| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0856313497822931, | |
| "eval_steps": 17, | |
| "global_step": 187, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005805515239477504, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.8715, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 0.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01741654571843251, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03483309143686502, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05224963715529753, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06966618287373004, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08708272859216255, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09869375907111756, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.9805, | |
| "eval_samples_per_second": 7.077, | |
| "eval_steps_per_second": 0.903, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10449927431059507, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12191582002902758, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13933236574746008, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1567489114658926, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1741654571843251, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19158200290275762, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19738751814223512, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.0205, | |
| "eval_samples_per_second": 7.07, | |
| "eval_steps_per_second": 0.902, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.20899854862119013, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.22641509433962265, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.24383164005805516, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2612481857764877, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.27866473149492016, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2960812772133527, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2960812772133527, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.0228, | |
| "eval_samples_per_second": 7.069, | |
| "eval_steps_per_second": 0.902, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3134978229317852, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3309143686502177, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3483309143686502, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.36574746008708275, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.38316400580551524, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.39477503628447025, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.999, | |
| "eval_samples_per_second": 7.073, | |
| "eval_steps_per_second": 0.902, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4005805515239477, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.41799709724238027, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.43541364296081275, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4528301886792453, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.4702467343976778, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.4876632801161103, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.4934687953555878, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.0012, | |
| "eval_samples_per_second": 7.073, | |
| "eval_steps_per_second": 0.902, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5050798258345428, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5224963715529753, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5399129172714079, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.5573294629898403, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.5747460087082729, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5921625544267054, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.5921625544267054, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.9845, | |
| "eval_samples_per_second": 7.076, | |
| "eval_steps_per_second": 0.903, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6095791001451378, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6269956458635704, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6444121915820029, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.6618287373004355, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.6792452830188679, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.690856313497823, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.9816, | |
| "eval_samples_per_second": 7.076, | |
| "eval_steps_per_second": 0.903, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.6966618287373004, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.714078374455733, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.7314949201741655, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.7489114658925979, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.7663280116110305, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.783744557329463, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7895500725689405, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.0342, | |
| "eval_samples_per_second": 7.067, | |
| "eval_steps_per_second": 0.902, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8011611030478955, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.818577648766328, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.8359941944847605, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.8534107402031931, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.8708272859216255, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.888243831640058, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.888243831640058, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.0536, | |
| "eval_samples_per_second": 7.064, | |
| "eval_steps_per_second": 0.901, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.9056603773584906, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.9404934687953556, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.9579100145137881, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9753265602322206, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.9869375907111756, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.0328, | |
| "eval_samples_per_second": 7.068, | |
| "eval_steps_per_second": 0.902, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9927431059506531, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.0101596516690856, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.0275761973875182, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.0449927431059507, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0624092888243832, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.0798258345428158, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.0856313497822931, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.9782, | |
| "eval_samples_per_second": 7.077, | |
| "eval_steps_per_second": 0.903, | |
| "step": 187 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.3524561305953894e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |