| { | |
| "best_metric": 0.031172048300504684, | |
| "best_model_checkpoint": "/kaggle/working/output/checkpoint-140", | |
| "epoch": 42.857142857142854, | |
| "eval_steps": 500, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8571428571428571, | |
| "eval_LCC": -0.13924632211285398, | |
| "eval_SROCC": -0.16677070828331333, | |
| "eval_loss": 0.30208367109298706, | |
| "eval_runtime": 40.3225, | |
| "eval_samples_per_second": 1.24, | |
| "eval_steps_per_second": 0.05, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_LCC": -0.13474898479193245, | |
| "eval_SROCC": -0.1807923169267707, | |
| "eval_loss": 0.12863630056381226, | |
| "eval_runtime": 40.2585, | |
| "eval_samples_per_second": 1.242, | |
| "eval_steps_per_second": 0.05, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 2.176586151123047, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.2494, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_LCC": -0.1273026992962787, | |
| "eval_SROCC": -0.17839135654261706, | |
| "eval_loss": 0.06783520430326462, | |
| "eval_runtime": 38.6817, | |
| "eval_samples_per_second": 1.293, | |
| "eval_steps_per_second": 0.052, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_LCC": -0.11136535393072287, | |
| "eval_SROCC": -0.16254501800720286, | |
| "eval_loss": 0.1143360510468483, | |
| "eval_runtime": 40.2563, | |
| "eval_samples_per_second": 1.242, | |
| "eval_steps_per_second": 0.05, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "eval_LCC": -0.11520350547892241, | |
| "eval_SROCC": -0.19394957983193276, | |
| "eval_loss": 0.0686483308672905, | |
| "eval_runtime": 41.6029, | |
| "eval_samples_per_second": 1.202, | |
| "eval_steps_per_second": 0.048, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 1.4751098155975342, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.069, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_LCC": -0.13762820684113933, | |
| "eval_SROCC": -0.2063385354141657, | |
| "eval_loss": 0.05720577389001846, | |
| "eval_runtime": 40.3372, | |
| "eval_samples_per_second": 1.24, | |
| "eval_steps_per_second": 0.05, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_LCC": -0.14053110609303213, | |
| "eval_SROCC": -0.19654261704681872, | |
| "eval_loss": 0.05371831730008125, | |
| "eval_runtime": 38.7274, | |
| "eval_samples_per_second": 1.291, | |
| "eval_steps_per_second": 0.052, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_LCC": -0.1289209958563034, | |
| "eval_SROCC": -0.17944777911164464, | |
| "eval_loss": 0.06708792597055435, | |
| "eval_runtime": 39.9307, | |
| "eval_samples_per_second": 1.252, | |
| "eval_steps_per_second": 0.05, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "grad_norm": 1.0116759538650513, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.0276, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.857142857142858, | |
| "eval_LCC": -0.11639993851566689, | |
| "eval_SROCC": -0.14429771908763506, | |
| "eval_loss": 0.05505238473415375, | |
| "eval_runtime": 40.7189, | |
| "eval_samples_per_second": 1.228, | |
| "eval_steps_per_second": 0.049, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_LCC": -0.09483350559637191, | |
| "eval_SROCC": -0.11097238895558223, | |
| "eval_loss": 0.04916208237409592, | |
| "eval_runtime": 39.8785, | |
| "eval_samples_per_second": 1.254, | |
| "eval_steps_per_second": 0.05, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_LCC": -0.07673019260109643, | |
| "eval_SROCC": -0.09445378151260504, | |
| "eval_loss": 0.04647849500179291, | |
| "eval_runtime": 40.0012, | |
| "eval_samples_per_second": 1.25, | |
| "eval_steps_per_second": 0.05, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 0.6633228063583374, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.0181, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_LCC": -0.04636396970926032, | |
| "eval_SROCC": -0.0830252100840336, | |
| "eval_loss": 0.04492847993969917, | |
| "eval_runtime": 40.5111, | |
| "eval_samples_per_second": 1.234, | |
| "eval_steps_per_second": 0.049, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.857142857142858, | |
| "eval_LCC": -0.028021486790691955, | |
| "eval_SROCC": -0.06593037214885954, | |
| "eval_loss": 0.04024951532483101, | |
| "eval_runtime": 39.9421, | |
| "eval_samples_per_second": 1.252, | |
| "eval_steps_per_second": 0.05, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_LCC": -0.011749661725862606, | |
| "eval_SROCC": -0.041056422569027605, | |
| "eval_loss": 0.038896750658750534, | |
| "eval_runtime": 38.1309, | |
| "eval_samples_per_second": 1.311, | |
| "eval_steps_per_second": 0.052, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.285714285714286, | |
| "grad_norm": 0.8275535106658936, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.0128, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_LCC": -0.005515563619600932, | |
| "eval_SROCC": -0.03481392557022809, | |
| "eval_loss": 0.03803449496626854, | |
| "eval_runtime": 39.4857, | |
| "eval_samples_per_second": 1.266, | |
| "eval_steps_per_second": 0.051, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_LCC": 0.008753274292948681, | |
| "eval_SROCC": -0.023193277310924368, | |
| "eval_loss": 0.037131380289793015, | |
| "eval_runtime": 39.5889, | |
| "eval_samples_per_second": 1.263, | |
| "eval_steps_per_second": 0.051, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.857142857142858, | |
| "eval_LCC": 0.020548187715507097, | |
| "eval_SROCC": 0.00475390156062425, | |
| "eval_loss": 0.03600911796092987, | |
| "eval_runtime": 38.3606, | |
| "eval_samples_per_second": 1.303, | |
| "eval_steps_per_second": 0.052, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 0.48783865571022034, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.0112, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_LCC": 0.038465536486787584, | |
| "eval_SROCC": 0.01282112845138055, | |
| "eval_loss": 0.03541974350810051, | |
| "eval_runtime": 39.3983, | |
| "eval_samples_per_second": 1.269, | |
| "eval_steps_per_second": 0.051, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_LCC": 0.05092487532044425, | |
| "eval_SROCC": 0.019735894357743092, | |
| "eval_loss": 0.03518449887633324, | |
| "eval_runtime": 38.2131, | |
| "eval_samples_per_second": 1.308, | |
| "eval_steps_per_second": 0.052, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.5530023574829102, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.0088, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_LCC": 0.06701747831478003, | |
| "eval_SROCC": 0.03308523409363745, | |
| "eval_loss": 0.03455502539873123, | |
| "eval_runtime": 37.5917, | |
| "eval_samples_per_second": 1.33, | |
| "eval_steps_per_second": 0.053, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.857142857142858, | |
| "eval_LCC": 0.08014093003987598, | |
| "eval_SROCC": 0.04124849939975991, | |
| "eval_loss": 0.033747877925634384, | |
| "eval_runtime": 37.8795, | |
| "eval_samples_per_second": 1.32, | |
| "eval_steps_per_second": 0.053, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_LCC": 0.08790653267137535, | |
| "eval_SROCC": 0.039615846338535404, | |
| "eval_loss": 0.034678902477025986, | |
| "eval_runtime": 40.032, | |
| "eval_samples_per_second": 1.249, | |
| "eval_steps_per_second": 0.05, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 0.45388710498809814, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.008, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_LCC": 0.09537098486730576, | |
| "eval_SROCC": 0.051236494597839126, | |
| "eval_loss": 0.034752532839775085, | |
| "eval_runtime": 38.2511, | |
| "eval_samples_per_second": 1.307, | |
| "eval_steps_per_second": 0.052, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_LCC": 0.10710952739103984, | |
| "eval_SROCC": 0.06429771908763504, | |
| "eval_loss": 0.0338628776371479, | |
| "eval_runtime": 37.9231, | |
| "eval_samples_per_second": 1.318, | |
| "eval_steps_per_second": 0.053, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.857142857142858, | |
| "eval_LCC": 0.11431013947231683, | |
| "eval_SROCC": 0.07649459783913565, | |
| "eval_loss": 0.03316153585910797, | |
| "eval_runtime": 39.8963, | |
| "eval_samples_per_second": 1.253, | |
| "eval_steps_per_second": 0.05, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "grad_norm": 0.3282585144042969, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.0066, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_LCC": 0.12399887441297865, | |
| "eval_SROCC": 0.08552220888355341, | |
| "eval_loss": 0.03337186202406883, | |
| "eval_runtime": 38.9243, | |
| "eval_samples_per_second": 1.285, | |
| "eval_steps_per_second": 0.051, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "eval_LCC": 0.12917364004592166, | |
| "eval_SROCC": 0.09378151260504201, | |
| "eval_loss": 0.032974038273096085, | |
| "eval_runtime": 38.6081, | |
| "eval_samples_per_second": 1.295, | |
| "eval_steps_per_second": 0.052, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_LCC": 0.13808917019413902, | |
| "eval_SROCC": 0.09973589435774309, | |
| "eval_loss": 0.03173243626952171, | |
| "eval_runtime": 40.6852, | |
| "eval_samples_per_second": 1.229, | |
| "eval_steps_per_second": 0.049, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 0.3081737458705902, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.006, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.857142857142858, | |
| "eval_LCC": 0.14324069262154604, | |
| "eval_SROCC": 0.1086674669867947, | |
| "eval_loss": 0.031397391110658646, | |
| "eval_runtime": 40.3292, | |
| "eval_samples_per_second": 1.24, | |
| "eval_steps_per_second": 0.05, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_LCC": 0.14463811773223376, | |
| "eval_SROCC": 0.10530612244897959, | |
| "eval_loss": 0.03169296309351921, | |
| "eval_runtime": 38.2368, | |
| "eval_samples_per_second": 1.308, | |
| "eval_steps_per_second": 0.052, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "eval_LCC": 0.14653245871689255, | |
| "eval_SROCC": 0.09714285714285714, | |
| "eval_loss": 0.0316772386431694, | |
| "eval_runtime": 39.419, | |
| "eval_samples_per_second": 1.268, | |
| "eval_steps_per_second": 0.051, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.428571428571427, | |
| "grad_norm": 0.286915123462677, | |
| "learning_rate": 2.0142070414860704e-06, | |
| "loss": 0.0062, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_LCC": 0.14957484084767725, | |
| "eval_SROCC": 0.10319327731092437, | |
| "eval_loss": 0.03150345757603645, | |
| "eval_runtime": 37.6067, | |
| "eval_samples_per_second": 1.33, | |
| "eval_steps_per_second": 0.053, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.857142857142854, | |
| "eval_LCC": 0.15114563767181508, | |
| "eval_SROCC": 0.10319327731092437, | |
| "eval_loss": 0.031500138342380524, | |
| "eval_runtime": 39.4534, | |
| "eval_samples_per_second": 1.267, | |
| "eval_steps_per_second": 0.051, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_LCC": 0.15328812324811011, | |
| "eval_SROCC": 0.10319327731092437, | |
| "eval_loss": 0.03136735409498215, | |
| "eval_runtime": 39.3064, | |
| "eval_samples_per_second": 1.272, | |
| "eval_steps_per_second": 0.051, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 0.290955513715744, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.0057, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.857142857142854, | |
| "eval_LCC": 0.15433310778646528, | |
| "eval_SROCC": 0.10943577430972388, | |
| "eval_loss": 0.03135786950588226, | |
| "eval_runtime": 39.8429, | |
| "eval_samples_per_second": 1.255, | |
| "eval_steps_per_second": 0.05, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_LCC": 0.15576240657153692, | |
| "eval_SROCC": 0.10905162064825931, | |
| "eval_loss": 0.03134962171316147, | |
| "eval_runtime": 37.8477, | |
| "eval_samples_per_second": 1.321, | |
| "eval_steps_per_second": 0.053, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 36.857142857142854, | |
| "eval_LCC": 0.15697894936703244, | |
| "eval_SROCC": 0.11318127250900359, | |
| "eval_loss": 0.03124266117811203, | |
| "eval_runtime": 38.2997, | |
| "eval_samples_per_second": 1.305, | |
| "eval_steps_per_second": 0.052, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 37.142857142857146, | |
| "grad_norm": 0.33939629793167114, | |
| "learning_rate": 5.318367983829393e-07, | |
| "loss": 0.006, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_LCC": 0.15766699322349262, | |
| "eval_SROCC": 0.11318127250900359, | |
| "eval_loss": 0.031217649579048157, | |
| "eval_runtime": 40.1834, | |
| "eval_samples_per_second": 1.244, | |
| "eval_steps_per_second": 0.05, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 38.857142857142854, | |
| "eval_LCC": 0.15808379809146395, | |
| "eval_SROCC": 0.11318127250900359, | |
| "eval_loss": 0.031192703172564507, | |
| "eval_runtime": 40.4348, | |
| "eval_samples_per_second": 1.237, | |
| "eval_steps_per_second": 0.049, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.4542177617549896, | |
| "learning_rate": 1.3477564710088097e-07, | |
| "loss": 0.0058, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_LCC": 0.15832038036938517, | |
| "eval_SROCC": 0.11318127250900359, | |
| "eval_loss": 0.031172048300504684, | |
| "eval_runtime": 38.0122, | |
| "eval_samples_per_second": 1.315, | |
| "eval_steps_per_second": 0.053, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 40.857142857142854, | |
| "eval_LCC": 0.15841233686752923, | |
| "eval_SROCC": 0.11318127250900359, | |
| "eval_loss": 0.03117518685758114, | |
| "eval_runtime": 38.0357, | |
| "eval_samples_per_second": 1.315, | |
| "eval_steps_per_second": 0.053, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_LCC": 0.15844144208781846, | |
| "eval_SROCC": 0.11318127250900359, | |
| "eval_loss": 0.031179124489426613, | |
| "eval_runtime": 37.8479, | |
| "eval_samples_per_second": 1.321, | |
| "eval_steps_per_second": 0.053, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "grad_norm": 0.2731544077396393, | |
| "learning_rate": 0.0, | |
| "loss": 0.006, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "eval_LCC": 0.15844069648001213, | |
| "eval_SROCC": 0.11318127250900359, | |
| "eval_loss": 0.031179847195744514, | |
| "eval_runtime": 38.1122, | |
| "eval_samples_per_second": 1.312, | |
| "eval_steps_per_second": 0.052, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "step": 150, | |
| "total_flos": 3.763995548539945e+18, | |
| "train_loss": 0.029827568009495736, | |
| "train_runtime": 8529.9763, | |
| "train_samples_per_second": 1.254, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.763995548539945e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |