| { | |
| "best_metric": 0.936290979385376, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.047078208674159946, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009415641734831989, | |
| "grad_norm": 3.8461720943450928, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5958, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009415641734831989, | |
| "eval_loss": 1.838472604751587, | |
| "eval_runtime": 824.226, | |
| "eval_samples_per_second": 8.681, | |
| "eval_steps_per_second": 1.086, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018831283469663979, | |
| "grad_norm": 4.2466535568237305, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6918, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002824692520449597, | |
| "grad_norm": 2.6511600017547607, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.4523, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037662566939327957, | |
| "grad_norm": 1.0277491807937622, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1465, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004707820867415995, | |
| "grad_norm": 1.2869750261306763, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.097, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005649385040899194, | |
| "grad_norm": 0.8979297280311584, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.0728, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0065909492143823925, | |
| "grad_norm": 0.6931923031806946, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0463, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0075325133878655914, | |
| "grad_norm": 0.7879935503005981, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.092, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00847407756134879, | |
| "grad_norm": 0.7516279220581055, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.9826, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00941564173483199, | |
| "grad_norm": 0.7835001945495605, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0892, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010357205908315188, | |
| "grad_norm": 0.7206426858901978, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0094, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011298770081798387, | |
| "grad_norm": 0.7802558541297913, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9792, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012240334255281586, | |
| "grad_norm": 0.6156499981880188, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.941, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013181898428764785, | |
| "grad_norm": 0.5618372559547424, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0179, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014123462602247984, | |
| "grad_norm": 0.5174239277839661, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9344, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015065026775731183, | |
| "grad_norm": 0.5582432150840759, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.9726, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016006590949214382, | |
| "grad_norm": 0.5761141180992126, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9738, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01694815512269758, | |
| "grad_norm": 0.59812992811203, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9674, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01788971929618078, | |
| "grad_norm": 0.6350106000900269, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.9759, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01883128346966398, | |
| "grad_norm": 0.6189097166061401, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9705, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019772847643147178, | |
| "grad_norm": 0.6576741337776184, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9483, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.020714411816630376, | |
| "grad_norm": 0.6912825703620911, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.0014, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.021655975990113575, | |
| "grad_norm": 0.6828396320343018, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.959, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.022597540163596774, | |
| "grad_norm": 0.6953498721122742, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.9404, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023539104337079973, | |
| "grad_norm": 0.8147681355476379, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.9689, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023539104337079973, | |
| "eval_loss": 0.9542607665061951, | |
| "eval_runtime": 377.3703, | |
| "eval_samples_per_second": 18.96, | |
| "eval_steps_per_second": 2.372, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024480668510563172, | |
| "grad_norm": 0.46768563985824585, | |
| "learning_rate": 5e-05, | |
| "loss": 0.928, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02542223268404637, | |
| "grad_norm": 0.49125248193740845, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.9374, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02636379685752957, | |
| "grad_norm": 0.5207680463790894, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9841, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02730536103101277, | |
| "grad_norm": 0.5152724981307983, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8901, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.028246925204495968, | |
| "grad_norm": 0.5606867074966431, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9898, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.029188489377979167, | |
| "grad_norm": 0.609572172164917, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.9439, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.030130053551462366, | |
| "grad_norm": 0.590485155582428, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9188, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.031071617724945565, | |
| "grad_norm": 0.6072601675987244, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.988, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.032013181898428764, | |
| "grad_norm": 0.6646048426628113, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9882, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03295474607191196, | |
| "grad_norm": 0.6721041798591614, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.9303, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03389631024539516, | |
| "grad_norm": 0.6807247400283813, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.9333, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03483787441887836, | |
| "grad_norm": 0.7210736870765686, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.931, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03577943859236156, | |
| "grad_norm": 0.5208472013473511, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9138, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03672100276584476, | |
| "grad_norm": 0.4660947322845459, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.9754, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03766256693932796, | |
| "grad_norm": 0.4870927929878235, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9354, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.038604131112811156, | |
| "grad_norm": 0.4812670052051544, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8668, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.039545695286294355, | |
| "grad_norm": 0.560295045375824, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9332, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.040487259459777554, | |
| "grad_norm": 0.5502296090126038, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.897, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04142882363326075, | |
| "grad_norm": 0.5789206624031067, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9314, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04237038780674395, | |
| "grad_norm": 0.613252580165863, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9674, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04331195198022715, | |
| "grad_norm": 0.5821424722671509, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9128, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04425351615371035, | |
| "grad_norm": 0.6496718525886536, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9273, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04519508032719355, | |
| "grad_norm": 0.6486852765083313, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.8671, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04613664450067675, | |
| "grad_norm": 0.7399449348449707, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0272, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.047078208674159946, | |
| "grad_norm": 0.7195651531219482, | |
| "learning_rate": 0.0, | |
| "loss": 0.9048, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.047078208674159946, | |
| "eval_loss": 0.936290979385376, | |
| "eval_runtime": 377.2918, | |
| "eval_samples_per_second": 18.964, | |
| "eval_steps_per_second": 2.372, | |
| "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": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |