| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013789141051422005, | |
| "eval_steps": 500, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003447285262855501, | |
| "grad_norm": 2.125, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9343, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006894570525711002, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8061, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010341855788566503, | |
| "grad_norm": 0.9765625, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6954, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013789141051422005, | |
| "grad_norm": 1.4296875, | |
| "learning_rate": 0.0001999999738729554, | |
| "loss": 1.7722, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0017236426314277506, | |
| "grad_norm": 0.9453125, | |
| "learning_rate": 0.00019999983670600854, | |
| "loss": 1.8276, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0020683711577133006, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 0.00019999958196755926, | |
| "loss": 1.8313, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0024130996839988508, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 0.00019999920965790713, | |
| "loss": 1.8188, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002757828210284401, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 0.00019999871977748987, | |
| "loss": 1.8129, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003102556736569951, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 0.00019999811232688342, | |
| "loss": 1.8128, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0034472852628555013, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 0.000199997387306802, | |
| "loss": 1.8022, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0037920137891410514, | |
| "grad_norm": 1.25, | |
| "learning_rate": 0.000199996544718098, | |
| "loss": 1.9719, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004136742315426601, | |
| "grad_norm": 8.1875, | |
| "learning_rate": 0.00019999558456176205, | |
| "loss": 1.886, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004481470841712152, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 0.00019999450683892307, | |
| "loss": 1.8663, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0048261993679977015, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 0.00019999331155084812, | |
| "loss": 1.8967, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005170927894283252, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 0.00019999199869894256, | |
| "loss": 1.814, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005515656420568802, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 0.0001999905682847499, | |
| "loss": 1.8673, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0058603849468543525, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 0.0001999890203099519, | |
| "loss": 1.7688, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.006205113473139902, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 0.00019998735477636857, | |
| "loss": 1.8559, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.006549841999425453, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 0.00019998557168595803, | |
| "loss": 1.7875, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0068945705257110025, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 0.0001999836710408168, | |
| "loss": 1.8685, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.007239299051996552, | |
| "grad_norm": 8.125, | |
| "learning_rate": 0.00019998165284317945, | |
| "loss": 1.843, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.007584027578282103, | |
| "grad_norm": 6.34375, | |
| "learning_rate": 0.0001999795170954188, | |
| "loss": 1.8448, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.007928756104567653, | |
| "grad_norm": 15.4375, | |
| "learning_rate": 0.00019997726380004585, | |
| "loss": 1.876, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.008273484630853202, | |
| "grad_norm": 3.5, | |
| "learning_rate": 0.00019997489295970993, | |
| "loss": 1.8822, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.008618213157138753, | |
| "grad_norm": 1.625, | |
| "learning_rate": 0.00019997240457719838, | |
| "loss": 1.9351, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.008962941683424304, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 0.0001999697986554369, | |
| "loss": 1.8457, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.009307670209709854, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 0.00019996707519748927, | |
| "loss": 1.8246, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.009652398735995403, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 0.00019996423420655756, | |
| "loss": 1.8404, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.009997127262280954, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 0.00019996127568598193, | |
| "loss": 1.8068, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.010341855788566504, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 0.0001999581996392408, | |
| "loss": 1.7634, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.010686584314852055, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 0.00019995500606995065, | |
| "loss": 1.8114, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.011031312841137604, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 0.00019995169498186632, | |
| "loss": 1.7789, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.011376041367423154, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 0.00019994826637888065, | |
| "loss": 1.8287, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.011720769893708705, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 0.00019994472026502467, | |
| "loss": 1.8947, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.012065498419994254, | |
| "grad_norm": 1.828125, | |
| "learning_rate": 0.0001999410566444677, | |
| "loss": 1.8602, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.012410226946279804, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 0.00019993727552151708, | |
| "loss": 1.814, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.012754955472565355, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 0.00019993337690061834, | |
| "loss": 1.9383, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.013099683998850906, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 0.00019992936078635509, | |
| "loss": 1.8192, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.013444412525136454, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 0.00019992522718344927, | |
| "loss": 1.8127, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.013789141051422005, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 0.00019992097609676073, | |
| "loss": 1.8332, | |
| "step": 120 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 8702, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 60, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.9279066133561344e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |