| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 19.931506849315067, | |
| "eval_steps": 500, | |
| "global_step": 1455, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 7.088261127471924, | |
| "learning_rate": 2.7397260273972603e-05, | |
| "loss": 1.4774, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 3.0658137798309326, | |
| "learning_rate": 5.479452054794521e-05, | |
| "loss": 0.5535, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 1.415347695350647, | |
| "learning_rate": 8.219178082191781e-05, | |
| "loss": 0.2769, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 1.2462260723114014, | |
| "learning_rate": 0.00010958904109589041, | |
| "loss": 0.2071, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 1.1219278573989868, | |
| "learning_rate": 0.000136986301369863, | |
| "loss": 0.179, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 2.4104228019714355, | |
| "learning_rate": 0.00016438356164383562, | |
| "loss": 0.1587, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 1.2239787578582764, | |
| "learning_rate": 0.0001917808219178082, | |
| "loss": 0.1366, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.095890410958904, | |
| "grad_norm": 0.9942715167999268, | |
| "learning_rate": 0.00019998733979961563, | |
| "loss": 0.1218, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2328767123287672, | |
| "grad_norm": 0.6293880939483643, | |
| "learning_rate": 0.0001999253383717226, | |
| "loss": 0.1168, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.36986301369863, | |
| "grad_norm": 0.7170248031616211, | |
| "learning_rate": 0.00019981170237143067, | |
| "loss": 0.1052, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5068493150684932, | |
| "grad_norm": 0.7464343905448914, | |
| "learning_rate": 0.00019964649051804355, | |
| "loss": 0.1066, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.643835616438356, | |
| "grad_norm": 0.6828764081001282, | |
| "learning_rate": 0.000199429788181734, | |
| "loss": 0.1057, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.7808219178082192, | |
| "grad_norm": 0.6028720736503601, | |
| "learning_rate": 0.0001991617073394306, | |
| "loss": 0.0843, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.9178082191780823, | |
| "grad_norm": 0.5440357327461243, | |
| "learning_rate": 0.00019884238651695556, | |
| "loss": 0.0948, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0547945205479454, | |
| "grad_norm": 0.8612964749336243, | |
| "learning_rate": 0.00019847199071744415, | |
| "loss": 0.085, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.191780821917808, | |
| "grad_norm": 0.889124870300293, | |
| "learning_rate": 0.00019805071133608242, | |
| "loss": 0.0962, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.328767123287671, | |
| "grad_norm": 0.45466411113739014, | |
| "learning_rate": 0.0001975787660612072, | |
| "loss": 0.0763, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.4657534246575343, | |
| "grad_norm": 0.42088282108306885, | |
| "learning_rate": 0.00019705639876181969, | |
| "loss": 0.0635, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.602739726027397, | |
| "grad_norm": 0.5170985460281372, | |
| "learning_rate": 0.00019648387936157068, | |
| "loss": 0.0726, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.73972602739726, | |
| "grad_norm": 0.4313249886035919, | |
| "learning_rate": 0.00019586150369928245, | |
| "loss": 0.0669, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.8767123287671232, | |
| "grad_norm": 0.3355115056037903, | |
| "learning_rate": 0.00019518959337607957, | |
| "loss": 0.0682, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0136986301369864, | |
| "grad_norm": 0.34427109360694885, | |
| "learning_rate": 0.0001944684955892075, | |
| "loss": 0.0638, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.1506849315068495, | |
| "grad_norm": 0.2929873466491699, | |
| "learning_rate": 0.0001936985829526247, | |
| "loss": 0.0632, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.287671232876712, | |
| "grad_norm": 0.3884938657283783, | |
| "learning_rate": 0.00019288025330446126, | |
| "loss": 0.0655, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.4246575342465753, | |
| "grad_norm": 0.27399152517318726, | |
| "learning_rate": 0.00019201392950144363, | |
| "loss": 0.0533, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.5616438356164384, | |
| "grad_norm": 0.2924444079399109, | |
| "learning_rate": 0.0001911000592003909, | |
| "loss": 0.0589, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.6986301369863015, | |
| "grad_norm": 0.43013861775398254, | |
| "learning_rate": 0.00019013911462689668, | |
| "loss": 0.0615, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.8356164383561646, | |
| "grad_norm": 0.5247001647949219, | |
| "learning_rate": 0.000189131592331315, | |
| "loss": 0.0583, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.9726027397260273, | |
| "grad_norm": 0.5796880722045898, | |
| "learning_rate": 0.00018807801293217735, | |
| "loss": 0.0556, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.109589041095891, | |
| "grad_norm": 0.5179729461669922, | |
| "learning_rate": 0.00018697892084717238, | |
| "loss": 0.056, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.2465753424657535, | |
| "grad_norm": 0.42960262298583984, | |
| "learning_rate": 0.00018583488401182843, | |
| "loss": 0.0637, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.383561643835616, | |
| "grad_norm": 0.3196163773536682, | |
| "learning_rate": 0.0001846464935860431, | |
| "loss": 0.0518, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.52054794520548, | |
| "grad_norm": 0.4424096643924713, | |
| "learning_rate": 0.0001834143636486124, | |
| "loss": 0.0524, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.657534246575342, | |
| "grad_norm": 0.50010746717453, | |
| "learning_rate": 0.00018213913087991685, | |
| "loss": 0.0629, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.794520547945205, | |
| "grad_norm": 0.4036540389060974, | |
| "learning_rate": 0.00018082145423292868, | |
| "loss": 0.0531, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.931506849315069, | |
| "grad_norm": 0.36036092042922974, | |
| "learning_rate": 0.0001794620145927101, | |
| "loss": 0.0556, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.068493150684931, | |
| "grad_norm": 0.22472509741783142, | |
| "learning_rate": 0.00017806151442457827, | |
| "loss": 0.0446, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.205479452054795, | |
| "grad_norm": 0.3514921963214874, | |
| "learning_rate": 0.00017662067741111974, | |
| "loss": 0.0443, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.342465753424658, | |
| "grad_norm": 0.2920095920562744, | |
| "learning_rate": 0.00017514024807824055, | |
| "loss": 0.0451, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.47945205479452, | |
| "grad_norm": 0.21051590144634247, | |
| "learning_rate": 0.00017362099141044626, | |
| "loss": 0.0476, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.616438356164384, | |
| "grad_norm": 0.36196619272232056, | |
| "learning_rate": 0.00017206369245555036, | |
| "loss": 0.0521, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.7534246575342465, | |
| "grad_norm": 0.3503723442554474, | |
| "learning_rate": 0.0001704691559190155, | |
| "loss": 0.0472, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.890410958904109, | |
| "grad_norm": 0.3881896734237671, | |
| "learning_rate": 0.0001688382057481364, | |
| "loss": 0.0537, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.027397260273973, | |
| "grad_norm": 0.29409492015838623, | |
| "learning_rate": 0.00016717168470628077, | |
| "loss": 0.0436, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.164383561643835, | |
| "grad_norm": 0.2455558031797409, | |
| "learning_rate": 0.0001654704539374066, | |
| "loss": 0.0429, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.301369863013699, | |
| "grad_norm": 0.30749672651290894, | |
| "learning_rate": 0.00016373539252108202, | |
| "loss": 0.042, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.438356164383562, | |
| "grad_norm": 0.4117829501628876, | |
| "learning_rate": 0.00016196739701823716, | |
| "loss": 0.0422, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.575342465753424, | |
| "grad_norm": 0.3047957718372345, | |
| "learning_rate": 0.00016016738100788297, | |
| "loss": 0.0456, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.712328767123288, | |
| "grad_norm": 0.3104310631752014, | |
| "learning_rate": 0.00015833627461503595, | |
| "loss": 0.0405, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.8493150684931505, | |
| "grad_norm": 0.3713166415691376, | |
| "learning_rate": 0.0001564750240300934, | |
| "loss": 0.0451, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.986301369863014, | |
| "grad_norm": 0.23804673552513123, | |
| "learning_rate": 0.00015458459101990693, | |
| "loss": 0.0387, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.123287671232877, | |
| "grad_norm": 0.4476951062679291, | |
| "learning_rate": 0.00015266595243080714, | |
| "loss": 0.0406, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.260273972602739, | |
| "grad_norm": 0.27973777055740356, | |
| "learning_rate": 0.00015072009968383656, | |
| "loss": 0.0464, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.397260273972603, | |
| "grad_norm": 0.3597777783870697, | |
| "learning_rate": 0.00014874803826245089, | |
| "loss": 0.0459, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.534246575342466, | |
| "grad_norm": 0.27027377486228943, | |
| "learning_rate": 0.00014675078719295415, | |
| "loss": 0.0375, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.671232876712329, | |
| "grad_norm": 0.27681443095207214, | |
| "learning_rate": 0.00014472937851793557, | |
| "loss": 0.0421, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.808219178082192, | |
| "grad_norm": 0.3312411904335022, | |
| "learning_rate": 0.00014268485676298078, | |
| "loss": 0.048, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.945205479452055, | |
| "grad_norm": 0.2358381599187851, | |
| "learning_rate": 0.0001406182783969324, | |
| "loss": 0.0409, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.082191780821917, | |
| "grad_norm": 0.19072838127613068, | |
| "learning_rate": 0.00013853071128597924, | |
| "loss": 0.0417, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.219178082191782, | |
| "grad_norm": 0.3328644931316376, | |
| "learning_rate": 0.0001364232341418564, | |
| "loss": 0.0397, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.356164383561644, | |
| "grad_norm": 0.27157458662986755, | |
| "learning_rate": 0.00013429693596444067, | |
| "loss": 0.0395, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.493150684931507, | |
| "grad_norm": 0.2969032824039459, | |
| "learning_rate": 0.00013215291547903006, | |
| "loss": 0.0406, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.63013698630137, | |
| "grad_norm": 0.2864357829093933, | |
| "learning_rate": 0.00012999228056859784, | |
| "loss": 0.0424, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.767123287671232, | |
| "grad_norm": 0.25885725021362305, | |
| "learning_rate": 0.00012781614770131442, | |
| "loss": 0.0392, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.904109589041095, | |
| "grad_norm": 0.2456735372543335, | |
| "learning_rate": 0.00012562564135363313, | |
| "loss": 0.0415, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.04109589041096, | |
| "grad_norm": 0.41431066393852234, | |
| "learning_rate": 0.0001234218934292376, | |
| "loss": 0.0407, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.178082191780822, | |
| "grad_norm": 0.260213702917099, | |
| "learning_rate": 0.00012120604267415172, | |
| "loss": 0.0393, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.315068493150685, | |
| "grad_norm": 0.3395901322364807, | |
| "learning_rate": 0.00011897923408831346, | |
| "loss": 0.035, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.452054794520548, | |
| "grad_norm": 0.3405311405658722, | |
| "learning_rate": 0.0001167426183339174, | |
| "loss": 0.0342, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.58904109589041, | |
| "grad_norm": 0.20802819728851318, | |
| "learning_rate": 0.00011449735114083127, | |
| "loss": 0.0347, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.726027397260275, | |
| "grad_norm": 0.5094506144523621, | |
| "learning_rate": 0.00011224459270939384, | |
| "loss": 0.0373, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.863013698630137, | |
| "grad_norm": 0.21799403429031372, | |
| "learning_rate": 0.000109985507110903, | |
| "loss": 0.0392, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.28433603048324585, | |
| "learning_rate": 0.00010772126168610325, | |
| "loss": 0.0373, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.136986301369863, | |
| "grad_norm": 0.3425813913345337, | |
| "learning_rate": 0.00010545302644198405, | |
| "loss": 0.0385, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.273972602739725, | |
| "grad_norm": 0.2662697434425354, | |
| "learning_rate": 0.00010318197344720018, | |
| "loss": 0.0347, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.41095890410959, | |
| "grad_norm": 0.2841816842556, | |
| "learning_rate": 0.0001009092762264271, | |
| "loss": 0.04, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 10.547945205479452, | |
| "grad_norm": 0.2933363914489746, | |
| "learning_rate": 9.863610915396365e-05, | |
| "loss": 0.0363, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 10.684931506849315, | |
| "grad_norm": 0.20692330598831177, | |
| "learning_rate": 9.63636468468959e-05, | |
| "loss": 0.0361, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 10.821917808219178, | |
| "grad_norm": 0.24741721153259277, | |
| "learning_rate": 9.409306355813529e-05, | |
| "loss": 0.0341, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 10.95890410958904, | |
| "grad_norm": 0.1948077529668808, | |
| "learning_rate": 9.18255325696454e-05, | |
| "loss": 0.0349, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.095890410958905, | |
| "grad_norm": 0.16165360808372498, | |
| "learning_rate": 8.956222558616998e-05, | |
| "loss": 0.0318, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 11.232876712328768, | |
| "grad_norm": 0.25702184438705444, | |
| "learning_rate": 8.730431212977625e-05, | |
| "loss": 0.0281, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 11.36986301369863, | |
| "grad_norm": 0.27587395906448364, | |
| "learning_rate": 8.505295893552594e-05, | |
| "loss": 0.0349, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 11.506849315068493, | |
| "grad_norm": 0.3140430152416229, | |
| "learning_rate": 8.280932934858652e-05, | |
| "loss": 0.0305, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 11.643835616438356, | |
| "grad_norm": 0.21165433526039124, | |
| "learning_rate": 8.05745827230941e-05, | |
| "loss": 0.0314, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 11.780821917808218, | |
| "grad_norm": 0.20445489883422852, | |
| "learning_rate": 7.834987382307861e-05, | |
| "loss": 0.0319, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 11.917808219178083, | |
| "grad_norm": 0.27832481265068054, | |
| "learning_rate": 7.613635222576072e-05, | |
| "loss": 0.0334, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 12.054794520547945, | |
| "grad_norm": 0.25728923082351685, | |
| "learning_rate": 7.393516172752919e-05, | |
| "loss": 0.033, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 12.191780821917808, | |
| "grad_norm": 0.2254086136817932, | |
| "learning_rate": 7.174743975290513e-05, | |
| "loss": 0.0346, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 12.32876712328767, | |
| "grad_norm": 0.31018713116645813, | |
| "learning_rate": 6.957431676679896e-05, | |
| "loss": 0.0329, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.465753424657533, | |
| "grad_norm": 0.32662343978881836, | |
| "learning_rate": 6.741691569036338e-05, | |
| "loss": 0.0342, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 12.602739726027398, | |
| "grad_norm": 0.2533169984817505, | |
| "learning_rate": 6.527635132074493e-05, | |
| "loss": 0.0264, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 12.73972602739726, | |
| "grad_norm": 0.27445635199546814, | |
| "learning_rate": 6.315372975503285e-05, | |
| "loss": 0.0281, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 12.876712328767123, | |
| "grad_norm": 0.21471256017684937, | |
| "learning_rate": 6.1050147818704e-05, | |
| "loss": 0.0321, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 13.013698630136986, | |
| "grad_norm": 0.19105984270572662, | |
| "learning_rate": 5.896669249885851e-05, | |
| "loss": 0.0273, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 13.150684931506849, | |
| "grad_norm": 0.3308360278606415, | |
| "learning_rate": 5.690444038253935e-05, | |
| "loss": 0.0343, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 13.287671232876713, | |
| "grad_norm": 0.1988590806722641, | |
| "learning_rate": 5.4864457100425783e-05, | |
| "loss": 0.028, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 13.424657534246576, | |
| "grad_norm": 0.1858794391155243, | |
| "learning_rate": 5.284779677618841e-05, | |
| "loss": 0.0273, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 13.561643835616438, | |
| "grad_norm": 0.29671627283096313, | |
| "learning_rate": 5.0855501481790305e-05, | |
| "loss": 0.0271, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 13.698630136986301, | |
| "grad_norm": 0.17693527042865753, | |
| "learning_rate": 4.8888600699015496e-05, | |
| "loss": 0.034, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 13.835616438356164, | |
| "grad_norm": 0.31038013100624084, | |
| "learning_rate": 4.694811078750338e-05, | |
| "loss": 0.0251, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 13.972602739726028, | |
| "grad_norm": 0.3317829668521881, | |
| "learning_rate": 4.50350344595635e-05, | |
| "loss": 0.0334, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 14.10958904109589, | |
| "grad_norm": 0.1818408966064453, | |
| "learning_rate": 4.315036026204262e-05, | |
| "loss": 0.0272, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 14.246575342465754, | |
| "grad_norm": 0.2105715572834015, | |
| "learning_rate": 4.129506206551138e-05, | |
| "loss": 0.025, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 14.383561643835616, | |
| "grad_norm": 0.18613150715827942, | |
| "learning_rate": 3.947009856103465e-05, | |
| "loss": 0.0238, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 14.520547945205479, | |
| "grad_norm": 0.2959461212158203, | |
| "learning_rate": 3.767641276478563e-05, | |
| "loss": 0.0249, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 14.657534246575342, | |
| "grad_norm": 0.18495745956897736, | |
| "learning_rate": 3.591493153075966e-05, | |
| "loss": 0.0214, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 14.794520547945206, | |
| "grad_norm": 0.1501263529062271, | |
| "learning_rate": 3.41865650718396e-05, | |
| "loss": 0.0266, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 14.931506849315069, | |
| "grad_norm": 0.3387095332145691, | |
| "learning_rate": 3.24922064894601e-05, | |
| "loss": 0.0268, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 15.068493150684931, | |
| "grad_norm": 0.23434942960739136, | |
| "learning_rate": 3.083273131211382e-05, | |
| "loss": 0.0272, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.205479452054794, | |
| "grad_norm": 0.163187175989151, | |
| "learning_rate": 2.920899704293849e-05, | |
| "loss": 0.0232, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 15.342465753424657, | |
| "grad_norm": 0.20000265538692474, | |
| "learning_rate": 2.762184271661785e-05, | |
| "loss": 0.0261, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 15.479452054794521, | |
| "grad_norm": 0.18943333625793457, | |
| "learning_rate": 2.6072088465826038e-05, | |
| "loss": 0.0246, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 15.616438356164384, | |
| "grad_norm": 0.2833252251148224, | |
| "learning_rate": 2.4560535097439108e-05, | |
| "loss": 0.0253, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 15.753424657534246, | |
| "grad_norm": 0.1302843540906906, | |
| "learning_rate": 2.308796367873296e-05, | |
| "loss": 0.0246, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 15.89041095890411, | |
| "grad_norm": 0.16615238785743713, | |
| "learning_rate": 2.165513513378121e-05, | |
| "loss": 0.0254, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 16.027397260273972, | |
| "grad_norm": 0.17113815248012543, | |
| "learning_rate": 2.0262789850261798e-05, | |
| "loss": 0.0288, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 16.164383561643834, | |
| "grad_norm": 0.21394069492816925, | |
| "learning_rate": 1.8911647296875147e-05, | |
| "loss": 0.025, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 16.301369863013697, | |
| "grad_norm": 0.2763649523258209, | |
| "learning_rate": 1.7602405651572275e-05, | |
| "loss": 0.0219, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 16.438356164383563, | |
| "grad_norm": 0.13925646245479584, | |
| "learning_rate": 1.6335741440784035e-05, | |
| "loss": 0.0217, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 16.575342465753426, | |
| "grad_norm": 0.20826192200183868, | |
| "learning_rate": 1.511230918983867e-05, | |
| "loss": 0.023, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 16.71232876712329, | |
| "grad_norm": 0.2256271094083786, | |
| "learning_rate": 1.3932741084747913e-05, | |
| "loss": 0.023, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 16.84931506849315, | |
| "grad_norm": 0.27016547322273254, | |
| "learning_rate": 1.2797646645536566e-05, | |
| "loss": 0.0211, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 16.986301369863014, | |
| "grad_norm": 0.26627489924430847, | |
| "learning_rate": 1.1707612411284253e-05, | |
| "loss": 0.0235, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 17.123287671232877, | |
| "grad_norm": 0.18498767912387848, | |
| "learning_rate": 1.0663201637042252e-05, | |
| "loss": 0.022, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 17.26027397260274, | |
| "grad_norm": 0.23852607607841492, | |
| "learning_rate": 9.664954002781745e-06, | |
| "loss": 0.0228, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 17.397260273972602, | |
| "grad_norm": 0.15411531925201416, | |
| "learning_rate": 8.713385334524283e-06, | |
| "loss": 0.0198, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 17.534246575342465, | |
| "grad_norm": 0.25403866171836853, | |
| "learning_rate": 7.808987337798158e-06, | |
| "loss": 0.0257, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 17.671232876712327, | |
| "grad_norm": 0.14403975009918213, | |
| "learning_rate": 6.952227343558671e-06, | |
| "loss": 0.0215, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 17.80821917808219, | |
| "grad_norm": 0.188527911901474, | |
| "learning_rate": 6.143548066703475e-06, | |
| "loss": 0.0224, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 17.945205479452056, | |
| "grad_norm": 0.1309424489736557, | |
| "learning_rate": 5.383367377307857e-06, | |
| "loss": 0.0215, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 18.08219178082192, | |
| "grad_norm": 0.11233002692461014, | |
| "learning_rate": 4.672078084698095e-06, | |
| "loss": 0.0211, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 18.21917808219178, | |
| "grad_norm": 0.22869743406772614, | |
| "learning_rate": 4.010047734474454e-06, | |
| "loss": 0.0215, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 18.356164383561644, | |
| "grad_norm": 0.11979719996452332, | |
| "learning_rate": 3.397618418588877e-06, | |
| "loss": 0.0273, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 18.493150684931507, | |
| "grad_norm": 0.2112375795841217, | |
| "learning_rate": 2.8351065985751766e-06, | |
| "loss": 0.0228, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 18.63013698630137, | |
| "grad_norm": 0.14134034514427185, | |
| "learning_rate": 2.322802942023461e-06, | |
| "loss": 0.0247, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 18.767123287671232, | |
| "grad_norm": 0.09884881973266602, | |
| "learning_rate": 1.8609721723830132e-06, | |
| "loss": 0.0196, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 18.904109589041095, | |
| "grad_norm": 0.14044946432113647, | |
| "learning_rate": 1.4498529321713584e-06, | |
| "loss": 0.0198, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 19.041095890410958, | |
| "grad_norm": 0.13853876292705536, | |
| "learning_rate": 1.0896576596600705e-06, | |
| "loss": 0.0182, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 19.17808219178082, | |
| "grad_norm": 0.1654110848903656, | |
| "learning_rate": 7.80572479101327e-07, | |
| "loss": 0.0229, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 19.315068493150687, | |
| "grad_norm": 0.15151838958263397, | |
| "learning_rate": 5.227571045515633e-07, | |
| "loss": 0.0202, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 19.45205479452055, | |
| "grad_norm": 0.2258201688528061, | |
| "learning_rate": 3.163447573422351e-07, | |
| "loss": 0.0197, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 19.589041095890412, | |
| "grad_norm": 0.24640779197216034, | |
| "learning_rate": 1.614420972401165e-07, | |
| "loss": 0.0187, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 19.726027397260275, | |
| "grad_norm": 0.21181590855121613, | |
| "learning_rate": 5.812916733284324e-08, | |
| "loss": 0.0198, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 19.863013698630137, | |
| "grad_norm": 0.14787183701992035, | |
| "learning_rate": 6.459352668164442e-09, | |
| "loss": 0.0186, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 19.931506849315067, | |
| "step": 1455, | |
| "total_flos": 1.1504025698630573e+17, | |
| "train_loss": 0.05927258820058554, | |
| "train_runtime": 1048.7401, | |
| "train_samples_per_second": 88.792, | |
| "train_steps_per_second": 1.387 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1455, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1504025698630573e+17, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |