| { | |
| "best_metric": 0.022257013246417046, | |
| "best_model_checkpoint": "/kaggle/working/output/checkpoint-150", | |
| "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": -0.38242422405954946, | |
| "eval_SROCC": -0.3890036014405762, | |
| "eval_loss": 0.2948198914527893, | |
| "eval_runtime": 37.5549, | |
| "eval_samples_per_second": 1.331, | |
| "eval_steps_per_second": 0.053, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_LCC": -0.3732136136633078, | |
| "eval_SROCC": -0.36653061224489797, | |
| "eval_loss": 0.11433681845664978, | |
| "eval_runtime": 35.6391, | |
| "eval_samples_per_second": 1.403, | |
| "eval_steps_per_second": 0.056, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 4.934920310974121, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.1552, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_LCC": -0.3657486170203663, | |
| "eval_SROCC": -0.3477070828331333, | |
| "eval_loss": 0.07677865773439407, | |
| "eval_runtime": 35.6897, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_LCC": -0.35044377450614, | |
| "eval_SROCC": -0.3395438175270108, | |
| "eval_loss": 0.07478620857000351, | |
| "eval_runtime": 35.8511, | |
| "eval_samples_per_second": 1.395, | |
| "eval_steps_per_second": 0.056, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "eval_LCC": -0.33219308626687694, | |
| "eval_SROCC": -0.34981992797118844, | |
| "eval_loss": 0.05174265429377556, | |
| "eval_runtime": 35.8384, | |
| "eval_samples_per_second": 1.395, | |
| "eval_steps_per_second": 0.056, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 2.3777573108673096, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.0657, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_LCC": -0.30599681663050493, | |
| "eval_SROCC": -0.33368547418967587, | |
| "eval_loss": 0.05527381971478462, | |
| "eval_runtime": 35.8215, | |
| "eval_samples_per_second": 1.396, | |
| "eval_steps_per_second": 0.056, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_LCC": -0.28100937429201095, | |
| "eval_SROCC": -0.2921008403361345, | |
| "eval_loss": 0.043372660875320435, | |
| "eval_runtime": 35.795, | |
| "eval_samples_per_second": 1.397, | |
| "eval_steps_per_second": 0.056, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_LCC": -0.25699939917329884, | |
| "eval_SROCC": -0.24811524609843938, | |
| "eval_loss": 0.040563274174928665, | |
| "eval_runtime": 35.9877, | |
| "eval_samples_per_second": 1.389, | |
| "eval_steps_per_second": 0.056, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "grad_norm": 1.0520217418670654, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.0249, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.857142857142858, | |
| "eval_LCC": -0.2477874480763097, | |
| "eval_SROCC": -0.23457382953181274, | |
| "eval_loss": 0.040173906832933426, | |
| "eval_runtime": 35.9073, | |
| "eval_samples_per_second": 1.392, | |
| "eval_steps_per_second": 0.056, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_LCC": -0.21817464996358082, | |
| "eval_SROCC": -0.20758703481392557, | |
| "eval_loss": 0.0384274497628212, | |
| "eval_runtime": 35.6916, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_LCC": -0.19225659084922117, | |
| "eval_SROCC": -0.19193277310924367, | |
| "eval_loss": 0.03174906224012375, | |
| "eval_runtime": 35.716, | |
| "eval_samples_per_second": 1.4, | |
| "eval_steps_per_second": 0.056, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 1.398345947265625, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.0215, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_LCC": -0.16355167219890276, | |
| "eval_SROCC": -0.15178871548619446, | |
| "eval_loss": 0.031038017943501472, | |
| "eval_runtime": 35.6946, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.857142857142858, | |
| "eval_LCC": -0.1548916268794662, | |
| "eval_SROCC": -0.1291236494597839, | |
| "eval_loss": 0.03165186941623688, | |
| "eval_runtime": 35.6768, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_LCC": -0.12920387967048147, | |
| "eval_SROCC": -0.09752701080432173, | |
| "eval_loss": 0.03006185218691826, | |
| "eval_runtime": 35.8955, | |
| "eval_samples_per_second": 1.393, | |
| "eval_steps_per_second": 0.056, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.285714285714286, | |
| "grad_norm": 0.4825093746185303, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.0154, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_LCC": -0.10573621549419017, | |
| "eval_SROCC": -0.08043217286914765, | |
| "eval_loss": 0.0284834336489439, | |
| "eval_runtime": 35.7717, | |
| "eval_samples_per_second": 1.398, | |
| "eval_steps_per_second": 0.056, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_LCC": -0.07621053426257447, | |
| "eval_SROCC": -0.04614645858343337, | |
| "eval_loss": 0.027657881379127502, | |
| "eval_runtime": 35.7321, | |
| "eval_samples_per_second": 1.399, | |
| "eval_steps_per_second": 0.056, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.857142857142858, | |
| "eval_LCC": -0.04854793231941595, | |
| "eval_SROCC": -0.03567827130852341, | |
| "eval_loss": 0.02630411647260189, | |
| "eval_runtime": 35.6683, | |
| "eval_samples_per_second": 1.402, | |
| "eval_steps_per_second": 0.056, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 0.7504790425300598, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.0128, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_LCC": -0.03166657911247084, | |
| "eval_SROCC": -0.01714285714285714, | |
| "eval_loss": 0.026295064017176628, | |
| "eval_runtime": 35.6163, | |
| "eval_samples_per_second": 1.404, | |
| "eval_steps_per_second": 0.056, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_LCC": -0.023641716533156595, | |
| "eval_SROCC": -0.003985594237695078, | |
| "eval_loss": 0.026547763496637344, | |
| "eval_runtime": 35.7061, | |
| "eval_samples_per_second": 1.4, | |
| "eval_steps_per_second": 0.056, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.4742915630340576, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.0113, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_LCC": -0.008938391820749465, | |
| "eval_SROCC": 0.022713085234093634, | |
| "eval_loss": 0.026299767196178436, | |
| "eval_runtime": 35.6413, | |
| "eval_samples_per_second": 1.403, | |
| "eval_steps_per_second": 0.056, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.857142857142858, | |
| "eval_LCC": 0.008109004168265264, | |
| "eval_SROCC": 0.025402160864345734, | |
| "eval_loss": 0.025580281391739845, | |
| "eval_runtime": 35.724, | |
| "eval_samples_per_second": 1.4, | |
| "eval_steps_per_second": 0.056, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_LCC": 0.023345863441218237, | |
| "eval_SROCC": 0.049315726290516206, | |
| "eval_loss": 0.02492944523692131, | |
| "eval_runtime": 35.624, | |
| "eval_samples_per_second": 1.404, | |
| "eval_steps_per_second": 0.056, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 0.43411004543304443, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.0104, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_LCC": 0.033023044716641976, | |
| "eval_SROCC": 0.06160864345738295, | |
| "eval_loss": 0.024564068764448166, | |
| "eval_runtime": 35.6925, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_LCC": 0.04347957438577821, | |
| "eval_SROCC": 0.06909963985594238, | |
| "eval_loss": 0.02423253282904625, | |
| "eval_runtime": 35.9004, | |
| "eval_samples_per_second": 1.393, | |
| "eval_steps_per_second": 0.056, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.857142857142858, | |
| "eval_LCC": 0.051818984749542364, | |
| "eval_SROCC": 0.07956782713085234, | |
| "eval_loss": 0.024022720754146576, | |
| "eval_runtime": 35.8318, | |
| "eval_samples_per_second": 1.395, | |
| "eval_steps_per_second": 0.056, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "grad_norm": 0.443155437707901, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.0095, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_LCC": 0.0679416905737761, | |
| "eval_SROCC": 0.0830252100840336, | |
| "eval_loss": 0.02380475588142872, | |
| "eval_runtime": 35.6776, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "eval_LCC": 0.0746956496870511, | |
| "eval_SROCC": 0.09291716686674668, | |
| "eval_loss": 0.023518024012446404, | |
| "eval_runtime": 35.6658, | |
| "eval_samples_per_second": 1.402, | |
| "eval_steps_per_second": 0.056, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_LCC": 0.08622063268749575, | |
| "eval_SROCC": 0.10031212484993997, | |
| "eval_loss": 0.02321736514568329, | |
| "eval_runtime": 35.7144, | |
| "eval_samples_per_second": 1.4, | |
| "eval_steps_per_second": 0.056, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 0.6047067642211914, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.009, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.857142857142858, | |
| "eval_LCC": 0.09545687497338319, | |
| "eval_SROCC": 0.10501800720288115, | |
| "eval_loss": 0.022862296551465988, | |
| "eval_runtime": 35.7409, | |
| "eval_samples_per_second": 1.399, | |
| "eval_steps_per_second": 0.056, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_LCC": 0.10522076553867485, | |
| "eval_SROCC": 0.10722689075630251, | |
| "eval_loss": 0.02260303497314453, | |
| "eval_runtime": 35.8268, | |
| "eval_samples_per_second": 1.396, | |
| "eval_steps_per_second": 0.056, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "eval_LCC": 0.11099832718077456, | |
| "eval_SROCC": 0.11769507803121249, | |
| "eval_loss": 0.022564733400940895, | |
| "eval_runtime": 35.6873, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.428571428571427, | |
| "grad_norm": 0.3605582118034363, | |
| "learning_rate": 2.0142070414860704e-06, | |
| "loss": 0.0084, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_LCC": 0.11518191832516576, | |
| "eval_SROCC": 0.12864345738295319, | |
| "eval_loss": 0.022482411935925484, | |
| "eval_runtime": 35.5295, | |
| "eval_samples_per_second": 1.407, | |
| "eval_steps_per_second": 0.056, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.857142857142854, | |
| "eval_LCC": 0.11672118384335717, | |
| "eval_SROCC": 0.12960384153661464, | |
| "eval_loss": 0.02244633622467518, | |
| "eval_runtime": 35.6625, | |
| "eval_samples_per_second": 1.402, | |
| "eval_steps_per_second": 0.056, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_LCC": 0.11853509722750845, | |
| "eval_SROCC": 0.12960384153661464, | |
| "eval_loss": 0.022433871403336525, | |
| "eval_runtime": 35.775, | |
| "eval_samples_per_second": 1.398, | |
| "eval_steps_per_second": 0.056, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 0.37335312366485596, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.0085, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.857142857142854, | |
| "eval_LCC": 0.11996998016040515, | |
| "eval_SROCC": 0.13104441776710685, | |
| "eval_loss": 0.022421473637223244, | |
| "eval_runtime": 35.8151, | |
| "eval_samples_per_second": 1.396, | |
| "eval_steps_per_second": 0.056, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_LCC": 0.12212764115994604, | |
| "eval_SROCC": 0.12633853541416568, | |
| "eval_loss": 0.02237151563167572, | |
| "eval_runtime": 35.6186, | |
| "eval_samples_per_second": 1.404, | |
| "eval_steps_per_second": 0.056, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 36.857142857142854, | |
| "eval_LCC": 0.12332180896765454, | |
| "eval_SROCC": 0.12489795918367347, | |
| "eval_loss": 0.022355427965521812, | |
| "eval_runtime": 35.9066, | |
| "eval_samples_per_second": 1.393, | |
| "eval_steps_per_second": 0.056, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 37.142857142857146, | |
| "grad_norm": 0.5681003332138062, | |
| "learning_rate": 5.318367983829393e-07, | |
| "loss": 0.0082, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_LCC": 0.12470767155506596, | |
| "eval_SROCC": 0.12720288115246098, | |
| "eval_loss": 0.022325601428747177, | |
| "eval_runtime": 35.6817, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 38.857142857142854, | |
| "eval_LCC": 0.1255198227036719, | |
| "eval_SROCC": 0.12720288115246098, | |
| "eval_loss": 0.02230682410299778, | |
| "eval_runtime": 35.758, | |
| "eval_samples_per_second": 1.398, | |
| "eval_steps_per_second": 0.056, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.49957460165023804, | |
| "learning_rate": 1.3477564710088097e-07, | |
| "loss": 0.008, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_LCC": 0.12651835944328998, | |
| "eval_SROCC": 0.1291236494597839, | |
| "eval_loss": 0.022274091839790344, | |
| "eval_runtime": 35.7033, | |
| "eval_samples_per_second": 1.4, | |
| "eval_steps_per_second": 0.056, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 40.857142857142854, | |
| "eval_LCC": 0.1269013775632479, | |
| "eval_SROCC": 0.1291236494597839, | |
| "eval_loss": 0.022262830287218094, | |
| "eval_runtime": 35.6563, | |
| "eval_samples_per_second": 1.402, | |
| "eval_steps_per_second": 0.056, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_LCC": 0.12710778753633592, | |
| "eval_SROCC": 0.1291236494597839, | |
| "eval_loss": 0.022257346659898758, | |
| "eval_runtime": 35.6941, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "grad_norm": 0.33458444476127625, | |
| "learning_rate": 0.0, | |
| "loss": 0.0078, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "eval_LCC": 0.12712191056512775, | |
| "eval_SROCC": 0.1291236494597839, | |
| "eval_loss": 0.022257013246417046, | |
| "eval_runtime": 35.8013, | |
| "eval_samples_per_second": 1.397, | |
| "eval_steps_per_second": 0.056, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "step": 150, | |
| "total_flos": 2.1207924866757427e+18, | |
| "train_loss": 0.02509542241692543, | |
| "train_runtime": 7697.1048, | |
| "train_samples_per_second": 1.39, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "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": 2.1207924866757427e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |