| { | |
| "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": 21.58336067199707, | |
| "learning_rate": 5e-05, | |
| "loss": 99.4744, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026683788764457196, | |
| "eval_loss": 3.534377336502075, | |
| "eval_runtime": 2.9302, | |
| "eval_samples_per_second": 17.063, | |
| "eval_steps_per_second": 4.437, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005336757752891439, | |
| "grad_norm": 22.419708251953125, | |
| "learning_rate": 0.0001, | |
| "loss": 103.3411, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008005136629337158, | |
| "grad_norm": 44.11233901977539, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 101.998, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010673515505782878, | |
| "grad_norm": 39.20323181152344, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 102.6876, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013341894382228596, | |
| "grad_norm": 33.18415069580078, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 98.8706, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016010273258674317, | |
| "grad_norm": 35.75772476196289, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 96.6055, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018678652135120035, | |
| "grad_norm": 36.51875686645508, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 94.8261, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021347031011565757, | |
| "grad_norm": 33.68272018432617, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 93.3615, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024015409888011475, | |
| "grad_norm": 30.13109016418457, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 91.072, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026683788764457193, | |
| "grad_norm": 32.036537170410156, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 93.589, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002935216764090291, | |
| "grad_norm": 24.110986709594727, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 93.6183, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0032020546517348633, | |
| "grad_norm": 59.20383071899414, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 100.723, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003468892539379435, | |
| "grad_norm": 72.5294418334961, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 103.4235, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003735730427024007, | |
| "grad_norm": 49.615962982177734, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 90.5619, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004002568314668579, | |
| "grad_norm": 36.85390853881836, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 90.9424, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004269406202313151, | |
| "grad_norm": 28.41231346130371, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 86.9021, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004536244089957723, | |
| "grad_norm": 19.181047439575195, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 87.2284, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004803081977602295, | |
| "grad_norm": 16.206340789794922, | |
| "learning_rate": 7.75e-05, | |
| "loss": 87.68, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005069919865246866, | |
| "grad_norm": 13.560489654541016, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 87.0709, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0053367577528914386, | |
| "grad_norm": 13.36911678314209, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 87.0837, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005603595640536011, | |
| "grad_norm": 13.232701301574707, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 87.4922, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005870433528180582, | |
| "grad_norm": 19.99480438232422, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 86.7508, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006137271415825154, | |
| "grad_norm": 19.568359375, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 88.3357, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006404109303469727, | |
| "grad_norm": 30.02350425720215, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 89.6037, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006670947191114298, | |
| "grad_norm": 132.76075744628906, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 106.9513, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006670947191114298, | |
| "eval_loss": 2.699881076812744, | |
| "eval_runtime": 2.969, | |
| "eval_samples_per_second": 16.841, | |
| "eval_steps_per_second": 4.379, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00693778507875887, | |
| "grad_norm": 11.069785118103027, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 85.2464, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0072046229664034424, | |
| "grad_norm": 11.894067764282227, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 86.4133, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007471460854048014, | |
| "grad_norm": 11.504545211791992, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 85.9424, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007738298741692586, | |
| "grad_norm": 9.52103042602539, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 85.5899, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008005136629337158, | |
| "grad_norm": 8.053053855895996, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 86.4908, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00827197451698173, | |
| "grad_norm": 6.596405982971191, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 84.509, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008538812404626303, | |
| "grad_norm": 12.154988288879395, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 85.5146, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008805650292270874, | |
| "grad_norm": 12.631579399108887, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 84.0384, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009072488179915445, | |
| "grad_norm": 14.187871932983398, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 85.3073, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009339326067560017, | |
| "grad_norm": 17.819459915161133, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 83.8787, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00960616395520459, | |
| "grad_norm": 20.426162719726562, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 87.1894, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009873001842849161, | |
| "grad_norm": 31.33350944519043, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 89.3437, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010139839730493733, | |
| "grad_norm": 47.56151580810547, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 100.6103, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010406677618138306, | |
| "grad_norm": 6.464964866638184, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 83.3005, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010673515505782877, | |
| "grad_norm": 6.612872123718262, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 84.2439, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010940353393427448, | |
| "grad_norm": 6.869765758514404, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 84.894, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011207191281072022, | |
| "grad_norm": 5.677627086639404, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 84.2743, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011474029168716593, | |
| "grad_norm": 6.212136745452881, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 85.6072, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011740867056361164, | |
| "grad_norm": 6.752817153930664, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 84.6236, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012007704944005737, | |
| "grad_norm": 7.166438102722168, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 83.1906, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012274542831650309, | |
| "grad_norm": 7.727652549743652, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 83.4727, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01254138071929488, | |
| "grad_norm": 8.032402038574219, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 84.3546, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012808218606939453, | |
| "grad_norm": 10.028108596801758, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 84.996, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013075056494584025, | |
| "grad_norm": 15.79798698425293, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 87.5037, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013341894382228596, | |
| "grad_norm": 68.88801574707031, | |
| "learning_rate": 1e-05, | |
| "loss": 99.1348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013341894382228596, | |
| "eval_loss": 2.6576178073883057, | |
| "eval_runtime": 2.9174, | |
| "eval_samples_per_second": 17.139, | |
| "eval_steps_per_second": 4.456, | |
| "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 | |
| } | |