| { | |
| "best_metric": 10.37037181854248, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06811409110259685, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001362281822051937, | |
| "grad_norm": 0.030297940596938133, | |
| "learning_rate": 5e-05, | |
| "loss": 10.377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001362281822051937, | |
| "eval_loss": 10.375895500183105, | |
| "eval_runtime": 4.9104, | |
| "eval_samples_per_second": 1007.24, | |
| "eval_steps_per_second": 126.058, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002724563644103874, | |
| "grad_norm": 0.03067098744213581, | |
| "learning_rate": 0.0001, | |
| "loss": 10.377, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004086845466155811, | |
| "grad_norm": 0.03045048378407955, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3761, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005449127288207748, | |
| "grad_norm": 0.030379315838217735, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3769, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006811409110259685, | |
| "grad_norm": 0.029919451102614403, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3773, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008173690932311623, | |
| "grad_norm": 0.03522740304470062, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00953597275436356, | |
| "grad_norm": 0.03352035954594612, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3758, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010898254576415497, | |
| "grad_norm": 0.03544633090496063, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3763, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012260536398467433, | |
| "grad_norm": 0.033980224281549454, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3752, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01362281822051937, | |
| "grad_norm": 0.03908739611506462, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3737, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014985100042571307, | |
| "grad_norm": 0.042532917112112045, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3742, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016347381864623246, | |
| "grad_norm": 0.04214796796441078, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3723, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017709663686675182, | |
| "grad_norm": 0.03926650807261467, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3752, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01907194550872712, | |
| "grad_norm": 0.04363276809453964, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3751, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020434227330779056, | |
| "grad_norm": 0.042585477232933044, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3742, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021796509152830993, | |
| "grad_norm": 0.0410710908472538, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3745, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02315879097488293, | |
| "grad_norm": 0.04400284215807915, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3746, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024521072796934867, | |
| "grad_norm": 0.04709471017122269, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3746, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025883354618986804, | |
| "grad_norm": 0.04849720746278763, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3741, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02724563644103874, | |
| "grad_norm": 0.050626903772354126, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.374, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028607918263090677, | |
| "grad_norm": 0.05237357318401337, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3757, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029970200085142614, | |
| "grad_norm": 0.05208142474293709, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3722, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03133248190719455, | |
| "grad_norm": 0.061516690999269485, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3711, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03269476372924649, | |
| "grad_norm": 0.06119893863797188, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3697, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.034057045551298425, | |
| "grad_norm": 0.07519170641899109, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3665, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034057045551298425, | |
| "eval_loss": 10.372044563293457, | |
| "eval_runtime": 4.9104, | |
| "eval_samples_per_second": 1007.254, | |
| "eval_steps_per_second": 126.059, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.035419327373350365, | |
| "grad_norm": 0.06022435054183006, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3724, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0367816091954023, | |
| "grad_norm": 0.060626592487096786, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3727, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03814389101745424, | |
| "grad_norm": 0.06244682893157005, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3713, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03950617283950617, | |
| "grad_norm": 0.06487547606229782, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3728, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04086845466155811, | |
| "grad_norm": 0.06838765740394592, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.372, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042230736483610046, | |
| "grad_norm": 0.06563523411750793, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3722, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.043593018305661986, | |
| "grad_norm": 0.06500206142663956, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3722, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04495530012771392, | |
| "grad_norm": 0.06630583852529526, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3729, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04631758194976586, | |
| "grad_norm": 0.06435850262641907, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3709, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04767986377181779, | |
| "grad_norm": 0.06977062672376633, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3693, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04904214559386973, | |
| "grad_norm": 0.08564142882823944, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3693, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05040442741592167, | |
| "grad_norm": 0.074698805809021, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3648, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05176670923797361, | |
| "grad_norm": 0.07015930861234665, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3707, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05312899106002554, | |
| "grad_norm": 0.07502926141023636, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3707, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05449127288207748, | |
| "grad_norm": 0.07593125849962234, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3715, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.055853554704129414, | |
| "grad_norm": 0.07538634538650513, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3715, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.057215836526181355, | |
| "grad_norm": 0.07371652126312256, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3724, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05857811834823329, | |
| "grad_norm": 0.07424209266901016, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3714, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05994040017028523, | |
| "grad_norm": 0.07837469130754471, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3715, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06130268199233716, | |
| "grad_norm": 0.07376153022050858, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3717, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0626649638143891, | |
| "grad_norm": 0.0708039253950119, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3716, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06402724563644104, | |
| "grad_norm": 0.0748865082859993, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3695, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06538952745849298, | |
| "grad_norm": 0.07984250783920288, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3707, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06675180928054492, | |
| "grad_norm": 0.0698637142777443, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3691, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06811409110259685, | |
| "grad_norm": 0.08626695722341537, | |
| "learning_rate": 0.0, | |
| "loss": 10.3653, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06811409110259685, | |
| "eval_loss": 10.37037181854248, | |
| "eval_runtime": 4.9285, | |
| "eval_samples_per_second": 1003.558, | |
| "eval_steps_per_second": 125.597, | |
| "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 | |
| } | |