| { | |
| "best_metric": 10.3431978225708, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2527646129541864, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005055292259083728, | |
| "grad_norm": 0.15741536021232605, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005055292259083728, | |
| "eval_loss": 10.369935989379883, | |
| "eval_runtime": 1.3355, | |
| "eval_samples_per_second": 998.137, | |
| "eval_steps_per_second": 125.048, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010110584518167456, | |
| "grad_norm": 0.18223460018634796, | |
| "learning_rate": 0.0001, | |
| "loss": 10.383, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015165876777251185, | |
| "grad_norm": 0.6735424995422363, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3887, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02022116903633491, | |
| "grad_norm": 0.6819682717323303, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3891, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02527646129541864, | |
| "grad_norm": 0.6052437424659729, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3847, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03033175355450237, | |
| "grad_norm": 0.622982382774353, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3825, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0353870458135861, | |
| "grad_norm": 0.6026582717895508, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3785, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04044233807266982, | |
| "grad_norm": 0.5945727825164795, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3725, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04549763033175355, | |
| "grad_norm": 1.03611421585083, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3428, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05055292259083728, | |
| "grad_norm": 1.223228931427002, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.323, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05560821484992101, | |
| "grad_norm": 0.814987063407898, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.325, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06066350710900474, | |
| "grad_norm": 1.3167004585266113, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3418, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06571879936808847, | |
| "grad_norm": 0.43501773476600647, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3786, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0707740916271722, | |
| "grad_norm": 0.16349023580551147, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3801, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07582938388625593, | |
| "grad_norm": 0.3947107195854187, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3795, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08088467614533965, | |
| "grad_norm": 0.6592985987663269, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3662, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08593996840442338, | |
| "grad_norm": 0.6609896421432495, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3627, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0909952606635071, | |
| "grad_norm": 0.647784948348999, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3647, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09605055292259083, | |
| "grad_norm": 0.6419176459312439, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3647, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10110584518167456, | |
| "grad_norm": 0.6310173869132996, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3605, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1061611374407583, | |
| "grad_norm": 0.8688631653785706, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3419, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11121642969984202, | |
| "grad_norm": 1.022196650505066, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3215, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11627172195892575, | |
| "grad_norm": 1.0036414861679077, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3204, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12132701421800948, | |
| "grad_norm": 1.3437373638153076, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3267, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1263823064770932, | |
| "grad_norm": 1.2378543615341187, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3288, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1263823064770932, | |
| "eval_loss": 10.348902702331543, | |
| "eval_runtime": 1.3018, | |
| "eval_samples_per_second": 1023.965, | |
| "eval_steps_per_second": 128.284, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13143759873617694, | |
| "grad_norm": 0.16551639139652252, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3903, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13649289099526066, | |
| "grad_norm": 0.25612032413482666, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3751, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1415481832543444, | |
| "grad_norm": 0.6713676452636719, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3534, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14660347551342812, | |
| "grad_norm": 0.6692630052566528, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3532, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.15165876777251186, | |
| "grad_norm": 0.6770070195198059, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3525, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15671406003159558, | |
| "grad_norm": 0.7069156169891357, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3531, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1617693522906793, | |
| "grad_norm": 0.6632951498031616, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3502, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16682464454976303, | |
| "grad_norm": 0.588923990726471, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3497, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.17187993680884675, | |
| "grad_norm": 0.9730269908905029, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3237, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1769352290679305, | |
| "grad_norm": 1.1822327375411987, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3171, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1819905213270142, | |
| "grad_norm": 0.8201085329055786, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3087, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18704581358609795, | |
| "grad_norm": 1.3781483173370361, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.318, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19210110584518167, | |
| "grad_norm": 0.40582355856895447, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3761, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1971563981042654, | |
| "grad_norm": 0.17469125986099243, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.38, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20221169036334913, | |
| "grad_norm": 0.47525304555892944, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3601, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20726698262243287, | |
| "grad_norm": 0.6610441207885742, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3537, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2123222748815166, | |
| "grad_norm": 0.652646541595459, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3501, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2173775671406003, | |
| "grad_norm": 0.650054931640625, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3502, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.22243285939968405, | |
| "grad_norm": 0.6490793824195862, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3485, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.22748815165876776, | |
| "grad_norm": 0.6380521059036255, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3507, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2325434439178515, | |
| "grad_norm": 0.768058180809021, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3388, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.23759873617693522, | |
| "grad_norm": 1.00645112991333, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.309, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.24265402843601896, | |
| "grad_norm": 1.031985878944397, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3109, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.24770932069510268, | |
| "grad_norm": 1.3196580410003662, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3179, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2527646129541864, | |
| "grad_norm": 1.2216837406158447, | |
| "learning_rate": 0.0, | |
| "loss": 10.3203, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2527646129541864, | |
| "eval_loss": 10.3431978225708, | |
| "eval_runtime": 1.3051, | |
| "eval_samples_per_second": 1021.385, | |
| "eval_steps_per_second": 127.96, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |