| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.032137032305751725, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006427406461150345, | |
| "grad_norm": 0.458984375, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0419, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001285481292230069, | |
| "grad_norm": 8.8125, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0641, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019282219383451036, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 1.9999950454033063e-05, | |
| "loss": 3.2405, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002570962584460138, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 1.9999801816623205e-05, | |
| "loss": 2.8447, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032137032305751727, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.9999554089243305e-05, | |
| "loss": 2.9348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003856443876690207, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.9999207274348143e-05, | |
| "loss": 2.966, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004499184522805242, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.9998761375374376e-05, | |
| "loss": 2.8849, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.005141925168920276, | |
| "grad_norm": 0.953125, | |
| "learning_rate": 1.9998216396740497e-05, | |
| "loss": 2.8674, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0057846658150353105, | |
| "grad_norm": 0.96484375, | |
| "learning_rate": 1.9997572343846814e-05, | |
| "loss": 2.789, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006427406461150345, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.9996829223075363e-05, | |
| "loss": 2.8306, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0070701471072653795, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 1.9995987041789876e-05, | |
| "loss": 2.5481, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.007712887753380414, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 1.999504580833569e-05, | |
| "loss": 2.6249, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.00835562839949545, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 1.9994005532039665e-05, | |
| "loss": 2.6078, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.008998369045610483, | |
| "grad_norm": 1.328125, | |
| "learning_rate": 1.9992866223210105e-05, | |
| "loss": 2.4607, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.009641109691725517, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 1.999162789313664e-05, | |
| "loss": 2.3672, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.010283850337840551, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 1.9990290554090123e-05, | |
| "loss": 2.4135, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.010926590983955587, | |
| "grad_norm": 1.1484375, | |
| "learning_rate": 1.9988854219322507e-05, | |
| "loss": 2.5179, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.011569331630070621, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 1.9987318903066704e-05, | |
| "loss": 2.3391, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.012212072276185655, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.9985684620536466e-05, | |
| "loss": 2.4168, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.01285481292230069, | |
| "grad_norm": 1.4609375, | |
| "learning_rate": 1.9983951387926216e-05, | |
| "loss": 2.2706, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.013497553568415725, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 1.998211922241088e-05, | |
| "loss": 2.2684, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.014140294214530759, | |
| "grad_norm": 1.1640625, | |
| "learning_rate": 1.9980188142145755e-05, | |
| "loss": 2.2022, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.014783034860645793, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 1.997815816626628e-05, | |
| "loss": 2.2821, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.015425775506760829, | |
| "grad_norm": 1.359375, | |
| "learning_rate": 1.9976029314887882e-05, | |
| "loss": 2.1055, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.016068516152875863, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 1.9973801609105757e-05, | |
| "loss": 2.1481, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0167112567989909, | |
| "grad_norm": 1.2265625, | |
| "learning_rate": 1.9971475070994675e-05, | |
| "loss": 2.1277, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.01735399744510593, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 1.9969049723608753e-05, | |
| "loss": 2.1143, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.017996738091220967, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 1.9966525590981228e-05, | |
| "loss": 2.1824, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.018639478737336002, | |
| "grad_norm": 1.6171875, | |
| "learning_rate": 1.9963902698124212e-05, | |
| "loss": 2.1849, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.019282219383451035, | |
| "grad_norm": 0.96875, | |
| "learning_rate": 1.996118107102847e-05, | |
| "loss": 2.1996, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01992496002956607, | |
| "grad_norm": 1.1171875, | |
| "learning_rate": 1.9958360736663117e-05, | |
| "loss": 2.1914, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.020567700675681103, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 1.99554417229754e-05, | |
| "loss": 2.0519, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.02121044132179614, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 1.995242405889039e-05, | |
| "loss": 2.0804, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.021853181967911174, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 1.99493077743107e-05, | |
| "loss": 2.0424, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.022495922614026206, | |
| "grad_norm": 1.4296875, | |
| "learning_rate": 1.99460929001162e-05, | |
| "loss": 2.1151, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.023138663260141242, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 1.9942779468163696e-05, | |
| "loss": 1.8499, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.023781403906256278, | |
| "grad_norm": 0.8671875, | |
| "learning_rate": 1.9939367511286635e-05, | |
| "loss": 2.1271, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.02442414455237131, | |
| "grad_norm": 0.75, | |
| "learning_rate": 1.993585706329475e-05, | |
| "loss": 2.0739, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.025066885198486346, | |
| "grad_norm": 1.3671875, | |
| "learning_rate": 1.9932248158973746e-05, | |
| "loss": 2.0379, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.02570962584460138, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.992854083408496e-05, | |
| "loss": 1.9566, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.026352366490716414, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 1.992473512536499e-05, | |
| "loss": 2.0377, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.02699510713683145, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 1.992083107052534e-05, | |
| "loss": 1.9839, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.027637847782946486, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.9916828708252046e-05, | |
| "loss": 1.9477, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.028280588429061518, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 1.9912728078205285e-05, | |
| "loss": 2.0033, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.028923329075176554, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 1.9908529221018994e-05, | |
| "loss": 1.9196, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.029566069721291586, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.9904232178300465e-05, | |
| "loss": 1.9712, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.03020881036740662, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 1.9899836992629922e-05, | |
| "loss": 1.9251, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.030851551013521657, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.989534370756011e-05, | |
| "loss": 1.9695, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.03149429165963669, | |
| "grad_norm": 0.9765625, | |
| "learning_rate": 1.989075236761586e-05, | |
| "loss": 1.9208, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.032137032305751725, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.988606301829365e-05, | |
| "loss": 1.9474, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 10000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 1.915828644400333e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |