| { | |
| "best_metric": 0.025447649881243706, | |
| "best_model_checkpoint": "/kaggle/working/output/checkpoint-98", | |
| "epoch": 32.857142857142854, | |
| "eval_steps": 500, | |
| "global_step": 115, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8571428571428571, | |
| "eval_LCC": -0.13879293215538938, | |
| "eval_SROCC": -0.15851140456182472, | |
| "eval_loss": 0.26562368869781494, | |
| "eval_runtime": 38.0061, | |
| "eval_samples_per_second": 1.316, | |
| "eval_steps_per_second": 0.053, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_LCC": -0.12769050797605289, | |
| "eval_SROCC": -0.18098439375750297, | |
| "eval_loss": 0.06580950319766998, | |
| "eval_runtime": 35.9745, | |
| "eval_samples_per_second": 1.39, | |
| "eval_steps_per_second": 0.056, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 6.6160054206848145, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.2144, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_LCC": -0.11849463789687457, | |
| "eval_SROCC": -0.16840336134453782, | |
| "eval_loss": 0.1341191679239273, | |
| "eval_runtime": 35.7755, | |
| "eval_samples_per_second": 1.398, | |
| "eval_steps_per_second": 0.056, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_LCC": -0.13792803325263353, | |
| "eval_SROCC": -0.23822328931572626, | |
| "eval_loss": 0.05623332038521767, | |
| "eval_runtime": 36.0015, | |
| "eval_samples_per_second": 1.389, | |
| "eval_steps_per_second": 0.056, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "eval_LCC": -0.14276549217386758, | |
| "eval_SROCC": -0.1657142857142857, | |
| "eval_loss": 0.061644963920116425, | |
| "eval_runtime": 35.7987, | |
| "eval_samples_per_second": 1.397, | |
| "eval_steps_per_second": 0.056, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 1.571254014968872, | |
| "learning_rate": 1.925925925925926e-05, | |
| "loss": 0.0575, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_LCC": -0.1185043581646345, | |
| "eval_SROCC": -0.15006002400960383, | |
| "eval_loss": 0.05936155468225479, | |
| "eval_runtime": 36.1077, | |
| "eval_samples_per_second": 1.385, | |
| "eval_steps_per_second": 0.055, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_LCC": -0.11221146661280773, | |
| "eval_SROCC": -0.12038415366146459, | |
| "eval_loss": 0.05129233002662659, | |
| "eval_runtime": 35.8427, | |
| "eval_samples_per_second": 1.395, | |
| "eval_steps_per_second": 0.056, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_LCC": -0.09867320013209922, | |
| "eval_SROCC": -0.06929171668667466, | |
| "eval_loss": 0.041676923632621765, | |
| "eval_runtime": 36.0348, | |
| "eval_samples_per_second": 1.388, | |
| "eval_steps_per_second": 0.056, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "grad_norm": 0.800278902053833, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 0.0201, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.857142857142858, | |
| "eval_LCC": -0.08130033550198683, | |
| "eval_SROCC": -0.07140456182472989, | |
| "eval_loss": 0.04058969393372536, | |
| "eval_runtime": 36.0799, | |
| "eval_samples_per_second": 1.386, | |
| "eval_steps_per_second": 0.055, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_LCC": -0.0384540491268753, | |
| "eval_SROCC": -0.02357743097238895, | |
| "eval_loss": 0.034295279532670975, | |
| "eval_runtime": 36.1741, | |
| "eval_samples_per_second": 1.382, | |
| "eval_steps_per_second": 0.055, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_LCC": 0.0010666390633979736, | |
| "eval_SROCC": 0.00744297719087635, | |
| "eval_loss": 0.031487837433815, | |
| "eval_runtime": 36.0877, | |
| "eval_samples_per_second": 1.386, | |
| "eval_steps_per_second": 0.055, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 0.3433558940887451, | |
| "learning_rate": 1.6296296296296297e-05, | |
| "loss": 0.0142, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_LCC": 0.03256796518969046, | |
| "eval_SROCC": 0.02175270108043217, | |
| "eval_loss": 0.03087497688829899, | |
| "eval_runtime": 35.9382, | |
| "eval_samples_per_second": 1.391, | |
| "eval_steps_per_second": 0.056, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.857142857142858, | |
| "eval_LCC": 0.04658237209190174, | |
| "eval_SROCC": 0.03807923169267707, | |
| "eval_loss": 0.030963044613599777, | |
| "eval_runtime": 36.1523, | |
| "eval_samples_per_second": 1.383, | |
| "eval_steps_per_second": 0.055, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_LCC": 0.06813425647249395, | |
| "eval_SROCC": 0.05354141656662665, | |
| "eval_loss": 0.029918596148490906, | |
| "eval_runtime": 35.716, | |
| "eval_samples_per_second": 1.4, | |
| "eval_steps_per_second": 0.056, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.285714285714286, | |
| "grad_norm": 0.8214556574821472, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0097, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_LCC": 0.07492776273224191, | |
| "eval_SROCC": 0.06036014405762304, | |
| "eval_loss": 0.03141804039478302, | |
| "eval_runtime": 36.0969, | |
| "eval_samples_per_second": 1.385, | |
| "eval_steps_per_second": 0.055, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_LCC": 0.10494559746287975, | |
| "eval_SROCC": 0.07851140456182472, | |
| "eval_loss": 0.02881774678826332, | |
| "eval_runtime": 35.9818, | |
| "eval_samples_per_second": 1.39, | |
| "eval_steps_per_second": 0.056, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.857142857142858, | |
| "eval_LCC": 0.12693485096467225, | |
| "eval_SROCC": 0.09435774309723889, | |
| "eval_loss": 0.0282765943557024, | |
| "eval_runtime": 36.0917, | |
| "eval_samples_per_second": 1.385, | |
| "eval_steps_per_second": 0.055, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 0.5231106877326965, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0083, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_LCC": 0.14480085260022996, | |
| "eval_SROCC": 0.1022328931572629, | |
| "eval_loss": 0.0297652930021286, | |
| "eval_runtime": 35.9054, | |
| "eval_samples_per_second": 1.393, | |
| "eval_steps_per_second": 0.056, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_LCC": 0.16514532692258366, | |
| "eval_SROCC": 0.11183673469387755, | |
| "eval_loss": 0.02742738462984562, | |
| "eval_runtime": 35.7423, | |
| "eval_samples_per_second": 1.399, | |
| "eval_steps_per_second": 0.056, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.43896809220314026, | |
| "learning_rate": 1.1851851851851852e-05, | |
| "loss": 0.0063, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_LCC": 0.17032522192761249, | |
| "eval_SROCC": 0.12240096038415366, | |
| "eval_loss": 0.028603849932551384, | |
| "eval_runtime": 36.0386, | |
| "eval_samples_per_second": 1.387, | |
| "eval_steps_per_second": 0.055, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.857142857142858, | |
| "eval_LCC": 0.1833462608756279, | |
| "eval_SROCC": 0.13709483793517407, | |
| "eval_loss": 0.028336353600025177, | |
| "eval_runtime": 35.9704, | |
| "eval_samples_per_second": 1.39, | |
| "eval_steps_per_second": 0.056, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_LCC": 0.19435351727111327, | |
| "eval_SROCC": 0.13171668667466988, | |
| "eval_loss": 0.028169861063361168, | |
| "eval_runtime": 36.261, | |
| "eval_samples_per_second": 1.379, | |
| "eval_steps_per_second": 0.055, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 0.3503696024417877, | |
| "learning_rate": 1.037037037037037e-05, | |
| "loss": 0.0059, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_LCC": 0.20354883288709705, | |
| "eval_SROCC": 0.13815126050420168, | |
| "eval_loss": 0.027723778039216995, | |
| "eval_runtime": 36.0717, | |
| "eval_samples_per_second": 1.386, | |
| "eval_steps_per_second": 0.055, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_LCC": 0.21464098120344227, | |
| "eval_SROCC": 0.1479471788715486, | |
| "eval_loss": 0.027026496827602386, | |
| "eval_runtime": 36.0759, | |
| "eval_samples_per_second": 1.386, | |
| "eval_steps_per_second": 0.055, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.857142857142858, | |
| "eval_LCC": 0.21974470798595805, | |
| "eval_SROCC": 0.1499639855942377, | |
| "eval_loss": 0.026259804144501686, | |
| "eval_runtime": 35.9282, | |
| "eval_samples_per_second": 1.392, | |
| "eval_steps_per_second": 0.056, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "grad_norm": 0.24314194917678833, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.0046, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_LCC": 0.21990605203497599, | |
| "eval_SROCC": 0.13642256902761105, | |
| "eval_loss": 0.026854444295167923, | |
| "eval_runtime": 36.0574, | |
| "eval_samples_per_second": 1.387, | |
| "eval_steps_per_second": 0.055, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "eval_LCC": 0.22513542090356625, | |
| "eval_SROCC": 0.1406482593037215, | |
| "eval_loss": 0.025891508907079697, | |
| "eval_runtime": 36.0239, | |
| "eval_samples_per_second": 1.388, | |
| "eval_steps_per_second": 0.056, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_LCC": 0.23080971037643985, | |
| "eval_SROCC": 0.15515006002400963, | |
| "eval_loss": 0.025447649881243706, | |
| "eval_runtime": 36.1194, | |
| "eval_samples_per_second": 1.384, | |
| "eval_steps_per_second": 0.055, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 0.2996827960014343, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0039, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.857142857142858, | |
| "eval_LCC": 0.22614882286734456, | |
| "eval_SROCC": 0.14804321728691477, | |
| "eval_loss": 0.026662170886993408, | |
| "eval_runtime": 35.7837, | |
| "eval_samples_per_second": 1.397, | |
| "eval_steps_per_second": 0.056, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_LCC": 0.22468420274739098, | |
| "eval_SROCC": 0.14890756302521005, | |
| "eval_loss": 0.02701684460043907, | |
| "eval_runtime": 35.9924, | |
| "eval_samples_per_second": 1.389, | |
| "eval_steps_per_second": 0.056, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "eval_LCC": 0.2319344817291397, | |
| "eval_SROCC": 0.15764705882352942, | |
| "eval_loss": 0.026096588000655174, | |
| "eval_runtime": 35.7006, | |
| "eval_samples_per_second": 1.401, | |
| "eval_steps_per_second": 0.056, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.428571428571427, | |
| "grad_norm": 0.31328070163726807, | |
| "learning_rate": 5.925925925925926e-06, | |
| "loss": 0.0041, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_LCC": 0.23109019043125076, | |
| "eval_SROCC": 0.1630252100840336, | |
| "eval_loss": 0.026817049831151962, | |
| "eval_runtime": 36.031, | |
| "eval_samples_per_second": 1.388, | |
| "eval_steps_per_second": 0.056, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.857142857142854, | |
| "eval_LCC": 0.22573394181226267, | |
| "eval_SROCC": 0.1569747899159664, | |
| "eval_loss": 0.028198465704917908, | |
| "eval_runtime": 35.9924, | |
| "eval_samples_per_second": 1.389, | |
| "eval_steps_per_second": 0.056, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 32.857142857142854, | |
| "step": 115, | |
| "total_flos": 2.895570431785304e+18, | |
| "train_loss": 0.030544885701459388, | |
| "train_runtime": 6073.1055, | |
| "train_samples_per_second": 1.762, | |
| "train_steps_per_second": 0.025 | |
| } | |
| ], | |
| "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": 2.895570431785304e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |