| { | |
| "best_metric": 0.9841269841269842, | |
| "best_model_checkpoint": "teacher-status-van-tiny-256/checkpoint-187", | |
| "epoch": 28.8, | |
| "eval_steps": 500, | |
| "global_step": 360, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.6928, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.6685393258426966, | |
| "eval_f1_score": 0.7630522088353413, | |
| "eval_loss": 0.6904417276382446, | |
| "eval_precision": 0.6168831168831169, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.2798, | |
| "eval_samples_per_second": 139.083, | |
| "eval_steps_per_second": 4.688, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.6893, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5393258426966292, | |
| "eval_f1_score": 0.698529411764706, | |
| "eval_loss": 0.6683324575424194, | |
| "eval_precision": 0.536723163841808, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.0413, | |
| "eval_samples_per_second": 170.94, | |
| "eval_steps_per_second": 5.762, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6726, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.5842696629213483, | |
| "eval_f1_score": 0.7196969696969697, | |
| "eval_loss": 0.5703710913658142, | |
| "eval_precision": 0.5621301775147929, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.3234, | |
| "eval_samples_per_second": 134.506, | |
| "eval_steps_per_second": 4.534, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.6047, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.783950617283951e-05, | |
| "loss": 0.5295, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9213483146067416, | |
| "eval_f1_score": 0.9263157894736842, | |
| "eval_loss": 0.4148499667644501, | |
| "eval_precision": 0.9263157894736842, | |
| "eval_recall": 0.9263157894736842, | |
| "eval_runtime": 1.0116, | |
| "eval_samples_per_second": 175.963, | |
| "eval_steps_per_second": 5.931, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.4745, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_accuracy": 0.9382022471910112, | |
| "eval_f1_score": 0.9430051813471502, | |
| "eval_loss": 0.31081339716911316, | |
| "eval_precision": 0.9285714285714286, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.3432, | |
| "eval_samples_per_second": 132.515, | |
| "eval_steps_per_second": 4.467, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.4753086419753084e-05, | |
| "loss": 0.4206, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9438202247191011, | |
| "eval_f1_score": 0.9473684210526315, | |
| "eval_loss": 0.2301165908575058, | |
| "eval_precision": 0.9473684210526315, | |
| "eval_recall": 0.9473684210526315, | |
| "eval_runtime": 1.0463, | |
| "eval_samples_per_second": 170.129, | |
| "eval_steps_per_second": 5.735, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.3898, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_accuracy": 0.949438202247191, | |
| "eval_f1_score": 0.9518716577540107, | |
| "eval_loss": 0.1820228397846222, | |
| "eval_precision": 0.967391304347826, | |
| "eval_recall": 0.9368421052631579, | |
| "eval_runtime": 1.0432, | |
| "eval_samples_per_second": 170.633, | |
| "eval_steps_per_second": 5.752, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.3557, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.3153, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.949438202247191, | |
| "eval_f1_score": 0.9538461538461539, | |
| "eval_loss": 0.1545208990573883, | |
| "eval_precision": 0.93, | |
| "eval_recall": 0.9789473684210527, | |
| "eval_runtime": 1.2226, | |
| "eval_samples_per_second": 145.595, | |
| "eval_steps_per_second": 4.908, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 3.8580246913580246e-05, | |
| "loss": 0.3077, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_accuracy": 0.9606741573033708, | |
| "eval_f1_score": 0.9621621621621621, | |
| "eval_loss": 0.1521005630493164, | |
| "eval_precision": 0.9888888888888889, | |
| "eval_recall": 0.9368421052631579, | |
| "eval_runtime": 1.2664, | |
| "eval_samples_per_second": 140.559, | |
| "eval_steps_per_second": 4.738, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3048, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9606741573033708, | |
| "eval_f1_score": 0.9625668449197862, | |
| "eval_loss": 0.133090078830719, | |
| "eval_precision": 0.9782608695652174, | |
| "eval_recall": 0.9473684210526315, | |
| "eval_runtime": 1.032, | |
| "eval_samples_per_second": 172.478, | |
| "eval_steps_per_second": 5.814, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 3.5493827160493834e-05, | |
| "loss": 0.3004, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "eval_accuracy": 0.9606741573033708, | |
| "eval_f1_score": 0.9633507853403142, | |
| "eval_loss": 0.13144755363464355, | |
| "eval_precision": 0.9583333333333334, | |
| "eval_recall": 0.968421052631579, | |
| "eval_runtime": 1.0224, | |
| "eval_samples_per_second": 174.103, | |
| "eval_steps_per_second": 5.869, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.2685, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.2839, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9606741573033708, | |
| "eval_f1_score": 0.9621621621621621, | |
| "eval_loss": 0.1272086501121521, | |
| "eval_precision": 0.9888888888888889, | |
| "eval_recall": 0.9368421052631579, | |
| "eval_runtime": 1.0248, | |
| "eval_samples_per_second": 173.691, | |
| "eval_steps_per_second": 5.855, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.286, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "eval_accuracy": 0.9606741573033708, | |
| "eval_f1_score": 0.9621621621621621, | |
| "eval_loss": 0.11889710277318954, | |
| "eval_precision": 0.9888888888888889, | |
| "eval_recall": 0.9368421052631579, | |
| "eval_runtime": 1.0343, | |
| "eval_samples_per_second": 172.102, | |
| "eval_steps_per_second": 5.801, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 2.9320987654320992e-05, | |
| "loss": 0.2473, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9719101123595506, | |
| "eval_f1_score": 0.9732620320855614, | |
| "eval_loss": 0.09774552285671234, | |
| "eval_precision": 0.9891304347826086, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.2533, | |
| "eval_samples_per_second": 142.026, | |
| "eval_steps_per_second": 4.787, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2774, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "eval_accuracy": 0.9831460674157303, | |
| "eval_f1_score": 0.9841269841269842, | |
| "eval_loss": 0.09884575009346008, | |
| "eval_precision": 0.9893617021276596, | |
| "eval_recall": 0.9789473684210527, | |
| "eval_runtime": 1.2659, | |
| "eval_samples_per_second": 140.612, | |
| "eval_steps_per_second": 4.74, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.623456790123457e-05, | |
| "loss": 0.2733, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.2541, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9719101123595506, | |
| "eval_f1_score": 0.9732620320855614, | |
| "eval_loss": 0.09689934551715851, | |
| "eval_precision": 0.9891304347826086, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.0329, | |
| "eval_samples_per_second": 172.331, | |
| "eval_steps_per_second": 5.809, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.2383, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "eval_accuracy": 0.9719101123595506, | |
| "eval_f1_score": 0.9732620320855614, | |
| "eval_loss": 0.10420462489128113, | |
| "eval_precision": 0.9891304347826086, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.0218, | |
| "eval_samples_per_second": 174.204, | |
| "eval_steps_per_second": 5.872, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.2552, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9719101123595506, | |
| "eval_f1_score": 0.9732620320855614, | |
| "eval_loss": 0.10807426273822784, | |
| "eval_precision": 0.9891304347826086, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.0141, | |
| "eval_samples_per_second": 175.532, | |
| "eval_steps_per_second": 5.917, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 2.006172839506173e-05, | |
| "loss": 0.2223, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 18.96, | |
| "eval_accuracy": 0.9662921348314607, | |
| "eval_f1_score": 0.9680851063829788, | |
| "eval_loss": 0.11498517543077469, | |
| "eval_precision": 0.978494623655914, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.0007, | |
| "eval_samples_per_second": 177.868, | |
| "eval_steps_per_second": 5.996, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2364, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.697530864197531e-05, | |
| "loss": 0.2561, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9550561797752809, | |
| "eval_f1_score": 0.9574468085106383, | |
| "eval_loss": 0.12337563186883926, | |
| "eval_precision": 0.967741935483871, | |
| "eval_recall": 0.9473684210526315, | |
| "eval_runtime": 1.025, | |
| "eval_samples_per_second": 173.653, | |
| "eval_steps_per_second": 5.853, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 0.2462, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "eval_accuracy": 0.9606741573033708, | |
| "eval_f1_score": 0.962962962962963, | |
| "eval_loss": 0.11782826483249664, | |
| "eval_precision": 0.9680851063829787, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.277, | |
| "eval_samples_per_second": 139.389, | |
| "eval_steps_per_second": 4.698, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.2294, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9382022471910112, | |
| "eval_f1_score": 0.9430051813471502, | |
| "eval_loss": 0.12620893120765686, | |
| "eval_precision": 0.9285714285714286, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.0278, | |
| "eval_samples_per_second": 173.184, | |
| "eval_steps_per_second": 5.838, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.2296, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "eval_accuracy": 0.9438202247191011, | |
| "eval_f1_score": 0.9479166666666666, | |
| "eval_loss": 0.12900537252426147, | |
| "eval_precision": 0.9381443298969072, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.0136, | |
| "eval_samples_per_second": 175.614, | |
| "eval_steps_per_second": 5.92, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 1.0802469135802469e-05, | |
| "loss": 0.2351, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.2224, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.949438202247191, | |
| "eval_f1_score": 0.9528795811518324, | |
| "eval_loss": 0.1152968481183052, | |
| "eval_precision": 0.9479166666666666, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.0182, | |
| "eval_samples_per_second": 174.822, | |
| "eval_steps_per_second": 5.893, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 7.71604938271605e-06, | |
| "loss": 0.2205, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "eval_accuracy": 0.949438202247191, | |
| "eval_f1_score": 0.9528795811518324, | |
| "eval_loss": 0.11498025059700012, | |
| "eval_precision": 0.9479166666666666, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.0221, | |
| "eval_samples_per_second": 174.15, | |
| "eval_steps_per_second": 5.87, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.2169, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9550561797752809, | |
| "eval_f1_score": 0.9574468085106383, | |
| "eval_loss": 0.1120525524020195, | |
| "eval_precision": 0.967741935483871, | |
| "eval_recall": 0.9473684210526315, | |
| "eval_runtime": 1.0268, | |
| "eval_samples_per_second": 173.35, | |
| "eval_steps_per_second": 5.843, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.2212, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 26.96, | |
| "eval_accuracy": 0.949438202247191, | |
| "eval_f1_score": 0.9528795811518324, | |
| "eval_loss": 0.11452833563089371, | |
| "eval_precision": 0.9479166666666666, | |
| "eval_recall": 0.9578947368421052, | |
| "eval_runtime": 1.951, | |
| "eval_samples_per_second": 91.236, | |
| "eval_steps_per_second": 3.075, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.2265, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 1.5432098765432098e-06, | |
| "loss": 0.2188, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.949438202247191, | |
| "eval_f1_score": 0.9523809523809523, | |
| "eval_loss": 0.11309711635112762, | |
| "eval_precision": 0.9574468085106383, | |
| "eval_recall": 0.9473684210526315, | |
| "eval_runtime": 1.0255, | |
| "eval_samples_per_second": 173.568, | |
| "eval_steps_per_second": 5.851, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 0.0, | |
| "loss": 0.2015, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "eval_accuracy": 0.949438202247191, | |
| "eval_f1_score": 0.9523809523809523, | |
| "eval_loss": 0.11295311897993088, | |
| "eval_precision": 0.9574468085106383, | |
| "eval_recall": 0.9473684210526315, | |
| "eval_runtime": 1.3178, | |
| "eval_samples_per_second": 135.073, | |
| "eval_steps_per_second": 4.553, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "step": 360, | |
| "total_flos": 2.0837941191062323e+17, | |
| "train_loss": 0.3229101174407535, | |
| "train_runtime": 715.5601, | |
| "train_samples_per_second": 66.787, | |
| "train_steps_per_second": 0.503 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 360, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 2.0837941191062323e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |