| { | |
| "best_metric": 0.5393036603927612, | |
| "best_model_checkpoint": "classify-google-augment/checkpoint-1650", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1650, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015151515151515152, | |
| "grad_norm": 13.14976978302002, | |
| "learning_rate": 7.272727272727272e-06, | |
| "loss": 2.3788, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": 10.54937744140625, | |
| "learning_rate": 1.484848484848485e-05, | |
| "loss": 2.0054, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 13.539351463317871, | |
| "learning_rate": 2.2424242424242424e-05, | |
| "loss": 1.6992, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 15.256404876708984, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7111, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07575757575757576, | |
| "grad_norm": 11.585308074951172, | |
| "learning_rate": 3.757575757575758e-05, | |
| "loss": 1.6489, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 16.133155822753906, | |
| "learning_rate": 4.515151515151516e-05, | |
| "loss": 1.4506, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10606060606060606, | |
| "grad_norm": 14.52907943725586, | |
| "learning_rate": 4.9696969696969694e-05, | |
| "loss": 1.4889, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 11.5184965133667, | |
| "learning_rate": 4.885521885521886e-05, | |
| "loss": 1.732, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 9.789813041687012, | |
| "learning_rate": 4.8013468013468016e-05, | |
| "loss": 1.4171, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.15151515151515152, | |
| "grad_norm": 9.932942390441895, | |
| "learning_rate": 4.7171717171717174e-05, | |
| "loss": 1.2866, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 12.85246753692627, | |
| "learning_rate": 4.632996632996633e-05, | |
| "loss": 1.5966, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 13.539669036865234, | |
| "learning_rate": 4.548821548821549e-05, | |
| "loss": 1.3419, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19696969696969696, | |
| "grad_norm": 8.646981239318848, | |
| "learning_rate": 4.464646464646465e-05, | |
| "loss": 1.3768, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.21212121212121213, | |
| "grad_norm": 10.593306541442871, | |
| "learning_rate": 4.380471380471381e-05, | |
| "loss": 1.3912, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 5.752423286437988, | |
| "learning_rate": 4.296296296296296e-05, | |
| "loss": 1.3558, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 7.588248252868652, | |
| "learning_rate": 4.212121212121212e-05, | |
| "loss": 1.2124, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25757575757575757, | |
| "grad_norm": 10.205862998962402, | |
| "learning_rate": 4.127946127946128e-05, | |
| "loss": 1.0778, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 8.397643089294434, | |
| "learning_rate": 4.043771043771044e-05, | |
| "loss": 1.1563, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.2878787878787879, | |
| "grad_norm": 13.5399169921875, | |
| "learning_rate": 3.9595959595959594e-05, | |
| "loss": 1.1386, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 9.785845756530762, | |
| "learning_rate": 3.875420875420875e-05, | |
| "loss": 1.1826, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3181818181818182, | |
| "grad_norm": 9.576815605163574, | |
| "learning_rate": 3.791245791245792e-05, | |
| "loss": 1.2484, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 10.881918907165527, | |
| "learning_rate": 3.7070707070707075e-05, | |
| "loss": 1.2501, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3484848484848485, | |
| "grad_norm": 4.649813652038574, | |
| "learning_rate": 3.6228956228956226e-05, | |
| "loss": 0.8895, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 5.953652381896973, | |
| "learning_rate": 3.538720538720539e-05, | |
| "loss": 1.1989, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3787878787878788, | |
| "grad_norm": 9.50765609741211, | |
| "learning_rate": 3.454545454545455e-05, | |
| "loss": 1.0395, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.3939393939393939, | |
| "grad_norm": 7.9036126136779785, | |
| "learning_rate": 3.3703703703703706e-05, | |
| "loss": 0.9029, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.4090909090909091, | |
| "grad_norm": 6.874680519104004, | |
| "learning_rate": 3.2861952861952864e-05, | |
| "loss": 1.0177, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 11.416817665100098, | |
| "learning_rate": 3.202020202020202e-05, | |
| "loss": 1.2795, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4393939393939394, | |
| "grad_norm": 7.107864856719971, | |
| "learning_rate": 3.117845117845118e-05, | |
| "loss": 0.9335, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 5.847291469573975, | |
| "learning_rate": 3.0336700336700337e-05, | |
| "loss": 0.8479, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.4696969696969697, | |
| "grad_norm": 8.807320594787598, | |
| "learning_rate": 2.9494949494949498e-05, | |
| "loss": 1.0565, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 9.044240951538086, | |
| "learning_rate": 2.8653198653198653e-05, | |
| "loss": 0.9249, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 6.79242467880249, | |
| "learning_rate": 2.781144781144781e-05, | |
| "loss": 0.958, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.5151515151515151, | |
| "grad_norm": 8.256180763244629, | |
| "learning_rate": 2.696969696969697e-05, | |
| "loss": 0.9815, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.5303030303030303, | |
| "grad_norm": 10.210299491882324, | |
| "learning_rate": 2.612794612794613e-05, | |
| "loss": 0.9463, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 10.20052719116211, | |
| "learning_rate": 2.5286195286195287e-05, | |
| "loss": 0.8696, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.5606060606060606, | |
| "grad_norm": 5.729280471801758, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.9741, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.5757575757575758, | |
| "grad_norm": 8.521025657653809, | |
| "learning_rate": 2.3602693602693603e-05, | |
| "loss": 0.9395, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.5909090909090909, | |
| "grad_norm": 7.029082298278809, | |
| "learning_rate": 2.2760942760942764e-05, | |
| "loss": 0.8523, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 15.19565486907959, | |
| "learning_rate": 2.191919191919192e-05, | |
| "loss": 1.0135, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6212121212121212, | |
| "grad_norm": 11.735282897949219, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.8963, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 7.976740837097168, | |
| "learning_rate": 2.0269360269360272e-05, | |
| "loss": 0.8541, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.6515151515151515, | |
| "grad_norm": 10.43382453918457, | |
| "learning_rate": 1.9427609427609426e-05, | |
| "loss": 0.9451, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 8.731287002563477, | |
| "learning_rate": 1.8585858585858588e-05, | |
| "loss": 0.9462, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.6818181818181818, | |
| "grad_norm": 8.06290340423584, | |
| "learning_rate": 1.7744107744107745e-05, | |
| "loss": 0.8175, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.696969696969697, | |
| "grad_norm": 20.532014846801758, | |
| "learning_rate": 1.6902356902356903e-05, | |
| "loss": 0.8604, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.7121212121212122, | |
| "grad_norm": 10.84019947052002, | |
| "learning_rate": 1.606060606060606e-05, | |
| "loss": 0.8538, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 8.15449047088623, | |
| "learning_rate": 1.5218855218855219e-05, | |
| "loss": 0.8301, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7424242424242424, | |
| "grad_norm": 7.453359127044678, | |
| "learning_rate": 1.4377104377104378e-05, | |
| "loss": 0.8899, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 8.70699691772461, | |
| "learning_rate": 1.3535353535353538e-05, | |
| "loss": 0.8645, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.7727272727272727, | |
| "grad_norm": 6.581109046936035, | |
| "learning_rate": 1.2693602693602694e-05, | |
| "loss": 0.7355, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": 6.576424598693848, | |
| "learning_rate": 1.1851851851851853e-05, | |
| "loss": 0.8093, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.803030303030303, | |
| "grad_norm": 9.948806762695312, | |
| "learning_rate": 1.1010101010101011e-05, | |
| "loss": 0.7704, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 3.807300329208374, | |
| "learning_rate": 1.0168350168350169e-05, | |
| "loss": 0.8601, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 6.901116847991943, | |
| "learning_rate": 9.326599326599327e-06, | |
| "loss": 0.7588, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 9.398531913757324, | |
| "learning_rate": 8.484848484848486e-06, | |
| "loss": 0.6331, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8636363636363636, | |
| "grad_norm": 6.804070949554443, | |
| "learning_rate": 7.643097643097644e-06, | |
| "loss": 0.7387, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.8787878787878788, | |
| "grad_norm": 8.357223510742188, | |
| "learning_rate": 6.801346801346802e-06, | |
| "loss": 0.7136, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.8939393939393939, | |
| "grad_norm": 9.511758804321289, | |
| "learning_rate": 5.9595959595959605e-06, | |
| "loss": 0.8399, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 7.744482517242432, | |
| "learning_rate": 5.117845117845118e-06, | |
| "loss": 0.8673, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9242424242424242, | |
| "grad_norm": 10.048524856567383, | |
| "learning_rate": 4.276094276094277e-06, | |
| "loss": 0.8057, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.9393939393939394, | |
| "grad_norm": 6.401331424713135, | |
| "learning_rate": 3.4343434343434343e-06, | |
| "loss": 0.693, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.9545454545454546, | |
| "grad_norm": 9.841402053833008, | |
| "learning_rate": 2.5925925925925925e-06, | |
| "loss": 0.7771, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 11.016989707946777, | |
| "learning_rate": 1.750841750841751e-06, | |
| "loss": 0.7287, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.9848484848484849, | |
| "grad_norm": 10.226309776306152, | |
| "learning_rate": 9.09090909090909e-07, | |
| "loss": 0.7603, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 5.509101390838623, | |
| "learning_rate": 6.734006734006734e-08, | |
| "loss": 0.653, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8357575757575758, | |
| "eval_f1_macro": 0.7937276418883129, | |
| "eval_f1_micro": 0.8357575757575758, | |
| "eval_f1_weighted": 0.8309508918437231, | |
| "eval_loss": 0.5393036603927612, | |
| "eval_precision_macro": 0.8009361572777395, | |
| "eval_precision_micro": 0.8357575757575758, | |
| "eval_precision_weighted": 0.832849266981749, | |
| "eval_recall_macro": 0.7951666666666667, | |
| "eval_recall_micro": 0.8357575757575758, | |
| "eval_recall_weighted": 0.8357575757575758, | |
| "eval_runtime": 18.907, | |
| "eval_samples_per_second": 174.538, | |
| "eval_steps_per_second": 10.948, | |
| "step": 1650 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1650, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.616053372842803e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |