| { | |
| "best_metric": 10.372970581054688, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0690428928972124, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013808578579442479, | |
| "grad_norm": 0.04139500483870506, | |
| "learning_rate": 5e-05, | |
| "loss": 10.38, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013808578579442479, | |
| "eval_loss": 10.379789352416992, | |
| "eval_runtime": 10.9893, | |
| "eval_samples_per_second": 443.979, | |
| "eval_steps_per_second": 55.509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027617157158884957, | |
| "grad_norm": 0.03684312477707863, | |
| "learning_rate": 0.0001, | |
| "loss": 10.38, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0041425735738327436, | |
| "grad_norm": 0.037199754267930984, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3767, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005523431431776991, | |
| "grad_norm": 0.044797610491514206, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.376, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006904289289721239, | |
| "grad_norm": 0.04013918712735176, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3827, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008285147147665487, | |
| "grad_norm": 0.04175626486539841, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3805, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009666005005609735, | |
| "grad_norm": 0.03924490883946419, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.375, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011046862863553983, | |
| "grad_norm": 0.04195459932088852, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3755, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01242772072149823, | |
| "grad_norm": 0.04290958121418953, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3773, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013808578579442479, | |
| "grad_norm": 0.05032459273934364, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3811, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015189436437386726, | |
| "grad_norm": 0.05104326084256172, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3795, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016570294295330974, | |
| "grad_norm": 0.05313715711236, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3788, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017951152153275224, | |
| "grad_norm": 0.04768276959657669, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3779, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01933201001121947, | |
| "grad_norm": 0.045165643095970154, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3757, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02071286786916372, | |
| "grad_norm": 0.048992518335580826, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3807, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022093725727107966, | |
| "grad_norm": 0.04732849821448326, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3743, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023474583585052215, | |
| "grad_norm": 0.05337689071893692, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3782, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02485544144299646, | |
| "grad_norm": 0.04232427105307579, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3776, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02623629930094071, | |
| "grad_norm": 0.046079106628894806, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3702, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027617157158884957, | |
| "grad_norm": 0.048103321343660355, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3756, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028998015016829207, | |
| "grad_norm": 0.05433672294020653, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3749, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030378872874773453, | |
| "grad_norm": 0.06023729592561722, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3773, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0317597307327177, | |
| "grad_norm": 0.06002996489405632, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3733, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03314058859066195, | |
| "grad_norm": 0.07419168949127197, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3771, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0345214464486062, | |
| "grad_norm": 0.07050827145576477, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3769, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0345214464486062, | |
| "eval_loss": 10.37507152557373, | |
| "eval_runtime": 12.0229, | |
| "eval_samples_per_second": 405.809, | |
| "eval_steps_per_second": 50.736, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03590230430655045, | |
| "grad_norm": 0.0471736304461956, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3719, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03728316216449469, | |
| "grad_norm": 0.05829121172428131, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.375, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03866402002243894, | |
| "grad_norm": 0.05979091301560402, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.373, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04004487788038319, | |
| "grad_norm": 0.05182816460728645, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3747, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04142573573832744, | |
| "grad_norm": 0.0602106899023056, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3706, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04280659359627168, | |
| "grad_norm": 0.0521862730383873, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3722, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04418745145421593, | |
| "grad_norm": 0.058822404593229294, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3714, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04556830931216018, | |
| "grad_norm": 0.0678439810872078, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3721, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04694916717010443, | |
| "grad_norm": 0.07424871623516083, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.371, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04833002502804867, | |
| "grad_norm": 0.060588035732507706, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3781, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04971088288599292, | |
| "grad_norm": 0.07945407181978226, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3716, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05109174074393717, | |
| "grad_norm": 0.09332533180713654, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3682, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05247259860188142, | |
| "grad_norm": 0.07418868690729141, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3753, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.053853456459825665, | |
| "grad_norm": 0.06986246258020401, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3681, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.055234314317769914, | |
| "grad_norm": 0.06155727431178093, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3729, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.056615172175714164, | |
| "grad_norm": 0.08188867568969727, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3738, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05799603003365841, | |
| "grad_norm": 0.05540422722697258, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3729, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.059376887891602656, | |
| "grad_norm": 0.07518801093101501, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3773, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.060757745749546906, | |
| "grad_norm": 0.0601360946893692, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3724, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.062138603607491155, | |
| "grad_norm": 0.06842557340860367, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3736, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0635194614654354, | |
| "grad_norm": 0.05971304327249527, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3746, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06490031932337965, | |
| "grad_norm": 0.08014393597841263, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3719, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0662811771813239, | |
| "grad_norm": 0.08833498507738113, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3671, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06766203503926814, | |
| "grad_norm": 0.08900207281112671, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.373, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0690428928972124, | |
| "grad_norm": 0.09857583791017532, | |
| "learning_rate": 0.0, | |
| "loss": 10.3799, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0690428928972124, | |
| "eval_loss": 10.372970581054688, | |
| "eval_runtime": 11.793, | |
| "eval_samples_per_second": 413.719, | |
| "eval_steps_per_second": 51.725, | |
| "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 | |
| } | |