| { | |
| "best_metric": 0.607333779335022, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.020552344251766216, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00041104688503532436, | |
| "grad_norm": 0.42189228534698486, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5958, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041104688503532436, | |
| "eval_loss": 0.7471380829811096, | |
| "eval_runtime": 1.9158, | |
| "eval_samples_per_second": 26.098, | |
| "eval_steps_per_second": 6.786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008220937700706487, | |
| "grad_norm": 0.40581896901130676, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5299, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012331406551059731, | |
| "grad_norm": 0.30362221598625183, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.6054, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016441875401412974, | |
| "grad_norm": 0.18104228377342224, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.5701, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020552344251766217, | |
| "grad_norm": 0.32237139344215393, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.5833, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0024662813102119463, | |
| "grad_norm": 0.35897475481033325, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.6258, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0028773281952472704, | |
| "grad_norm": 0.26716870069503784, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.6258, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003288375080282595, | |
| "grad_norm": 0.16926148533821106, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.6284, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003699421965317919, | |
| "grad_norm": 0.1988511085510254, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.6702, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0041104688503532435, | |
| "grad_norm": 0.24423794448375702, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.6511, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004521515735388568, | |
| "grad_norm": 0.28637418150901794, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6656, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0049325626204238925, | |
| "grad_norm": 0.35017290711402893, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.752, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005343609505459216, | |
| "grad_norm": 0.25023409724235535, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.6468, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005754656390494541, | |
| "grad_norm": 0.14405648410320282, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.4637, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006165703275529865, | |
| "grad_norm": 0.15588894486427307, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.4921, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00657675016056519, | |
| "grad_norm": 0.1540333777666092, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5399, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006987797045600513, | |
| "grad_norm": 0.14874142408370972, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.542, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007398843930635838, | |
| "grad_norm": 0.18614919483661652, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.583, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0078098908156711624, | |
| "grad_norm": 0.17342880368232727, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5685, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008220937700706487, | |
| "grad_norm": 0.19265905022621155, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.6226, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008631984585741811, | |
| "grad_norm": 0.19549770653247833, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.5984, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009043031470777136, | |
| "grad_norm": 0.19770582020282745, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6333, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00945407835581246, | |
| "grad_norm": 0.25710514187812805, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6652, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009865125240847785, | |
| "grad_norm": 0.23367339372634888, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.7225, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010276172125883108, | |
| "grad_norm": 0.379349023103714, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.7839, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010276172125883108, | |
| "eval_loss": 0.6144869327545166, | |
| "eval_runtime": 1.8259, | |
| "eval_samples_per_second": 27.384, | |
| "eval_steps_per_second": 7.12, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010687219010918432, | |
| "grad_norm": 0.19118790328502655, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6411, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011098265895953757, | |
| "grad_norm": 0.16022659838199615, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.5458, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011509312780989081, | |
| "grad_norm": 0.15464924275875092, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.5753, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.011920359666024406, | |
| "grad_norm": 0.14745046198368073, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.5552, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01233140655105973, | |
| "grad_norm": 0.1524490863084793, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.5481, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012742453436095055, | |
| "grad_norm": 0.1493389755487442, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.6118, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01315350032113038, | |
| "grad_norm": 0.14796514809131622, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.5846, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013564547206165704, | |
| "grad_norm": 0.16894492506980896, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.561, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.013975594091201027, | |
| "grad_norm": 0.18197695910930634, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5872, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014386640976236351, | |
| "grad_norm": 0.1984691470861435, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.632, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014797687861271676, | |
| "grad_norm": 0.203140988945961, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.6874, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.015208734746307, | |
| "grad_norm": 0.24718748033046722, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.7103, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.015619781631342325, | |
| "grad_norm": 0.19124455749988556, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.574, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01603082851637765, | |
| "grad_norm": 0.11284204572439194, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.5393, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.016441875401412974, | |
| "grad_norm": 0.11567499488592148, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.5388, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0168529222864483, | |
| "grad_norm": 0.12443256378173828, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5278, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.017263969171483623, | |
| "grad_norm": 0.13997887074947357, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.5467, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.017675016056518947, | |
| "grad_norm": 0.14487455785274506, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.5852, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.018086062941554272, | |
| "grad_norm": 0.14718098938465118, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.6089, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.018497109826589597, | |
| "grad_norm": 0.1477862000465393, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6058, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01890815671162492, | |
| "grad_norm": 0.16084028780460358, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.6454, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.019319203596660246, | |
| "grad_norm": 0.1836438626050949, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.6058, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01973025048169557, | |
| "grad_norm": 0.2165912538766861, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.6425, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02014129736673089, | |
| "grad_norm": 0.21257087588310242, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.6357, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.020552344251766216, | |
| "grad_norm": 0.3003726303577423, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6998, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020552344251766216, | |
| "eval_loss": 0.607333779335022, | |
| "eval_runtime": 1.8278, | |
| "eval_samples_per_second": 27.355, | |
| "eval_steps_per_second": 7.112, | |
| "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": 6.167641412935352e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |