| { | |
| "best_metric": 0.511543134872418, | |
| "best_model_checkpoint": "/content/our_data/checkpoint-9500", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 12410, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.91941982272361e-05, | |
| "loss": 1.7886, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.6168970448045757, | |
| "eval_f1": 0.19641754169240272, | |
| "eval_loss": 1.5075236558914185, | |
| "eval_precision": 0.1842410196987254, | |
| "eval_recall": 0.21031746031746032, | |
| "eval_runtime": 4.697, | |
| "eval_samples_per_second": 64.723, | |
| "eval_steps_per_second": 32.361, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.83883964544722e-05, | |
| "loss": 1.3644, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.6491897044804575, | |
| "eval_f1": 0.26658972879399884, | |
| "eval_loss": 1.3342480659484863, | |
| "eval_precision": 0.23643807574206754, | |
| "eval_recall": 0.3055555555555556, | |
| "eval_runtime": 3.8755, | |
| "eval_samples_per_second": 78.442, | |
| "eval_steps_per_second": 39.221, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.75825946817083e-05, | |
| "loss": 1.1181, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_accuracy": 0.6812440419447092, | |
| "eval_f1": 0.3241626794258373, | |
| "eval_loss": 1.2655349969863892, | |
| "eval_precision": 0.29585152838427947, | |
| "eval_recall": 0.3584656084656085, | |
| "eval_runtime": 4.9077, | |
| "eval_samples_per_second": 61.944, | |
| "eval_steps_per_second": 30.972, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 1.67767929089444e-05, | |
| "loss": 0.9833, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_accuracy": 0.6777883698760725, | |
| "eval_f1": 0.33541785105173394, | |
| "eval_loss": 1.2368232011795044, | |
| "eval_precision": 0.29411764705882354, | |
| "eval_recall": 0.39021164021164023, | |
| "eval_runtime": 4.7308, | |
| "eval_samples_per_second": 64.26, | |
| "eval_steps_per_second": 32.13, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.59709911361805e-05, | |
| "loss": 0.9036, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_accuracy": 0.7023355576739753, | |
| "eval_f1": 0.37717121588089325, | |
| "eval_loss": 1.268211007118225, | |
| "eval_precision": 0.35514018691588783, | |
| "eval_recall": 0.4021164021164021, | |
| "eval_runtime": 3.7593, | |
| "eval_samples_per_second": 80.867, | |
| "eval_steps_per_second": 40.434, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.5165189363416601e-05, | |
| "loss": 0.7102, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_accuracy": 0.7159199237368923, | |
| "eval_f1": 0.40775558166862513, | |
| "eval_loss": 1.2175697088241577, | |
| "eval_precision": 0.3668076109936575, | |
| "eval_recall": 0.458994708994709, | |
| "eval_runtime": 4.1645, | |
| "eval_samples_per_second": 72.998, | |
| "eval_steps_per_second": 36.499, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.4359387590652701e-05, | |
| "loss": 0.6868, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_accuracy": 0.7147283126787417, | |
| "eval_f1": 0.41918294849023086, | |
| "eval_loss": 1.2170379161834717, | |
| "eval_precision": 0.37942122186495175, | |
| "eval_recall": 0.46825396825396826, | |
| "eval_runtime": 4.987, | |
| "eval_samples_per_second": 60.958, | |
| "eval_steps_per_second": 30.479, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.35535858178888e-05, | |
| "loss": 0.5671, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "eval_accuracy": 0.7259294566253575, | |
| "eval_f1": 0.4366863905325444, | |
| "eval_loss": 1.2602918148040771, | |
| "eval_precision": 0.3950749464668094, | |
| "eval_recall": 0.4880952380952381, | |
| "eval_runtime": 3.9634, | |
| "eval_samples_per_second": 76.702, | |
| "eval_steps_per_second": 38.351, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.27477840451249e-05, | |
| "loss": 0.4878, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "eval_accuracy": 0.7333174451858914, | |
| "eval_f1": 0.4432930339666091, | |
| "eval_loss": 1.2460124492645264, | |
| "eval_precision": 0.3924566768603466, | |
| "eval_recall": 0.5092592592592593, | |
| "eval_runtime": 5.1761, | |
| "eval_samples_per_second": 58.732, | |
| "eval_steps_per_second": 29.366, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 1.1941982272361e-05, | |
| "loss": 0.4942, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_accuracy": 0.7284318398474738, | |
| "eval_f1": 0.43920145190562615, | |
| "eval_loss": 1.314683198928833, | |
| "eval_precision": 0.40468227424749165, | |
| "eval_recall": 0.4801587301587302, | |
| "eval_runtime": 3.8399, | |
| "eval_samples_per_second": 79.169, | |
| "eval_steps_per_second": 39.585, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 1.11361804995971e-05, | |
| "loss": 0.3812, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_accuracy": 0.7351048617731173, | |
| "eval_f1": 0.46281975014872095, | |
| "eval_loss": 1.3308484554290771, | |
| "eval_precision": 0.4205405405405405, | |
| "eval_recall": 0.5145502645502645, | |
| "eval_runtime": 4.4524, | |
| "eval_samples_per_second": 68.278, | |
| "eval_steps_per_second": 34.139, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 1.0330378726833199e-05, | |
| "loss": 0.421, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_accuracy": 0.738560533841754, | |
| "eval_f1": 0.4702380952380952, | |
| "eval_loss": 1.3030654191970825, | |
| "eval_precision": 0.4274891774891775, | |
| "eval_recall": 0.5224867724867724, | |
| "eval_runtime": 4.5652, | |
| "eval_samples_per_second": 66.59, | |
| "eval_steps_per_second": 33.295, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 9.5245769540693e-06, | |
| "loss": 0.3157, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "eval_accuracy": 0.7292659675881792, | |
| "eval_f1": 0.4541120381406436, | |
| "eval_loss": 1.394273042678833, | |
| "eval_precision": 0.41323210412147504, | |
| "eval_recall": 0.503968253968254, | |
| "eval_runtime": 4.8385, | |
| "eval_samples_per_second": 62.83, | |
| "eval_steps_per_second": 31.415, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 8.7187751813054e-06, | |
| "loss": 0.3072, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "eval_accuracy": 0.7396329837940896, | |
| "eval_f1": 0.47030593881223753, | |
| "eval_loss": 1.4086649417877197, | |
| "eval_precision": 0.43029637760702527, | |
| "eval_recall": 0.5185185185185185, | |
| "eval_runtime": 3.6352, | |
| "eval_samples_per_second": 83.626, | |
| "eval_steps_per_second": 41.813, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 7.9129734085415e-06, | |
| "loss": 0.3436, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "eval_accuracy": 0.7362964728312679, | |
| "eval_f1": 0.48238153098420417, | |
| "eval_loss": 1.4196876287460327, | |
| "eval_precision": 0.4460674157303371, | |
| "eval_recall": 0.5251322751322751, | |
| "eval_runtime": 3.9627, | |
| "eval_samples_per_second": 76.716, | |
| "eval_steps_per_second": 38.358, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 7.107171635777599e-06, | |
| "loss": 0.2774, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "eval_accuracy": 0.7377264061010487, | |
| "eval_f1": 0.4702380952380952, | |
| "eval_loss": 1.4248775243759155, | |
| "eval_precision": 0.4274891774891775, | |
| "eval_recall": 0.5224867724867724, | |
| "eval_runtime": 4.1017, | |
| "eval_samples_per_second": 74.116, | |
| "eval_steps_per_second": 37.058, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 6.301369863013699e-06, | |
| "loss": 0.2629, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "eval_accuracy": 0.732721639656816, | |
| "eval_f1": 0.4932844932844933, | |
| "eval_loss": 1.4811160564422607, | |
| "eval_precision": 0.4580498866213152, | |
| "eval_recall": 0.5343915343915344, | |
| "eval_runtime": 3.7972, | |
| "eval_samples_per_second": 80.06, | |
| "eval_steps_per_second": 40.03, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 5.495568090249799e-06, | |
| "loss": 0.2271, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "eval_accuracy": 0.7415395614871306, | |
| "eval_f1": 0.5043263288009888, | |
| "eval_loss": 1.5576499700546265, | |
| "eval_precision": 0.4733178654292343, | |
| "eval_recall": 0.5396825396825397, | |
| "eval_runtime": 3.7692, | |
| "eval_samples_per_second": 80.653, | |
| "eval_steps_per_second": 40.326, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 4.689766317485899e-06, | |
| "loss": 0.235, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "eval_accuracy": 0.7401096282173498, | |
| "eval_f1": 0.511543134872418, | |
| "eval_loss": 1.5468007326126099, | |
| "eval_precision": 0.4730337078651685, | |
| "eval_recall": 0.5568783068783069, | |
| "eval_runtime": 4.6282, | |
| "eval_samples_per_second": 65.684, | |
| "eval_steps_per_second": 32.842, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 3.883964544721999e-06, | |
| "loss": 0.2415, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "eval_accuracy": 0.7433269780743565, | |
| "eval_f1": 0.5058461538461538, | |
| "eval_loss": 1.5955547094345093, | |
| "eval_precision": 0.47295742232451093, | |
| "eval_recall": 0.5436507936507936, | |
| "eval_runtime": 4.7141, | |
| "eval_samples_per_second": 64.487, | |
| "eval_steps_per_second": 32.244, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 3.0781627719580986e-06, | |
| "loss": 0.1826, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_accuracy": 0.7413012392755005, | |
| "eval_f1": 0.48864994026284353, | |
| "eval_loss": 1.616766333580017, | |
| "eval_precision": 0.4455337690631808, | |
| "eval_recall": 0.541005291005291, | |
| "eval_runtime": 4.6222, | |
| "eval_samples_per_second": 65.77, | |
| "eval_steps_per_second": 32.885, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 2.2723609991941985e-06, | |
| "loss": 0.2083, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.7413012392755005, | |
| "eval_f1": 0.49219687875150064, | |
| "eval_loss": 1.5865833759307861, | |
| "eval_precision": 0.45054945054945056, | |
| "eval_recall": 0.5423280423280423, | |
| "eval_runtime": 4.7524, | |
| "eval_samples_per_second": 63.967, | |
| "eval_steps_per_second": 31.984, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 1.4665592264302982e-06, | |
| "loss": 0.2169, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "eval_accuracy": 0.7467826501429933, | |
| "eval_f1": 0.5046040515653776, | |
| "eval_loss": 1.5974096059799194, | |
| "eval_precision": 0.47079037800687284, | |
| "eval_recall": 0.5436507936507936, | |
| "eval_runtime": 3.7982, | |
| "eval_samples_per_second": 80.038, | |
| "eval_steps_per_second": 40.019, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 6.607574536663981e-07, | |
| "loss": 0.1747, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_accuracy": 0.740467111534795, | |
| "eval_f1": 0.4963768115942029, | |
| "eval_loss": 1.6219406127929688, | |
| "eval_precision": 0.45666666666666667, | |
| "eval_recall": 0.5436507936507936, | |
| "eval_runtime": 4.7158, | |
| "eval_samples_per_second": 64.464, | |
| "eval_steps_per_second": 32.232, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 12410, | |
| "total_flos": 499833589185600.0, | |
| "train_loss": 0.5249143927833133, | |
| "train_runtime": 2240.4976, | |
| "train_samples_per_second": 11.073, | |
| "train_steps_per_second": 5.539 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 12410, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 499833589185600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |