| { |
| "best_global_step": 600, |
| "best_metric": 0.9695240197651653, |
| "best_model_checkpoint": "taskA-codebert-base-focal/checkpoint-600", |
| "epoch": 0.14680694886224616, |
| "eval_steps": 200, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002446782481037436, |
| "grad_norm": 1.0, |
| "learning_rate": 3.6734693877551025e-07, |
| "loss": 1.1949, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.004893564962074872, |
| "grad_norm": 0.9999998807907104, |
| "learning_rate": 7.755102040816327e-07, |
| "loss": 1.1644, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.007340347443112307, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.1836734693877552e-06, |
| "loss": 0.96, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.009787129924149743, |
| "grad_norm": 1.0, |
| "learning_rate": 1.5918367346938775e-06, |
| "loss": 0.7557, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.012233912405187179, |
| "grad_norm": 1.0, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.5786, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.014680694886224614, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 2.4081632653061225e-06, |
| "loss": 0.4813, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.01712747736726205, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 2.816326530612245e-06, |
| "loss": 0.4477, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.019574259848299486, |
| "grad_norm": 1.0, |
| "learning_rate": 3.2244897959183672e-06, |
| "loss": 0.4254, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.022021042329336923, |
| "grad_norm": 1.0, |
| "learning_rate": 3.6326530612244903e-06, |
| "loss": 0.4017, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.024467824810374357, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 4.040816326530612e-06, |
| "loss": 0.379, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.026914607291411794, |
| "grad_norm": 1.0000001192092896, |
| "learning_rate": 4.448979591836735e-06, |
| "loss": 0.3749, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.029361389772449228, |
| "grad_norm": 1.0, |
| "learning_rate": 4.857142857142858e-06, |
| "loss": 0.3536, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.031808172253486665, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 5.26530612244898e-06, |
| "loss": 0.336, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.0342549547345241, |
| "grad_norm": 1.0000001192092896, |
| "learning_rate": 5.673469387755103e-06, |
| "loss": 0.3261, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.03670173721556154, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 6.0816326530612245e-06, |
| "loss": 0.3134, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.03914851969659897, |
| "grad_norm": 1.0, |
| "learning_rate": 6.489795918367348e-06, |
| "loss": 0.308, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.041595302177636406, |
| "grad_norm": 1.0, |
| "learning_rate": 6.8979591836734705e-06, |
| "loss": 0.2961, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.04404208465867385, |
| "grad_norm": 1.0, |
| "learning_rate": 7.306122448979592e-06, |
| "loss": 0.2998, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.04648886713971128, |
| "grad_norm": 1.0, |
| "learning_rate": 7.714285714285716e-06, |
| "loss": 0.2895, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.048935649620748714, |
| "grad_norm": 1.0, |
| "learning_rate": 8.122448979591837e-06, |
| "loss": 0.2773, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.048935649620748714, |
| "eval_accuracy": 0.81444, |
| "eval_f1_weighted": 0.8120194753530078, |
| "eval_loss": 0.10672978311777115, |
| "eval_macro_f1": 0.8128217919062601, |
| "eval_precision": 0.8426688032270206, |
| "eval_recall": 0.81444, |
| "eval_runtime": 1609.4299, |
| "eval_samples_per_second": 62.134, |
| "eval_steps_per_second": 0.243, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.051382432101786155, |
| "grad_norm": 1.0, |
| "learning_rate": 8.530612244897961e-06, |
| "loss": 0.2658, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.05382921458282359, |
| "grad_norm": 1.0000001192092896, |
| "learning_rate": 8.938775510204082e-06, |
| "loss": 0.2574, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.05627599706386102, |
| "grad_norm": 1.0, |
| "learning_rate": 9.346938775510204e-06, |
| "loss": 0.2633, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.058722779544898455, |
| "grad_norm": 1.0, |
| "learning_rate": 9.755102040816327e-06, |
| "loss": 0.2503, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.061169562025935896, |
| "grad_norm": 1.0, |
| "learning_rate": 1.016326530612245e-05, |
| "loss": 0.2359, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.06361634450697333, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.0571428571428572e-05, |
| "loss": 0.2327, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.06606312698801077, |
| "grad_norm": 1.0, |
| "learning_rate": 1.0979591836734695e-05, |
| "loss": 0.2305, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.0685099094690482, |
| "grad_norm": 1.0, |
| "learning_rate": 1.1387755102040819e-05, |
| "loss": 0.2284, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.07095669195008564, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.179591836734694e-05, |
| "loss": 0.226, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.07340347443112308, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.2204081632653062e-05, |
| "loss": 0.2225, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.0758502569121605, |
| "grad_norm": 1.0, |
| "learning_rate": 1.2612244897959185e-05, |
| "loss": 0.2156, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.07829703939319795, |
| "grad_norm": 1.0, |
| "learning_rate": 1.3020408163265308e-05, |
| "loss": 0.2033, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.08074382187423539, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.3428571428571429e-05, |
| "loss": 0.2021, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.08319060435527281, |
| "grad_norm": 1.0, |
| "learning_rate": 1.3836734693877551e-05, |
| "loss": 0.1902, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.08563738683631025, |
| "grad_norm": 1.0, |
| "learning_rate": 1.4244897959183674e-05, |
| "loss": 0.1975, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.0880841693173477, |
| "grad_norm": 1.0, |
| "learning_rate": 1.4653061224489798e-05, |
| "loss": 0.1921, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.09053095179838512, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.506122448979592e-05, |
| "loss": 0.2039, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.09297773427942256, |
| "grad_norm": 1.0000001192092896, |
| "learning_rate": 1.546938775510204e-05, |
| "loss": 0.202, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.09542451676046, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.5877551020408162e-05, |
| "loss": 0.1885, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.09787129924149743, |
| "grad_norm": 0.9999998807907104, |
| "learning_rate": 1.6285714285714287e-05, |
| "loss": 0.1818, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.09787129924149743, |
| "eval_accuracy": 0.9495, |
| "eval_f1_weighted": 0.9495267406510758, |
| "eval_loss": 0.039080820977687836, |
| "eval_macro_f1": 0.9494696691689186, |
| "eval_precision": 0.9504394545408126, |
| "eval_recall": 0.9495, |
| "eval_runtime": 1609.6857, |
| "eval_samples_per_second": 62.124, |
| "eval_steps_per_second": 0.243, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.10031808172253487, |
| "grad_norm": 1.0, |
| "learning_rate": 1.669387755102041e-05, |
| "loss": 0.1813, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.10276486420357231, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.7102040816326532e-05, |
| "loss": 0.1758, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.10521164668460974, |
| "grad_norm": 1.0000001192092896, |
| "learning_rate": 1.7510204081632653e-05, |
| "loss": 0.1778, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.10765842916564718, |
| "grad_norm": 0.9999998807907104, |
| "learning_rate": 1.7918367346938777e-05, |
| "loss": 0.1681, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.1101052116466846, |
| "grad_norm": 0.9999998807907104, |
| "learning_rate": 1.8326530612244898e-05, |
| "loss": 0.1715, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.11255199412772204, |
| "grad_norm": 1.0, |
| "learning_rate": 1.8734693877551022e-05, |
| "loss": 0.1773, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.11499877660875948, |
| "grad_norm": 1.0, |
| "learning_rate": 1.9142857142857146e-05, |
| "loss": 0.1859, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.11744555908979691, |
| "grad_norm": 1.0, |
| "learning_rate": 1.9551020408163267e-05, |
| "loss": 0.173, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.11989234157083435, |
| "grad_norm": 1.0, |
| "learning_rate": 1.9959183673469388e-05, |
| "loss": 0.1753, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.12233912405187179, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.9998764266160687e-05, |
| "loss": 0.1712, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.12478590653290922, |
| "grad_norm": 1.0, |
| "learning_rate": 1.9994492985725524e-05, |
| "loss": 0.1644, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.12723268901394666, |
| "grad_norm": 0.9999998807907104, |
| "learning_rate": 1.9987172205655365e-05, |
| "loss": 0.1585, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.1296794714949841, |
| "grad_norm": 1.0000001192092896, |
| "learning_rate": 1.9976804159651927e-05, |
| "loss": 0.1625, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.13212625397602154, |
| "grad_norm": 1.0, |
| "learning_rate": 1.9963392011192586e-05, |
| "loss": 0.1656, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.13457303645705898, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.994693985256516e-05, |
| "loss": 0.1528, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.1370198189380964, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.9927452703619262e-05, |
| "loss": 0.1547, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.13946660141913383, |
| "grad_norm": 1.0, |
| "learning_rate": 1.9904936510234648e-05, |
| "loss": 0.1685, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.14191338390017127, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.987939814250705e-05, |
| "loss": 0.1568, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.14436016638120872, |
| "grad_norm": 1.0, |
| "learning_rate": 1.985084539265195e-05, |
| "loss": 0.1589, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.14680694886224616, |
| "grad_norm": 1.0, |
| "learning_rate": 1.9819286972627066e-05, |
| "loss": 0.1617, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.14680694886224616, |
| "eval_accuracy": 0.96956, |
| "eval_f1_weighted": 0.9695722935959534, |
| "eval_loss": 0.02569369599223137, |
| "eval_macro_f1": 0.9695240197651653, |
| "eval_precision": 0.9698519718113257, |
| "eval_recall": 0.96956, |
| "eval_runtime": 1608.5431, |
| "eval_samples_per_second": 62.168, |
| "eval_steps_per_second": 0.243, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 4087, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.0299639947264e+16, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
