335989375830013e-05, | |
| "loss": 0.8093, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.61, | |
| "eval_f1": 0.584707628587346, | |
| "eval_loss": 0.8303987979888916, | |
| "eval_precision": 0.6022599150943656, | |
| "eval_recall": 0.6097290164964017, | |
| "eval_runtime": 15.8756, | |
| "eval_samples_per_second": 31.495, | |
| "eval_steps_per_second": 3.968, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 2.3904382470119523, | |
| "grad_norm": 11.920299530029297, | |
| "learning_rate": 9.203187250996016e-05, | |
| "loss": 0.7275, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.7888446215139444, | |
| "grad_norm": 12.057920455932617, | |
| "learning_rate": 9.070385126162018e-05, | |
| "loss": 0.7444, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.578, | |
| "eval_f1": 0.5180026990553307, | |
| "eval_loss": 0.8966869115829468, | |
| "eval_precision": 0.6246163183733936, | |
| "eval_recall": 0.5751176873923239, | |
| "eval_runtime": 16.5617, | |
| "eval_samples_per_second": 30.19, | |
| "eval_steps_per_second": 3.804, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 3.187250996015936, | |
| "grad_norm": 12.730193138122559, | |
| "learning_rate": 8.937583001328021e-05, | |
| "loss": 0.7091, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.585657370517928, | |
| "grad_norm": 11.721458435058594, | |
| "learning_rate": 8.804780876494024e-05, | |
| "loss": 0.6502, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.9840637450199203, | |
| "grad_norm": 11.902241706848145, | |
| "learning_rate": 8.671978751660027e-05, | |
| "loss": 0.6391, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.624, | |
| "eval_f1": 0.6176260916415671, | |
| "eval_loss": 0.8131240010261536, | |
| "eval_precision": 0.6213088498802785, | |
| "eval_recall": 0.6225291409540601, | |
| "eval_runtime": 16.9186, | |
| "eval_samples_per_second": 29.553, | |
| "eval_steps_per_second": 3.724, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 4.382470119521912, | |
| "grad_norm": 11.794739723205566, | |
| "learning_rate": 8.539176626826029e-05, | |
| "loss": 0.5683, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.780876494023905, | |
| "grad_norm": 11.683808326721191, | |
| "learning_rate": 8.406374501992032e-05, | |
| "loss": 0.5691, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.622, | |
| "eval_f1": 0.5716700610476999, | |
| "eval_loss": 0.8928351998329163, | |
| "eval_precision": 0.6410496659546192, | |
| "eval_recall": 0.6199959090306707, | |
| "eval_runtime": 16.6354, | |
| "eval_samples_per_second": 30.056, | |
| "eval_steps_per_second": 3.787, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 5.179282868525896, | |
| "grad_norm": 13.705164909362793, | |
| "learning_rate": 8.273572377158035e-05, | |
| "loss": 0.5855, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.577689243027889, | |
| "grad_norm": 11.817400932312012, | |
| "learning_rate": 8.140770252324038e-05, | |
| "loss": 0.513, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.9760956175298805, | |
| "grad_norm": 11.755231857299805, | |
| "learning_rate": 8.00796812749004e-05, | |
| "loss": 0.5009, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.656, | |
| "eval_f1": 0.6379970132206839, | |
| "eval_loss": 0.8215978741645813, | |
| "eval_precision": 0.6485419139105967, | |
| "eval_recall": 0.6545787165880164, | |
| "eval_runtime": 17.7464, | |
| "eval_samples_per_second": 28.175, | |
| "eval_steps_per_second": 3.55, | |
| "step": 1506 | |
| }, | |
| { | |
| "epoch": 6.374501992031872, | |
| "grad_norm": 10.913691520690918, | |
| "learning_rate": 7.875166002656043e-05, | |
| "loss": 0.4488, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.772908366533865, | |
| "grad_norm": 10.615025520324707, | |
| "learning_rate": 7.742363877822046e-05, | |
| "loss": 0.4855, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.654, | |
| "eval_f1": 0.6439337408377656, | |
| "eval_loss": 0.8311923742294312, | |
| "eval_precision": 0.6495670995670996, | |
| "eval_recall": 0.6520354012895196, | |
| "eval_runtime": 17.519, | |
| "eval_samples_per_second": 28.54, | |
| "eval_steps_per_second": 3.596, | |
| "step": 1757 | |
| }, | |
| { | |
| "epoch": 7.171314741035856, | |
| "grad_norm": 12.026023864746094, | |
| "learning_rate": 7.609561752988048e-05, | |
| "loss": 0.4177, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7.569721115537849, | |
| "grad_norm": 10.010376930236816, | |
| "learning_rate": 7.476759628154051e-05, | |
| "loss": 0.409, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.968127490039841, | |
| "grad_norm": 12.596341133117676, | |
| "learning_rate": 7.343957503320054e-05, | |
| "loss": 0.39, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.682, | |
| "eval_f1": 0.6538606492353024, | |
| "eval_loss": 0.9214051365852356, | |
| "eval_precision": 0.7101278814728985, | |
| "eval_recall": 0.6804800262743945, | |
| "eval_runtime": 17.2651, | |
| "eval_samples_per_second": 28.96, | |
| "eval_steps_per_second": 3.649, | |
| "step": 2008 | |
| }, | |
| { | |
| "epoch": 8.366533864541832, | |
| "grad_norm": 14.169309616088867, | |
| "learning_rate": 7.211155378486057e-05, | |
| "loss": 0.3646, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.764940239043824, | |
| "grad_norm": 12.020890235900879, | |
| "learning_rate": 7.07835325365206e-05, | |
| "loss": 0.3708, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.598, | |
| "eval_f1": 0.5725541685903895, | |
| "eval_loss": 1.0422428846359253, | |
| "eval_precision": 0.6090800979488745, | |
| "eval_recall": 0.5948744763847355, | |
| "eval_runtime": 17.2984, | |
| "eval_samples_per_second": 28.904, | |
| "eval_steps_per_second": 3.642, | |
| "step": 2259 | |
| }, | |
| { | |
| "epoch": 9.163346613545817, | |
| "grad_norm": 10.583425521850586, | |
| "learning_rate": 6.945551128818062e-05, | |
| "loss": 0.3533, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9.56175298804781, | |
| "grad_norm": 13.7178316116333, | |
| "learning_rate": 6.812749003984064e-05, | |
| "loss": 0.2984, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.9601593625498, | |
| "grad_norm": 10.42063045501709, | |
| "learning_rate": 6.679946879150066e-05, | |
| "loss": 0.3328, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.718, | |
| "eval_f1": 0.715429962270956, | |
| "eval_loss": 0.7483692765235901, | |
| "eval_precision": 0.7195966559320596, | |
| "eval_recall": 0.7178075285359515, | |
| "eval_runtime": 17.492, | |
| "eval_samples_per_second": 28.584, | |
| "eval_steps_per_second": 3.602, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 10.358565737051793, | |
| "grad_norm": 10.752534866333008, | |
| "learning_rate": 6.547144754316069e-05, | |
| "loss": 0.2561, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 10.756972111553784, | |
| "grad_norm": 10.988365173339844, | |
| "learning_rate": 6.414342629482072e-05, | |
| "loss": 0.3092, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.72, | |
| "eval_f1": 0.7160176967190494, | |
| "eval_loss": 0.8250208497047424, | |
| "eval_precision": 0.7184132303947973, | |
| "eval_recall": 0.7186398391269527, | |
| "eval_runtime": 17.2463, | |
| "eval_samples_per_second": 28.992, | |
| "eval_steps_per_second": 3.653, | |
| "step": 2761 | |
| }, | |
| { | |
| "epoch": 11.155378486055778, | |
| "grad_norm": 10.967025756835938, | |
| "learning_rate": 6.281540504648075e-05, | |
| "loss": 0.28, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11.55378486055777, | |
| "grad_norm": 11.933313369750977, | |
| "learning_rate": 6.148738379814077e-05, | |
| "loss": 0.2747, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 11.952191235059761, | |
| "grad_norm": 12.90857219696045, | |
| "learning_rate": 6.01593625498008e-05, | |
| "loss": 0.281, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.694, | |
| "eval_f1": 0.6781251589992235, | |
| "eval_loss": 0.9806899428367615, | |
| "eval_precision": 0.6976797604396068, | |
| "eval_recall": 0.6921398650556313, | |
| "eval_runtime": 17.2981, | |
| "eval_samples_per_second": 28.905, | |
| "eval_steps_per_second": 3.642, | |
| "step": 3012 | |
| }, | |
| { | |
| "epoch": 12.350597609561753, | |
| "grad_norm": 11.363082885742188, | |
| "learning_rate": 5.883134130146083e-05, | |
| "loss": 0.2596, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 12.749003984063744, | |
| "grad_norm": 12.736093521118164, | |
| "learning_rate": 5.7503320053120855e-05, | |
| "loss": 0.2162, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.708, | |
| "eval_f1": 0.7021505447248022, | |
| "eval_loss": 0.9850034117698669, | |
| "eval_precision": 0.7101112865680695, | |
| "eval_recall": 0.7063781669000248, | |
| "eval_runtime": 17.6848, | |
| "eval_samples_per_second": 28.273, | |
| "eval_steps_per_second": 3.562, | |
| "step": 3263 | |
| }, | |
| { | |
| "epoch": 13.147410358565738, | |
| "grad_norm": 11.957535743713379, | |
| "learning_rate": 5.6175298804780876e-05, | |
| "loss": 0.2271, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 13.54581673306773, | |
| "grad_norm": 13.91019058227539, | |
| "learning_rate": 5.48472775564409e-05, | |
| "loss": 0.2284, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 13.944223107569721, | |
| "grad_norm": 10.606439590454102, | |
| "learning_rate": 5.351925630810093e-05, | |
| "loss": 0.2352, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.698, | |
| "eval_f1": 0.6875106838790609, | |
| "eval_loss": 0.9122900366783142, | |
| "eval_precision": 0.6937544840437923, | |
| "eval_recall": 0.6964621758194903, | |
| "eval_runtime": 17.3918, | |
| "eval_samples_per_second": 28.749, | |
| "eval_steps_per_second": 3.622, | |
| "step": 3514 | |
| }, | |
| { | |
| "epoch": 14.342629482071713, | |
| "grad_norm": 10.729408264160156, | |
| "learning_rate": 5.219123505976096e-05, | |
| "loss": 0.2339, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 14.741035856573705, | |
| "grad_norm": 10.717667579650879, | |
| "learning_rate": 5.0863213811420985e-05, | |
| "loss": 0.1947, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.694, | |
| "eval_f1": 0.6847697638967624, | |
| "eval_loss": 1.0269464254379272, | |
| "eval_precision": 0.6984319398216817, | |
| "eval_recall": 0.6918425495381815, | |
| "eval_runtime": 17.3612, | |
| "eval_samples_per_second": 28.8, | |
| "eval_steps_per_second": 3.629, | |
| "step": 3765 | |
| }, | |
| { | |
| "epoch": 15.139442231075698, | |
| "grad_norm": 15.637863159179688, | |
| "learning_rate": 4.953519256308101e-05, | |
| "loss": 0.2033, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 15.53784860557769, | |
| "grad_norm": 11.52315902709961, | |
| "learning_rate": 4.820717131474104e-05, | |
| "loss": 0.2073, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 15.936254980079681, | |
| "grad_norm": 10.585031509399414, | |
| "learning_rate": 4.687915006640107e-05, | |
| "loss": 0.1902, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.702, | |
| "eval_f1": 0.6936988146223305, | |
| "eval_loss": 1.0092582702636719, | |
| "eval_precision": 0.704450992084371, | |
| "eval_recall": 0.6998746780522377, | |
| "eval_runtime": 17.2437, | |
| "eval_samples_per_second": 28.996, | |
| "eval_steps_per_second": 3.654, | |
| "step": 4016 | |
| }, | |
| { | |
| "epoch": 16.334661354581673, | |
| "grad_norm": 13.553791046142578, | |
| "learning_rate": 4.555112881806109e-05, | |
| "loss": 0.1961, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 16.733067729083665, | |
| "grad_norm": 10.33850383758545, | |
| "learning_rate": 4.4223107569721116e-05, | |
| "loss": 0.1912, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.712, | |
| "eval_f1": 0.7037256290589013, | |
| "eval_loss": 0.9451501369476318, | |
| "eval_precision": 0.7113280708081392, | |
| "eval_recall": 0.710350440499444, | |
| "eval_runtime": 17.5777, | |
| "eval_samples_per_second": 28.445, | |
| "eval_steps_per_second": 3.584, | |
| "step": 4267 | |
| }, | |
| { | |
| "epoch": 17.131474103585656, | |
| "grad_norm": 10.550813674926758, | |
| "learning_rate": 4.289508632138114e-05, | |
| "loss": 0.1724, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 17.529880478087648, | |
| "grad_norm": 11.269770622253418, | |
| "learning_rate": 4.156706507304117e-05, | |
| "loss": 0.166, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 17.92828685258964, | |
| "grad_norm": 11.22702693939209, | |
| "learning_rate": 4.02390438247012e-05, | |
| "loss": 0.1626, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.71, | |
| "eval_f1": 0.6965991557822268, | |
| "eval_loss": 1.0229520797729492, | |
| "eval_precision": 0.7119117791531585, | |
| "eval_recall": 0.7080606500607883, | |
| "eval_runtime": 17.3563, | |
| "eval_samples_per_second": 28.808, | |
| "eval_steps_per_second": 3.63, | |
| "step": 4518 | |
| }, | |
| { | |
| "epoch": 18.326693227091635, | |
| "grad_norm": 11.750710487365723, | |
| "learning_rate": 3.8911022576361225e-05, | |
| "loss": 0.146, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 18.725099601593627, | |
| "grad_norm": 10.37628173828125, | |
| "learning_rate": 3.758300132802125e-05, | |
| "loss": 0.1524, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.716, | |
| "eval_f1": 0.7120852228214192, | |
| "eval_loss": 0.9977978467941284, | |
| "eval_precision": 0.7210033022533023, | |
| "eval_recall": 0.7144085668354911, | |
| "eval_runtime": 17.5249, | |
| "eval_samples_per_second": 28.531, | |
| "eval_steps_per_second": 3.595, | |
| "step": 4769 | |
| }, | |
| { | |
| "epoch": 19.12350597609562, | |
| "grad_norm": 12.99516487121582, | |
| "learning_rate": 3.625498007968128e-05, | |
| "loss": 0.1321, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 19.52191235059761, | |
| "grad_norm": 11.697456359863281, | |
| "learning_rate": 3.492695883134131e-05, | |
| "loss": 0.1508, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 19.9203187250996, | |
| "grad_norm": 11.452008247375488, | |
| "learning_rate": 3.359893758300133e-05, | |
| "loss": 0.1258, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.71, | |
| "eval_f1": 0.7074786456937486, | |
| "eval_loss": 1.050653338432312, | |
| "eval_precision": 0.7215994120996662, | |
| "eval_recall": 0.7083547965174904, | |
| "eval_runtime": 29.4041, | |
| "eval_samples_per_second": 17.004, | |
| "eval_steps_per_second": 2.143, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 20.318725099601593, | |
| "grad_norm": 12.027978897094727, | |
| "learning_rate": 3.2270916334661356e-05, | |
| "loss": 0.1387, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 20.717131474103585, | |
| "grad_norm": 13.427599906921387, | |
| "learning_rate": 3.094289508632138e-05, | |
| "loss": 0.1116, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.724, | |
| "eval_f1": 0.7153409174915838, | |
| "eval_loss": 1.0689764022827148, | |
| "eval_precision": 0.7231692880094706, | |
| "eval_recall": 0.722209642011374, | |
| "eval_runtime": 17.4789, | |
| "eval_samples_per_second": 28.606, | |
| "eval_steps_per_second": 3.604, | |
| "step": 5271 | |
| }, | |
| { | |
| "epoch": 21.115537848605577, | |
| "grad_norm": 12.410263061523438, | |
| "learning_rate": 2.961487383798141e-05, | |
| "loss": 0.1378, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 21.51394422310757, | |
| "grad_norm": 12.236252784729004, | |
| "learning_rate": 2.8286852589641438e-05, | |
| "loss": 0.1181, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 21.91235059760956, | |
| "grad_norm": 11.362260818481445, | |
| "learning_rate": 2.6958831341301462e-05, | |
| "loss": 0.1158, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.702, | |
| "eval_f1": 0.6967439243675191, | |
| "eval_loss": 1.1378962993621826, | |
| "eval_precision": 0.7034445997704206, | |
| "eval_recall": 0.7004485661440597, | |
| "eval_runtime": 17.752, | |
| "eval_samples_per_second": 28.166, | |
| "eval_steps_per_second": 3.549, | |
| "step": 5522 | |
| }, | |
| { | |
| "epoch": 22.310756972111555, | |
| "grad_norm": 12.567873001098633, | |
| "learning_rate": 2.563081009296149e-05, | |
| "loss": 0.1089, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 22.709163346613547, | |
| "grad_norm": 10.872307777404785, | |
| "learning_rate": 2.4302788844621517e-05, | |
| "loss": 0.1069, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.722, | |
| "eval_f1": 0.7172758119553166, | |
| "eval_loss": 1.157360553741455, | |
| "eval_precision": 0.727205590108816, | |
| "eval_recall": 0.7205813209797584, | |
| "eval_runtime": 17.8753, | |
| "eval_samples_per_second": 27.972, | |
| "eval_steps_per_second": 3.524, | |
| "step": 5773 | |
| }, | |
| { | |
| "epoch": 23.10756972111554, | |
| "grad_norm": 10.918773651123047, | |
| "learning_rate": 2.297476759628154e-05, | |
| "loss": 0.1112, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 23.50597609561753, | |
| "grad_norm": 11.303016662597656, | |
| "learning_rate": 2.1646746347941568e-05, | |
| "loss": 0.0954, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 23.904382470119522, | |
| "grad_norm": 10.82700252532959, | |
| "learning_rate": 2.0318725099601595e-05, | |
| "loss": 0.1089, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.712, | |
| "eval_f1": 0.7075426800060708, | |
| "eval_loss": 1.1160012483596802, | |
| "eval_precision": 0.7194793034050283, | |
| "eval_recall": 0.7103697429603638, | |
| "eval_runtime": 17.7441, | |
| "eval_samples_per_second": 28.178, | |
| "eval_steps_per_second": 3.55, | |
| "step": 6024 | |
| }, | |
| { | |
| "epoch": 24.302788844621514, | |
| "grad_norm": 10.5631742477417, | |
| "learning_rate": 1.899070385126162e-05, | |
| "loss": 0.0864, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 24.701195219123505, | |
| "grad_norm": 10.918201446533203, | |
| "learning_rate": 1.7662682602921647e-05, | |
| "loss": 0.0999, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.716, | |
| "eval_f1": 0.7090935362771184, | |
| "eval_loss": 1.0727450847625732, | |
| "eval_precision": 0.7106284520077623, | |
| "eval_recall": 0.7145099767794276, | |
| "eval_runtime": 17.8845, | |
| "eval_samples_per_second": 27.957, | |
| "eval_steps_per_second": 3.523, | |
| "step": 6275 | |
| }, | |
| { | |
| "epoch": 25.099601593625497, | |
| "grad_norm": 11.402228355407715, | |
| "learning_rate": 1.6334661354581674e-05, | |
| "loss": 0.1042, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 25.49800796812749, | |
| "grad_norm": 11.740915298461914, | |
| "learning_rate": 1.5006640106241702e-05, | |
| "loss": 0.089, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 25.89641434262948, | |
| "grad_norm": 11.218791961669922, | |
| "learning_rate": 1.3678618857901726e-05, | |
| "loss": 0.0738, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.706, | |
| "eval_f1": 0.699550751079995, | |
| "eval_loss": 1.2584666013717651, | |
| "eval_precision": 0.7133200179296525, | |
| "eval_recall": 0.704105950343699, | |
| "eval_runtime": 18.0765, | |
| "eval_samples_per_second": 27.66, | |
| "eval_steps_per_second": 3.485, | |
| "step": 6526 | |
| }, | |
| { | |
| "epoch": 26.294820717131476, | |
| "grad_norm": 9.9302339553833, | |
| "learning_rate": 1.2350597609561753e-05, | |
| "loss": 0.0914, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 26.693227091633467, | |
| "grad_norm": 11.051177024841309, | |
| "learning_rate": 1.102257636122178e-05, | |
| "loss": 0.0836, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.718, | |
| "eval_f1": 0.7104355302219595, | |
| "eval_loss": 1.1709084510803223, | |
| "eval_precision": 0.7172922964310544, | |
| "eval_recall": 0.7163028008735083, | |
| "eval_runtime": 17.5336, | |
| "eval_samples_per_second": 28.517, | |
| "eval_steps_per_second": 3.593, | |
| "step": 6777 | |
| }, | |
| { | |
| "epoch": 27.09163346613546, | |
| "grad_norm": 10.727697372436523, | |
| "learning_rate": 9.694555112881806e-06, | |
| "loss": 0.0986, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 27.49003984063745, | |
| "grad_norm": 11.817888259887695, | |
| "learning_rate": 8.366533864541832e-06, | |
| "loss": 0.07, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 27.888446215139442, | |
| "grad_norm": 10.357769966125488, | |
| "learning_rate": 7.03851261620186e-06, | |
| "loss": 0.0775, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.722, | |
| "eval_f1": 0.7145836341124611, | |
| "eval_loss": 1.2422434091567993, | |
| "eval_precision": 0.7256025662918439, | |
| "eval_recall": 0.720296105512437, | |
| "eval_runtime": 17.5709, | |
| "eval_samples_per_second": 28.456, | |
| "eval_steps_per_second": 3.585, | |
| "step": 7028 | |
| }, | |
| { | |
| "epoch": 28.286852589641434, | |
| "grad_norm": 10.4796142578125, | |
| "learning_rate": 5.710491367861886e-06, | |
| "loss": 0.0713, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 28.685258964143426, | |
| "grad_norm": 9.803996086120605, | |
| "learning_rate": 4.382470119521913e-06, | |
| "loss": 0.0752, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.728, | |
| "eval_f1": 0.7205734767025089, | |
| "eval_loss": 1.2145317792892456, | |
| "eval_precision": 0.730059540405073, | |
| "eval_recall": 0.7263936664880468, | |
| "eval_runtime": 17.625, | |
| "eval_samples_per_second": 28.369, | |
| "eval_steps_per_second": 3.574, | |
| "step": 7279 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 7530, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "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": 8.995893225012062e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |