| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.072398190045249, | |
| "eval_steps": 500, | |
| "global_step": 56, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03619909502262444, | |
| "grad_norm": 2.867363214492798, | |
| "learning_rate": 3.7037037037037036e-07, | |
| "loss": 0.7721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07239819004524888, | |
| "grad_norm": 2.795196771621704, | |
| "learning_rate": 7.407407407407407e-07, | |
| "loss": 0.7534, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1085972850678733, | |
| "grad_norm": 2.8518760204315186, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.7531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14479638009049775, | |
| "grad_norm": 2.7276031970977783, | |
| "learning_rate": 1.4814814814814815e-06, | |
| "loss": 0.7604, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18099547511312217, | |
| "grad_norm": 2.6922106742858887, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.7775, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2171945701357466, | |
| "grad_norm": 2.8505051136016846, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.7689, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25339366515837103, | |
| "grad_norm": 2.711665153503418, | |
| "learning_rate": 2.5925925925925925e-06, | |
| "loss": 0.7687, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2895927601809955, | |
| "grad_norm": 2.7716190814971924, | |
| "learning_rate": 2.962962962962963e-06, | |
| "loss": 0.769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3257918552036199, | |
| "grad_norm": 2.607780933380127, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.7674, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.36199095022624433, | |
| "grad_norm": 2.305697202682495, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.7529, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39819004524886875, | |
| "grad_norm": 1.5863313674926758, | |
| "learning_rate": 4.074074074074074e-06, | |
| "loss": 0.7259, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4343891402714932, | |
| "grad_norm": 1.2682443857192993, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.7206, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.010533332824707, | |
| "learning_rate": 4.814814814814815e-06, | |
| "loss": 0.6921, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5067873303167421, | |
| "grad_norm": 0.9136636257171631, | |
| "learning_rate": 5.185185185185185e-06, | |
| "loss": 0.6987, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5429864253393665, | |
| "grad_norm": 1.275439739227295, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.6997, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.579185520361991, | |
| "grad_norm": 1.4839826822280884, | |
| "learning_rate": 5.925925925925926e-06, | |
| "loss": 0.6773, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.5695866346359253, | |
| "learning_rate": 6.296296296296297e-06, | |
| "loss": 0.6582, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6515837104072398, | |
| "grad_norm": 1.6517796516418457, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6912, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6877828054298643, | |
| "grad_norm": 1.3464380502700806, | |
| "learning_rate": 7.0370370370370375e-06, | |
| "loss": 0.6636, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7239819004524887, | |
| "grad_norm": 1.0865730047225952, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.6571, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7601809954751131, | |
| "grad_norm": 0.8862206339836121, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.6583, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7963800904977375, | |
| "grad_norm": 0.9783180952072144, | |
| "learning_rate": 8.148148148148148e-06, | |
| "loss": 0.6688, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.832579185520362, | |
| "grad_norm": 0.7160141468048096, | |
| "learning_rate": 8.518518518518519e-06, | |
| "loss": 0.6408, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8687782805429864, | |
| "grad_norm": 0.6991405487060547, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.6447, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9049773755656109, | |
| "grad_norm": 0.7763178944587708, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.6512, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.5905259847640991, | |
| "learning_rate": 9.62962962962963e-06, | |
| "loss": 0.6337, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9773755656108597, | |
| "grad_norm": 0.7515297532081604, | |
| "learning_rate": 1e-05, | |
| "loss": 0.655, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0361990950226245, | |
| "grad_norm": 1.260597825050354, | |
| "learning_rate": 9.999582149277188e-06, | |
| "loss": 1.2675, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0723981900452488, | |
| "grad_norm": 0.5624723434448242, | |
| "learning_rate": 9.998328666948437e-06, | |
| "loss": 0.5869, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1085972850678734, | |
| "grad_norm": 0.5378224849700928, | |
| "learning_rate": 9.996239762521152e-06, | |
| "loss": 0.5919, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1447963800904977, | |
| "grad_norm": 0.48451751470565796, | |
| "learning_rate": 9.993315785135417e-06, | |
| "loss": 0.5952, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1809954751131222, | |
| "grad_norm": 0.4453476071357727, | |
| "learning_rate": 9.989557223505661e-06, | |
| "loss": 0.5941, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2171945701357467, | |
| "grad_norm": 0.5747421979904175, | |
| "learning_rate": 9.98496470583896e-06, | |
| "loss": 0.6023, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.253393665158371, | |
| "grad_norm": 0.4679132401943207, | |
| "learning_rate": 9.979538999730047e-06, | |
| "loss": 0.5768, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2895927601809956, | |
| "grad_norm": 0.4853627383708954, | |
| "learning_rate": 9.973281012033009e-06, | |
| "loss": 0.5566, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3257918552036199, | |
| "grad_norm": 0.44682788848876953, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.5981, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3619909502262444, | |
| "grad_norm": 0.4072805941104889, | |
| "learning_rate": 9.958272514655006e-06, | |
| "loss": 0.5664, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3981900452488687, | |
| "grad_norm": 0.35199496150016785, | |
| "learning_rate": 9.949524513498636e-06, | |
| "loss": 0.5864, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4343891402714932, | |
| "grad_norm": 0.420901894569397, | |
| "learning_rate": 9.939949247384046e-06, | |
| "loss": 0.5558, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4705882352941178, | |
| "grad_norm": 0.39620932936668396, | |
| "learning_rate": 9.929548316723983e-06, | |
| "loss": 0.5713, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.506787330316742, | |
| "grad_norm": 0.36159488558769226, | |
| "learning_rate": 9.918323459933006e-06, | |
| "loss": 0.5712, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5429864253393664, | |
| "grad_norm": 0.3682953119277954, | |
| "learning_rate": 9.906276553136924e-06, | |
| "loss": 0.5543, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5791855203619911, | |
| "grad_norm": 0.35126638412475586, | |
| "learning_rate": 9.893409609859221e-06, | |
| "loss": 0.5615, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6153846153846154, | |
| "grad_norm": 0.38464972376823425, | |
| "learning_rate": 9.879724780684518e-06, | |
| "loss": 0.5635, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6515837104072397, | |
| "grad_norm": 0.37480273842811584, | |
| "learning_rate": 9.86522435289912e-06, | |
| "loss": 0.5618, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6877828054298643, | |
| "grad_norm": 0.388458788394928, | |
| "learning_rate": 9.849910750108718e-06, | |
| "loss": 0.5635, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7239819004524888, | |
| "grad_norm": 0.4044710099697113, | |
| "learning_rate": 9.833786531833311e-06, | |
| "loss": 0.5665, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.760180995475113, | |
| "grad_norm": 0.3484383821487427, | |
| "learning_rate": 9.816854393079402e-06, | |
| "loss": 0.5522, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7963800904977374, | |
| "grad_norm": 0.33232375979423523, | |
| "learning_rate": 9.79911716388956e-06, | |
| "loss": 0.5712, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8325791855203621, | |
| "grad_norm": 0.4234112501144409, | |
| "learning_rate": 9.7805778088694e-06, | |
| "loss": 0.5496, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8687782805429864, | |
| "grad_norm": 0.3586530387401581, | |
| "learning_rate": 9.761239426692077e-06, | |
| "loss": 0.5488, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.9049773755656108, | |
| "grad_norm": 0.34319135546684265, | |
| "learning_rate": 9.741105249580383e-06, | |
| "loss": 0.5534, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.9411764705882353, | |
| "grad_norm": 0.406502366065979, | |
| "learning_rate": 9.7201786427665e-06, | |
| "loss": 0.5765, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.9773755656108598, | |
| "grad_norm": 0.3931889533996582, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.561, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.0361990950226243, | |
| "grad_norm": 0.7969871759414673, | |
| "learning_rate": 9.67596226261095e-06, | |
| "loss": 0.9762, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.072398190045249, | |
| "grad_norm": 0.34094685316085815, | |
| "learning_rate": 9.652679879607843e-06, | |
| "loss": 0.5055, | |
| "step": 56 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 270, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 28, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 71041648754688.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |