| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013341894382228596, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00026683788764457196, | |
| "grad_norm": 22.89421844482422, | |
| "learning_rate": 5e-05, | |
| "loss": 99.4744, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026683788764457196, | |
| "eval_loss": 3.534377336502075, | |
| "eval_runtime": 2.9106, | |
| "eval_samples_per_second": 17.179, | |
| "eval_steps_per_second": 4.466, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005336757752891439, | |
| "grad_norm": 23.7343692779541, | |
| "learning_rate": 0.0001, | |
| "loss": 103.3411, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008005136629337158, | |
| "grad_norm": 48.079044342041016, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 101.9827, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010673515505782878, | |
| "grad_norm": 38.11738967895508, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 102.6331, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013341894382228596, | |
| "grad_norm": 32.43550109863281, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 98.8496, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016010273258674317, | |
| "grad_norm": 36.24091339111328, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 96.6713, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018678652135120035, | |
| "grad_norm": 37.49607467651367, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 94.9006, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021347031011565757, | |
| "grad_norm": 34.56901931762695, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 93.4301, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024015409888011475, | |
| "grad_norm": 31.850221633911133, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 91.105, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026683788764457193, | |
| "grad_norm": 43.924991607666016, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 93.5747, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002935216764090291, | |
| "grad_norm": 33.07682800292969, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 93.5264, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0032020546517348633, | |
| "grad_norm": 52.70429992675781, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 100.4311, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003468892539379435, | |
| "grad_norm": 91.30162048339844, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 103.5051, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003735730427024007, | |
| "grad_norm": 48.74945068359375, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 90.932, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004002568314668579, | |
| "grad_norm": 38.04246139526367, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 91.092, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004269406202313151, | |
| "grad_norm": 32.99767303466797, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 86.978, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004536244089957723, | |
| "grad_norm": 25.959495544433594, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 87.323, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004803081977602295, | |
| "grad_norm": 22.552183151245117, | |
| "learning_rate": 7.75e-05, | |
| "loss": 87.7695, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005069919865246866, | |
| "grad_norm": 17.352420806884766, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 87.1552, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0053367577528914386, | |
| "grad_norm": 14.216341018676758, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 87.1521, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005603595640536011, | |
| "grad_norm": 13.55358600616455, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 87.6133, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005870433528180582, | |
| "grad_norm": 18.19391441345215, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 86.9043, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006137271415825154, | |
| "grad_norm": 20.173397064208984, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 88.4352, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006404109303469727, | |
| "grad_norm": 27.15044403076172, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 89.5455, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006670947191114298, | |
| "grad_norm": 77.1603012084961, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 105.756, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006670947191114298, | |
| "eval_loss": 2.6978037357330322, | |
| "eval_runtime": 2.9516, | |
| "eval_samples_per_second": 16.94, | |
| "eval_steps_per_second": 4.404, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00693778507875887, | |
| "grad_norm": 14.102134704589844, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 85.3265, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0072046229664034424, | |
| "grad_norm": 16.71866798400879, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 86.5452, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007471460854048014, | |
| "grad_norm": 18.847749710083008, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 86.1274, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007738298741692586, | |
| "grad_norm": 17.256502151489258, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 85.8048, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008005136629337158, | |
| "grad_norm": 10.483077049255371, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 86.754, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00827197451698173, | |
| "grad_norm": 7.900310039520264, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 84.7266, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008538812404626303, | |
| "grad_norm": 10.001039505004883, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 85.7117, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008805650292270874, | |
| "grad_norm": 15.488116264343262, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 84.1797, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009072488179915445, | |
| "grad_norm": 20.616697311401367, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 85.459, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009339326067560017, | |
| "grad_norm": 25.470232009887695, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 83.8137, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00960616395520459, | |
| "grad_norm": 34.425106048583984, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 87.1356, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009873001842849161, | |
| "grad_norm": 74.32858276367188, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 89.267, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010139839730493733, | |
| "grad_norm": 67.69532012939453, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 99.5797, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010406677618138306, | |
| "grad_norm": 6.894927978515625, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 83.4439, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010673515505782877, | |
| "grad_norm": 7.002964496612549, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 84.3967, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010940353393427448, | |
| "grad_norm": 6.538271903991699, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 85.0133, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011207191281072022, | |
| "grad_norm": 7.0363383293151855, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 84.4411, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011474029168716593, | |
| "grad_norm": 7.243854522705078, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 85.7455, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011740867056361164, | |
| "grad_norm": 6.435781478881836, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 84.7364, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012007704944005737, | |
| "grad_norm": 7.823002338409424, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 83.3252, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012274542831650309, | |
| "grad_norm": 8.64023494720459, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 83.6382, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01254138071929488, | |
| "grad_norm": 7.904877185821533, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 84.5418, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012808218606939453, | |
| "grad_norm": 10.810150146484375, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 85.2486, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013075056494584025, | |
| "grad_norm": 17.670724868774414, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 87.8722, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013341894382228596, | |
| "grad_norm": 50.694305419921875, | |
| "learning_rate": 1e-05, | |
| "loss": 99.3798, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013341894382228596, | |
| "eval_loss": 2.659498691558838, | |
| "eval_runtime": 2.9744, | |
| "eval_samples_per_second": 16.81, | |
| "eval_steps_per_second": 4.371, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.259156315439104e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |