{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1542, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006485084306095979, "grad_norm": 24.875, "learning_rate": 0.0, "loss": 1.3724734783172607, "step": 1 }, { "epoch": 0.0012970168612191958, "grad_norm": 24.375, "learning_rate": 2.1505376344086024e-07, "loss": 1.33021080493927, "step": 2 }, { "epoch": 0.0019455252918287938, "grad_norm": 26.5, "learning_rate": 4.301075268817205e-07, "loss": 1.3725509643554688, "step": 3 }, { "epoch": 0.0025940337224383916, "grad_norm": 23.0, "learning_rate": 6.451612903225807e-07, "loss": 1.3191320896148682, "step": 4 }, { "epoch": 0.00324254215304799, "grad_norm": 27.25, "learning_rate": 8.60215053763441e-07, "loss": 1.5109095573425293, "step": 5 }, { "epoch": 0.0038910505836575876, "grad_norm": 24.875, "learning_rate": 1.0752688172043011e-06, "loss": 1.374070644378662, "step": 6 }, { "epoch": 0.004539559014267186, "grad_norm": 30.25, "learning_rate": 1.2903225806451614e-06, "loss": 1.5186113119125366, "step": 7 }, { "epoch": 0.005188067444876783, "grad_norm": 20.5, "learning_rate": 1.5053763440860217e-06, "loss": 1.2014234066009521, "step": 8 }, { "epoch": 0.005836575875486381, "grad_norm": 26.625, "learning_rate": 1.720430107526882e-06, "loss": 1.4034003019332886, "step": 9 }, { "epoch": 0.00648508430609598, "grad_norm": 20.5, "learning_rate": 1.935483870967742e-06, "loss": 1.1191078424453735, "step": 10 }, { "epoch": 0.007133592736705577, "grad_norm": 23.625, "learning_rate": 2.1505376344086023e-06, "loss": 1.26027512550354, "step": 11 }, { "epoch": 0.007782101167315175, "grad_norm": 25.0, "learning_rate": 2.3655913978494625e-06, "loss": 1.2375681400299072, "step": 12 }, { "epoch": 0.008430609597924773, "grad_norm": 24.125, "learning_rate": 2.580645161290323e-06, "loss": 1.141279935836792, "step": 13 }, { "epoch": 0.009079118028534372, "grad_norm": 22.0, "learning_rate": 2.7956989247311827e-06, "loss": 1.1289750337600708, "step": 14 }, { "epoch": 0.009727626459143969, "grad_norm": 20.0, "learning_rate": 3.0107526881720433e-06, "loss": 1.1203900575637817, "step": 15 }, { "epoch": 0.010376134889753566, "grad_norm": 16.75, "learning_rate": 3.225806451612903e-06, "loss": 1.0053768157958984, "step": 16 }, { "epoch": 0.011024643320363165, "grad_norm": 16.125, "learning_rate": 3.440860215053764e-06, "loss": 1.0518271923065186, "step": 17 }, { "epoch": 0.011673151750972763, "grad_norm": 14.875, "learning_rate": 3.655913978494624e-06, "loss": 1.0514507293701172, "step": 18 }, { "epoch": 0.01232166018158236, "grad_norm": 8.25, "learning_rate": 3.870967741935484e-06, "loss": 0.8515669107437134, "step": 19 }, { "epoch": 0.01297016861219196, "grad_norm": 4.375, "learning_rate": 4.086021505376344e-06, "loss": 0.9130498170852661, "step": 20 }, { "epoch": 0.013618677042801557, "grad_norm": 2.65625, "learning_rate": 4.3010752688172045e-06, "loss": 0.7604691386222839, "step": 21 }, { "epoch": 0.014267185473411154, "grad_norm": 3.046875, "learning_rate": 4.516129032258065e-06, "loss": 0.832431972026825, "step": 22 }, { "epoch": 0.014915693904020753, "grad_norm": 3.828125, "learning_rate": 4.731182795698925e-06, "loss": 0.8399982452392578, "step": 23 }, { "epoch": 0.01556420233463035, "grad_norm": 3.515625, "learning_rate": 4.946236559139785e-06, "loss": 0.8314268589019775, "step": 24 }, { "epoch": 0.01621271076523995, "grad_norm": 5.03125, "learning_rate": 5.161290322580646e-06, "loss": 0.8676307201385498, "step": 25 }, { "epoch": 0.016861219195849545, "grad_norm": 4.78125, "learning_rate": 5.376344086021506e-06, "loss": 0.8974037766456604, "step": 26 }, { "epoch": 0.017509727626459144, "grad_norm": 3.484375, "learning_rate": 5.591397849462365e-06, "loss": 0.8008823394775391, "step": 27 }, { "epoch": 0.018158236057068743, "grad_norm": 2.5625, "learning_rate": 5.806451612903226e-06, "loss": 0.7774126529693604, "step": 28 }, { "epoch": 0.01880674448767834, "grad_norm": 2.125, "learning_rate": 6.021505376344087e-06, "loss": 0.8016293048858643, "step": 29 }, { "epoch": 0.019455252918287938, "grad_norm": 1.890625, "learning_rate": 6.236559139784947e-06, "loss": 0.7487913966178894, "step": 30 }, { "epoch": 0.020103761348897537, "grad_norm": 1.765625, "learning_rate": 6.451612903225806e-06, "loss": 0.7031495571136475, "step": 31 }, { "epoch": 0.020752269779507133, "grad_norm": 2.140625, "learning_rate": 6.666666666666667e-06, "loss": 0.7010327577590942, "step": 32 }, { "epoch": 0.021400778210116732, "grad_norm": 1.828125, "learning_rate": 6.881720430107528e-06, "loss": 0.6680476665496826, "step": 33 }, { "epoch": 0.02204928664072633, "grad_norm": 1.5078125, "learning_rate": 7.096774193548388e-06, "loss": 0.6398488879203796, "step": 34 }, { "epoch": 0.022697795071335927, "grad_norm": 1.5234375, "learning_rate": 7.311827956989248e-06, "loss": 0.6156654357910156, "step": 35 }, { "epoch": 0.023346303501945526, "grad_norm": 1.21875, "learning_rate": 7.526881720430108e-06, "loss": 0.5700726509094238, "step": 36 }, { "epoch": 0.023994811932555125, "grad_norm": 0.671875, "learning_rate": 7.741935483870968e-06, "loss": 0.4970965087413788, "step": 37 }, { "epoch": 0.02464332036316472, "grad_norm": 0.6484375, "learning_rate": 7.956989247311828e-06, "loss": 0.49744293093681335, "step": 38 }, { "epoch": 0.02529182879377432, "grad_norm": 0.79296875, "learning_rate": 8.172043010752689e-06, "loss": 0.5822708606719971, "step": 39 }, { "epoch": 0.02594033722438392, "grad_norm": 0.66015625, "learning_rate": 8.387096774193549e-06, "loss": 0.5359759330749512, "step": 40 }, { "epoch": 0.026588845654993514, "grad_norm": 0.4921875, "learning_rate": 8.602150537634409e-06, "loss": 0.5212804675102234, "step": 41 }, { "epoch": 0.027237354085603113, "grad_norm": 0.478515625, "learning_rate": 8.81720430107527e-06, "loss": 0.5423698425292969, "step": 42 }, { "epoch": 0.027885862516212712, "grad_norm": 0.392578125, "learning_rate": 9.03225806451613e-06, "loss": 0.5061851143836975, "step": 43 }, { "epoch": 0.028534370946822308, "grad_norm": 0.345703125, "learning_rate": 9.24731182795699e-06, "loss": 0.4676480293273926, "step": 44 }, { "epoch": 0.029182879377431907, "grad_norm": 0.3515625, "learning_rate": 9.46236559139785e-06, "loss": 0.49201688170433044, "step": 45 }, { "epoch": 0.029831387808041506, "grad_norm": 0.373046875, "learning_rate": 9.67741935483871e-06, "loss": 0.5090270638465881, "step": 46 }, { "epoch": 0.0304798962386511, "grad_norm": 0.298828125, "learning_rate": 9.89247311827957e-06, "loss": 0.4487128257751465, "step": 47 }, { "epoch": 0.0311284046692607, "grad_norm": 0.306640625, "learning_rate": 1.0107526881720431e-05, "loss": 0.42448240518569946, "step": 48 }, { "epoch": 0.031776913099870296, "grad_norm": 0.361328125, "learning_rate": 1.0322580645161291e-05, "loss": 0.47866204380989075, "step": 49 }, { "epoch": 0.0324254215304799, "grad_norm": 0.298828125, "learning_rate": 1.0537634408602151e-05, "loss": 0.4911368489265442, "step": 50 }, { "epoch": 0.033073929961089495, "grad_norm": 0.271484375, "learning_rate": 1.0752688172043012e-05, "loss": 0.4574756622314453, "step": 51 }, { "epoch": 0.03372243839169909, "grad_norm": 0.279296875, "learning_rate": 1.096774193548387e-05, "loss": 0.487529993057251, "step": 52 }, { "epoch": 0.03437094682230869, "grad_norm": 0.251953125, "learning_rate": 1.118279569892473e-05, "loss": 0.42067378759384155, "step": 53 }, { "epoch": 0.03501945525291829, "grad_norm": 0.265625, "learning_rate": 1.1397849462365593e-05, "loss": 0.4540294408798218, "step": 54 }, { "epoch": 0.035667963683527884, "grad_norm": 0.251953125, "learning_rate": 1.1612903225806453e-05, "loss": 0.4302766025066376, "step": 55 }, { "epoch": 0.03631647211413749, "grad_norm": 0.27734375, "learning_rate": 1.1827956989247313e-05, "loss": 0.5048185586929321, "step": 56 }, { "epoch": 0.03696498054474708, "grad_norm": 0.255859375, "learning_rate": 1.2043010752688173e-05, "loss": 0.4567241072654724, "step": 57 }, { "epoch": 0.03761348897535668, "grad_norm": 0.2490234375, "learning_rate": 1.2258064516129034e-05, "loss": 0.46765631437301636, "step": 58 }, { "epoch": 0.03826199740596628, "grad_norm": 0.2734375, "learning_rate": 1.2473118279569894e-05, "loss": 0.4931251108646393, "step": 59 }, { "epoch": 0.038910505836575876, "grad_norm": 0.263671875, "learning_rate": 1.2688172043010754e-05, "loss": 0.459461510181427, "step": 60 }, { "epoch": 0.03955901426718547, "grad_norm": 0.2470703125, "learning_rate": 1.2903225806451613e-05, "loss": 0.4404521584510803, "step": 61 }, { "epoch": 0.040207522697795074, "grad_norm": 0.240234375, "learning_rate": 1.3118279569892473e-05, "loss": 0.40942245721817017, "step": 62 }, { "epoch": 0.04085603112840467, "grad_norm": 0.24609375, "learning_rate": 1.3333333333333333e-05, "loss": 0.46552544832229614, "step": 63 }, { "epoch": 0.041504539559014265, "grad_norm": 0.244140625, "learning_rate": 1.3548387096774194e-05, "loss": 0.4526595175266266, "step": 64 }, { "epoch": 0.04215304798962387, "grad_norm": 0.2197265625, "learning_rate": 1.3763440860215056e-05, "loss": 0.42087337374687195, "step": 65 }, { "epoch": 0.042801556420233464, "grad_norm": 0.2353515625, "learning_rate": 1.3978494623655916e-05, "loss": 0.4462112784385681, "step": 66 }, { "epoch": 0.04345006485084306, "grad_norm": 0.2197265625, "learning_rate": 1.4193548387096776e-05, "loss": 0.4387781620025635, "step": 67 }, { "epoch": 0.04409857328145266, "grad_norm": 0.2255859375, "learning_rate": 1.4408602150537636e-05, "loss": 0.44689416885375977, "step": 68 }, { "epoch": 0.04474708171206226, "grad_norm": 0.2255859375, "learning_rate": 1.4623655913978497e-05, "loss": 0.44348466396331787, "step": 69 }, { "epoch": 0.04539559014267185, "grad_norm": 0.224609375, "learning_rate": 1.4838709677419357e-05, "loss": 0.4309629201889038, "step": 70 }, { "epoch": 0.046044098573281456, "grad_norm": 0.21875, "learning_rate": 1.5053763440860215e-05, "loss": 0.479592502117157, "step": 71 }, { "epoch": 0.04669260700389105, "grad_norm": 0.2236328125, "learning_rate": 1.5268817204301076e-05, "loss": 0.43672889471054077, "step": 72 }, { "epoch": 0.04734111543450065, "grad_norm": 0.2265625, "learning_rate": 1.5483870967741936e-05, "loss": 0.43101170659065247, "step": 73 }, { "epoch": 0.04798962386511025, "grad_norm": 0.224609375, "learning_rate": 1.5698924731182796e-05, "loss": 0.436391144990921, "step": 74 }, { "epoch": 0.048638132295719845, "grad_norm": 0.2119140625, "learning_rate": 1.5913978494623657e-05, "loss": 0.4143087565898895, "step": 75 }, { "epoch": 0.04928664072632944, "grad_norm": 0.2275390625, "learning_rate": 1.6129032258064517e-05, "loss": 0.446614146232605, "step": 76 }, { "epoch": 0.04993514915693904, "grad_norm": 0.2119140625, "learning_rate": 1.6344086021505377e-05, "loss": 0.4443016052246094, "step": 77 }, { "epoch": 0.05058365758754864, "grad_norm": 0.2314453125, "learning_rate": 1.6559139784946237e-05, "loss": 0.42434102296829224, "step": 78 }, { "epoch": 0.051232166018158234, "grad_norm": 0.2216796875, "learning_rate": 1.6774193548387098e-05, "loss": 0.43161994218826294, "step": 79 }, { "epoch": 0.05188067444876784, "grad_norm": 0.2119140625, "learning_rate": 1.6989247311827958e-05, "loss": 0.4179801344871521, "step": 80 }, { "epoch": 0.05252918287937743, "grad_norm": 0.201171875, "learning_rate": 1.7204301075268818e-05, "loss": 0.41737961769104004, "step": 81 }, { "epoch": 0.05317769130998703, "grad_norm": 0.205078125, "learning_rate": 1.741935483870968e-05, "loss": 0.42671385407447815, "step": 82 }, { "epoch": 0.05382619974059663, "grad_norm": 0.2099609375, "learning_rate": 1.763440860215054e-05, "loss": 0.42453673481941223, "step": 83 }, { "epoch": 0.054474708171206226, "grad_norm": 0.2158203125, "learning_rate": 1.78494623655914e-05, "loss": 0.44486096501350403, "step": 84 }, { "epoch": 0.05512321660181582, "grad_norm": 0.2099609375, "learning_rate": 1.806451612903226e-05, "loss": 0.41659870743751526, "step": 85 }, { "epoch": 0.055771725032425425, "grad_norm": 0.212890625, "learning_rate": 1.827956989247312e-05, "loss": 0.42657533288002014, "step": 86 }, { "epoch": 0.05642023346303502, "grad_norm": 0.197265625, "learning_rate": 1.849462365591398e-05, "loss": 0.43333303928375244, "step": 87 }, { "epoch": 0.057068741893644616, "grad_norm": 0.2138671875, "learning_rate": 1.870967741935484e-05, "loss": 0.39696574211120605, "step": 88 }, { "epoch": 0.05771725032425422, "grad_norm": 0.205078125, "learning_rate": 1.89247311827957e-05, "loss": 0.428231805562973, "step": 89 }, { "epoch": 0.058365758754863814, "grad_norm": 0.2109375, "learning_rate": 1.913978494623656e-05, "loss": 0.41363203525543213, "step": 90 }, { "epoch": 0.05901426718547341, "grad_norm": 0.1953125, "learning_rate": 1.935483870967742e-05, "loss": 0.4199996590614319, "step": 91 }, { "epoch": 0.05966277561608301, "grad_norm": 0.201171875, "learning_rate": 1.956989247311828e-05, "loss": 0.436684787273407, "step": 92 }, { "epoch": 0.06031128404669261, "grad_norm": 0.201171875, "learning_rate": 1.978494623655914e-05, "loss": 0.447677344083786, "step": 93 }, { "epoch": 0.0609597924773022, "grad_norm": 0.2109375, "learning_rate": 2e-05, "loss": 0.40784865617752075, "step": 94 }, { "epoch": 0.061608300907911806, "grad_norm": 0.2041015625, "learning_rate": 1.9999994483839634e-05, "loss": 0.4047895073890686, "step": 95 }, { "epoch": 0.0622568093385214, "grad_norm": 0.2119140625, "learning_rate": 1.999997793536461e-05, "loss": 0.4164491295814514, "step": 96 }, { "epoch": 0.062905317769131, "grad_norm": 0.2041015625, "learning_rate": 1.9999950354593198e-05, "loss": 0.4433131814002991, "step": 97 }, { "epoch": 0.06355382619974059, "grad_norm": 0.2041015625, "learning_rate": 1.9999911741555812e-05, "loss": 0.40185704827308655, "step": 98 }, { "epoch": 0.06420233463035019, "grad_norm": 0.203125, "learning_rate": 1.9999862096295063e-05, "loss": 0.4227330684661865, "step": 99 }, { "epoch": 0.0648508430609598, "grad_norm": 0.1982421875, "learning_rate": 1.999980141886571e-05, "loss": 0.3818020224571228, "step": 100 }, { "epoch": 0.0654993514915694, "grad_norm": 0.2060546875, "learning_rate": 1.9999729709334704e-05, "loss": 0.38270384073257446, "step": 101 }, { "epoch": 0.06614785992217899, "grad_norm": 0.208984375, "learning_rate": 1.9999646967781153e-05, "loss": 0.40086784958839417, "step": 102 }, { "epoch": 0.06679636835278858, "grad_norm": 0.203125, "learning_rate": 1.9999553194296343e-05, "loss": 0.409895658493042, "step": 103 }, { "epoch": 0.06744487678339818, "grad_norm": 0.21875, "learning_rate": 1.9999448388983725e-05, "loss": 0.4114656448364258, "step": 104 }, { "epoch": 0.06809338521400778, "grad_norm": 0.2138671875, "learning_rate": 1.9999332551958924e-05, "loss": 0.3995349407196045, "step": 105 }, { "epoch": 0.06874189364461739, "grad_norm": 0.2119140625, "learning_rate": 1.9999205683349733e-05, "loss": 0.4112667441368103, "step": 106 }, { "epoch": 0.06939040207522698, "grad_norm": 0.2080078125, "learning_rate": 1.9999067783296123e-05, "loss": 0.38258546590805054, "step": 107 }, { "epoch": 0.07003891050583658, "grad_norm": 0.20703125, "learning_rate": 1.9998918851950226e-05, "loss": 0.36877691745758057, "step": 108 }, { "epoch": 0.07068741893644617, "grad_norm": 0.2099609375, "learning_rate": 1.9998758889476346e-05, "loss": 0.405431866645813, "step": 109 }, { "epoch": 0.07133592736705577, "grad_norm": 0.20703125, "learning_rate": 1.9998587896050964e-05, "loss": 0.39622762799263, "step": 110 }, { "epoch": 0.07198443579766536, "grad_norm": 0.2001953125, "learning_rate": 1.9998405871862724e-05, "loss": 0.3759191334247589, "step": 111 }, { "epoch": 0.07263294422827497, "grad_norm": 0.19921875, "learning_rate": 1.9998212817112437e-05, "loss": 0.39343106746673584, "step": 112 }, { "epoch": 0.07328145265888457, "grad_norm": 0.201171875, "learning_rate": 1.999800873201309e-05, "loss": 0.36645883321762085, "step": 113 }, { "epoch": 0.07392996108949416, "grad_norm": 0.220703125, "learning_rate": 1.9997793616789837e-05, "loss": 0.37583309412002563, "step": 114 }, { "epoch": 0.07457846952010376, "grad_norm": 0.205078125, "learning_rate": 1.9997567471679996e-05, "loss": 0.3862660825252533, "step": 115 }, { "epoch": 0.07522697795071336, "grad_norm": 0.205078125, "learning_rate": 1.9997330296933066e-05, "loss": 0.3778155744075775, "step": 116 }, { "epoch": 0.07587548638132295, "grad_norm": 0.2080078125, "learning_rate": 1.9997082092810697e-05, "loss": 0.4014049172401428, "step": 117 }, { "epoch": 0.07652399481193256, "grad_norm": 0.2197265625, "learning_rate": 1.999682285958672e-05, "loss": 0.4239310920238495, "step": 118 }, { "epoch": 0.07717250324254216, "grad_norm": 0.201171875, "learning_rate": 1.9996552597547127e-05, "loss": 0.39182862639427185, "step": 119 }, { "epoch": 0.07782101167315175, "grad_norm": 0.201171875, "learning_rate": 1.9996271306990084e-05, "loss": 0.3869522213935852, "step": 120 }, { "epoch": 0.07846952010376135, "grad_norm": 0.2158203125, "learning_rate": 1.9995978988225912e-05, "loss": 0.3912217617034912, "step": 121 }, { "epoch": 0.07911802853437094, "grad_norm": 0.2080078125, "learning_rate": 1.9995675641577117e-05, "loss": 0.372033029794693, "step": 122 }, { "epoch": 0.07976653696498054, "grad_norm": 0.208984375, "learning_rate": 1.9995361267378355e-05, "loss": 0.3970673084259033, "step": 123 }, { "epoch": 0.08041504539559015, "grad_norm": 0.203125, "learning_rate": 1.999503586597645e-05, "loss": 0.3746938109397888, "step": 124 }, { "epoch": 0.08106355382619974, "grad_norm": 0.1982421875, "learning_rate": 1.9994699437730402e-05, "loss": 0.3660721778869629, "step": 125 }, { "epoch": 0.08171206225680934, "grad_norm": 0.208984375, "learning_rate": 1.9994351983011367e-05, "loss": 0.38770291209220886, "step": 126 }, { "epoch": 0.08236057068741894, "grad_norm": 0.203125, "learning_rate": 1.9993993502202666e-05, "loss": 0.40048661828041077, "step": 127 }, { "epoch": 0.08300907911802853, "grad_norm": 0.205078125, "learning_rate": 1.999362399569979e-05, "loss": 0.37481701374053955, "step": 128 }, { "epoch": 0.08365758754863813, "grad_norm": 0.2099609375, "learning_rate": 1.999324346391039e-05, "loss": 0.38433510065078735, "step": 129 }, { "epoch": 0.08430609597924774, "grad_norm": 0.2001953125, "learning_rate": 1.9992851907254275e-05, "loss": 0.3568296432495117, "step": 130 }, { "epoch": 0.08495460440985733, "grad_norm": 0.208984375, "learning_rate": 1.999244932616343e-05, "loss": 0.39519092440605164, "step": 131 }, { "epoch": 0.08560311284046693, "grad_norm": 0.2138671875, "learning_rate": 1.9992035721081994e-05, "loss": 0.3783279359340668, "step": 132 }, { "epoch": 0.08625162127107652, "grad_norm": 0.2021484375, "learning_rate": 1.9991611092466264e-05, "loss": 0.40476328134536743, "step": 133 }, { "epoch": 0.08690012970168612, "grad_norm": 0.2021484375, "learning_rate": 1.9991175440784715e-05, "loss": 0.3811950087547302, "step": 134 }, { "epoch": 0.08754863813229571, "grad_norm": 0.205078125, "learning_rate": 1.999072876651796e-05, "loss": 0.37133097648620605, "step": 135 }, { "epoch": 0.08819714656290532, "grad_norm": 0.201171875, "learning_rate": 1.9990271070158792e-05, "loss": 0.3922561705112457, "step": 136 }, { "epoch": 0.08884565499351492, "grad_norm": 0.2080078125, "learning_rate": 1.998980235221215e-05, "loss": 0.3603026270866394, "step": 137 }, { "epoch": 0.08949416342412451, "grad_norm": 0.2099609375, "learning_rate": 1.9989322613195145e-05, "loss": 0.4048859179019928, "step": 138 }, { "epoch": 0.09014267185473411, "grad_norm": 0.2060546875, "learning_rate": 1.9988831853637042e-05, "loss": 0.36560121178627014, "step": 139 }, { "epoch": 0.0907911802853437, "grad_norm": 0.2001953125, "learning_rate": 1.9988330074079254e-05, "loss": 0.39202678203582764, "step": 140 }, { "epoch": 0.0914396887159533, "grad_norm": 0.2138671875, "learning_rate": 1.9987817275075364e-05, "loss": 0.3897934556007385, "step": 141 }, { "epoch": 0.09208819714656291, "grad_norm": 0.1943359375, "learning_rate": 1.9987293457191114e-05, "loss": 0.3877807855606079, "step": 142 }, { "epoch": 0.0927367055771725, "grad_norm": 0.2109375, "learning_rate": 1.998675862100439e-05, "loss": 0.3831649124622345, "step": 143 }, { "epoch": 0.0933852140077821, "grad_norm": 0.2080078125, "learning_rate": 1.998621276710524e-05, "loss": 0.390967458486557, "step": 144 }, { "epoch": 0.0940337224383917, "grad_norm": 0.19921875, "learning_rate": 1.9985655896095868e-05, "loss": 0.3698822855949402, "step": 145 }, { "epoch": 0.0946822308690013, "grad_norm": 0.19921875, "learning_rate": 1.998508800859064e-05, "loss": 0.371660053730011, "step": 146 }, { "epoch": 0.09533073929961089, "grad_norm": 0.201171875, "learning_rate": 1.9984509105216054e-05, "loss": 0.37307265400886536, "step": 147 }, { "epoch": 0.0959792477302205, "grad_norm": 0.20703125, "learning_rate": 1.9983919186610786e-05, "loss": 0.4003124237060547, "step": 148 }, { "epoch": 0.0966277561608301, "grad_norm": 0.2138671875, "learning_rate": 1.9983318253425656e-05, "loss": 0.39315009117126465, "step": 149 }, { "epoch": 0.09727626459143969, "grad_norm": 0.2021484375, "learning_rate": 1.9982706306323618e-05, "loss": 0.3843832314014435, "step": 150 }, { "epoch": 0.09792477302204929, "grad_norm": 0.2001953125, "learning_rate": 1.9982083345979803e-05, "loss": 0.38168150186538696, "step": 151 }, { "epoch": 0.09857328145265888, "grad_norm": 0.2021484375, "learning_rate": 1.9981449373081478e-05, "loss": 0.365963339805603, "step": 152 }, { "epoch": 0.09922178988326848, "grad_norm": 0.2236328125, "learning_rate": 1.9980804388328056e-05, "loss": 0.3867374062538147, "step": 153 }, { "epoch": 0.09987029831387809, "grad_norm": 0.203125, "learning_rate": 1.9980148392431117e-05, "loss": 0.3945177495479584, "step": 154 }, { "epoch": 0.10051880674448768, "grad_norm": 0.216796875, "learning_rate": 1.997948138611437e-05, "loss": 0.3945233225822449, "step": 155 }, { "epoch": 0.10116731517509728, "grad_norm": 0.2060546875, "learning_rate": 1.9978803370113676e-05, "loss": 0.35957130789756775, "step": 156 }, { "epoch": 0.10181582360570687, "grad_norm": 0.2060546875, "learning_rate": 1.997811434517705e-05, "loss": 0.3516426086425781, "step": 157 }, { "epoch": 0.10246433203631647, "grad_norm": 0.2080078125, "learning_rate": 1.997741431206464e-05, "loss": 0.4016244411468506, "step": 158 }, { "epoch": 0.10311284046692606, "grad_norm": 0.20703125, "learning_rate": 1.9976703271548747e-05, "loss": 0.362133264541626, "step": 159 }, { "epoch": 0.10376134889753567, "grad_norm": 0.2138671875, "learning_rate": 1.9975981224413815e-05, "loss": 0.4081648588180542, "step": 160 }, { "epoch": 0.10440985732814527, "grad_norm": 0.2060546875, "learning_rate": 1.9975248171456432e-05, "loss": 0.3553345203399658, "step": 161 }, { "epoch": 0.10505836575875487, "grad_norm": 0.19921875, "learning_rate": 1.997450411348532e-05, "loss": 0.3703160583972931, "step": 162 }, { "epoch": 0.10570687418936446, "grad_norm": 0.216796875, "learning_rate": 1.997374905132135e-05, "loss": 0.34437796473503113, "step": 163 }, { "epoch": 0.10635538261997406, "grad_norm": 0.21484375, "learning_rate": 1.9972982985797528e-05, "loss": 0.3635660409927368, "step": 164 }, { "epoch": 0.10700389105058365, "grad_norm": 0.20703125, "learning_rate": 1.9972205917759008e-05, "loss": 0.37994685769081116, "step": 165 }, { "epoch": 0.10765239948119326, "grad_norm": 0.2109375, "learning_rate": 1.997141784806307e-05, "loss": 0.3574579358100891, "step": 166 }, { "epoch": 0.10830090791180286, "grad_norm": 0.208984375, "learning_rate": 1.9970618777579147e-05, "loss": 0.3717995882034302, "step": 167 }, { "epoch": 0.10894941634241245, "grad_norm": 0.2001953125, "learning_rate": 1.9969808707188792e-05, "loss": 0.3511693477630615, "step": 168 }, { "epoch": 0.10959792477302205, "grad_norm": 0.2099609375, "learning_rate": 1.9968987637785698e-05, "loss": 0.37727826833724976, "step": 169 }, { "epoch": 0.11024643320363164, "grad_norm": 0.19921875, "learning_rate": 1.9968155570275703e-05, "loss": 0.3403925895690918, "step": 170 }, { "epoch": 0.11089494163424124, "grad_norm": 0.2041015625, "learning_rate": 1.9967312505576765e-05, "loss": 0.3511483073234558, "step": 171 }, { "epoch": 0.11154345006485085, "grad_norm": 0.2060546875, "learning_rate": 1.9966458444618983e-05, "loss": 0.33980971574783325, "step": 172 }, { "epoch": 0.11219195849546044, "grad_norm": 0.2060546875, "learning_rate": 1.996559338834458e-05, "loss": 0.33395615220069885, "step": 173 }, { "epoch": 0.11284046692607004, "grad_norm": 0.20703125, "learning_rate": 1.9964717337707918e-05, "loss": 0.36414003372192383, "step": 174 }, { "epoch": 0.11348897535667964, "grad_norm": 0.2099609375, "learning_rate": 1.9963830293675483e-05, "loss": 0.3635435700416565, "step": 175 }, { "epoch": 0.11413748378728923, "grad_norm": 0.2138671875, "learning_rate": 1.996293225722589e-05, "loss": 0.37186816334724426, "step": 176 }, { "epoch": 0.11478599221789883, "grad_norm": 0.2138671875, "learning_rate": 1.9962023229349884e-05, "loss": 0.3823866844177246, "step": 177 }, { "epoch": 0.11543450064850844, "grad_norm": 0.2158203125, "learning_rate": 1.9961103211050333e-05, "loss": 0.36216211318969727, "step": 178 }, { "epoch": 0.11608300907911803, "grad_norm": 0.2119140625, "learning_rate": 1.9960172203342225e-05, "loss": 0.3792182207107544, "step": 179 }, { "epoch": 0.11673151750972763, "grad_norm": 0.1962890625, "learning_rate": 1.995923020725268e-05, "loss": 0.33125486969947815, "step": 180 }, { "epoch": 0.11738002594033722, "grad_norm": 0.20703125, "learning_rate": 1.995827722382095e-05, "loss": 0.35435962677001953, "step": 181 }, { "epoch": 0.11802853437094682, "grad_norm": 0.20703125, "learning_rate": 1.995731325409838e-05, "loss": 0.36526772379875183, "step": 182 }, { "epoch": 0.11867704280155641, "grad_norm": 0.2158203125, "learning_rate": 1.995633829914846e-05, "loss": 0.3561992049217224, "step": 183 }, { "epoch": 0.11932555123216602, "grad_norm": 0.224609375, "learning_rate": 1.9955352360046795e-05, "loss": 0.35107189416885376, "step": 184 }, { "epoch": 0.11997405966277562, "grad_norm": 0.2109375, "learning_rate": 1.9954355437881095e-05, "loss": 0.366899698972702, "step": 185 }, { "epoch": 0.12062256809338522, "grad_norm": 0.21484375, "learning_rate": 1.9953347533751208e-05, "loss": 0.35685789585113525, "step": 186 }, { "epoch": 0.12127107652399481, "grad_norm": 0.205078125, "learning_rate": 1.9952328648769076e-05, "loss": 0.3430757522583008, "step": 187 }, { "epoch": 0.1219195849546044, "grad_norm": 0.216796875, "learning_rate": 1.9951298784058773e-05, "loss": 0.3783787488937378, "step": 188 }, { "epoch": 0.122568093385214, "grad_norm": 0.208984375, "learning_rate": 1.9950257940756476e-05, "loss": 0.3612635135650635, "step": 189 }, { "epoch": 0.12321660181582361, "grad_norm": 0.2021484375, "learning_rate": 1.9949206120010472e-05, "loss": 0.3659682273864746, "step": 190 }, { "epoch": 0.12386511024643321, "grad_norm": 0.2001953125, "learning_rate": 1.994814332298117e-05, "loss": 0.34430402517318726, "step": 191 }, { "epoch": 0.1245136186770428, "grad_norm": 0.2197265625, "learning_rate": 1.9947069550841083e-05, "loss": 0.36645421385765076, "step": 192 }, { "epoch": 0.1251621271076524, "grad_norm": 0.2119140625, "learning_rate": 1.9945984804774824e-05, "loss": 0.3527486324310303, "step": 193 }, { "epoch": 0.125810635538262, "grad_norm": 0.220703125, "learning_rate": 1.9944889085979126e-05, "loss": 0.37905579805374146, "step": 194 }, { "epoch": 0.1264591439688716, "grad_norm": 0.2109375, "learning_rate": 1.9943782395662816e-05, "loss": 0.34702199697494507, "step": 195 }, { "epoch": 0.12710765239948119, "grad_norm": 0.208984375, "learning_rate": 1.9942664735046833e-05, "loss": 0.34745287895202637, "step": 196 }, { "epoch": 0.12775616083009078, "grad_norm": 0.2041015625, "learning_rate": 1.9941536105364214e-05, "loss": 0.35376638174057007, "step": 197 }, { "epoch": 0.12840466926070038, "grad_norm": 0.2197265625, "learning_rate": 1.9940396507860103e-05, "loss": 0.34441259503364563, "step": 198 }, { "epoch": 0.12905317769131, "grad_norm": 0.205078125, "learning_rate": 1.9939245943791737e-05, "loss": 0.34473466873168945, "step": 199 }, { "epoch": 0.1297016861219196, "grad_norm": 0.216796875, "learning_rate": 1.993808441442846e-05, "loss": 0.3371885120868683, "step": 200 }, { "epoch": 0.1303501945525292, "grad_norm": 0.197265625, "learning_rate": 1.9936911921051703e-05, "loss": 0.34203848242759705, "step": 201 }, { "epoch": 0.1309987029831388, "grad_norm": 0.2138671875, "learning_rate": 1.9935728464955002e-05, "loss": 0.3390808403491974, "step": 202 }, { "epoch": 0.13164721141374838, "grad_norm": 0.203125, "learning_rate": 1.9934534047443982e-05, "loss": 0.360973060131073, "step": 203 }, { "epoch": 0.13229571984435798, "grad_norm": 0.21875, "learning_rate": 1.993332866983636e-05, "loss": 0.3373987674713135, "step": 204 }, { "epoch": 0.13294422827496757, "grad_norm": 0.20703125, "learning_rate": 1.993211233346195e-05, "loss": 0.3268091678619385, "step": 205 }, { "epoch": 0.13359273670557717, "grad_norm": 0.2333984375, "learning_rate": 1.9930885039662658e-05, "loss": 0.34803783893585205, "step": 206 }, { "epoch": 0.13424124513618677, "grad_norm": 0.251953125, "learning_rate": 1.992964678979247e-05, "loss": 0.3735063970088959, "step": 207 }, { "epoch": 0.13488975356679636, "grad_norm": 0.205078125, "learning_rate": 1.9928397585217458e-05, "loss": 0.3565911054611206, "step": 208 }, { "epoch": 0.13553826199740596, "grad_norm": 0.2158203125, "learning_rate": 1.9927137427315788e-05, "loss": 0.3617969751358032, "step": 209 }, { "epoch": 0.13618677042801555, "grad_norm": 0.2109375, "learning_rate": 1.992586631747771e-05, "loss": 0.3360612392425537, "step": 210 }, { "epoch": 0.13683527885862518, "grad_norm": 0.2001953125, "learning_rate": 1.992458425710555e-05, "loss": 0.34708642959594727, "step": 211 }, { "epoch": 0.13748378728923477, "grad_norm": 0.205078125, "learning_rate": 1.992329124761372e-05, "loss": 0.3350972533226013, "step": 212 }, { "epoch": 0.13813229571984437, "grad_norm": 0.2236328125, "learning_rate": 1.9921987290428707e-05, "loss": 0.36041635274887085, "step": 213 }, { "epoch": 0.13878080415045396, "grad_norm": 0.2177734375, "learning_rate": 1.992067238698908e-05, "loss": 0.35008642077445984, "step": 214 }, { "epoch": 0.13942931258106356, "grad_norm": 0.2255859375, "learning_rate": 1.991934653874548e-05, "loss": 0.34039825201034546, "step": 215 }, { "epoch": 0.14007782101167315, "grad_norm": 0.2158203125, "learning_rate": 1.991800974716063e-05, "loss": 0.35526514053344727, "step": 216 }, { "epoch": 0.14072632944228275, "grad_norm": 0.2412109375, "learning_rate": 1.991666201370932e-05, "loss": 0.3464857339859009, "step": 217 }, { "epoch": 0.14137483787289234, "grad_norm": 0.2080078125, "learning_rate": 1.991530333987841e-05, "loss": 0.3405786156654358, "step": 218 }, { "epoch": 0.14202334630350194, "grad_norm": 0.2021484375, "learning_rate": 1.9913933727166838e-05, "loss": 0.3523654043674469, "step": 219 }, { "epoch": 0.14267185473411154, "grad_norm": 0.21875, "learning_rate": 1.9912553177085598e-05, "loss": 0.3361499607563019, "step": 220 }, { "epoch": 0.14332036316472113, "grad_norm": 0.21875, "learning_rate": 1.991116169115776e-05, "loss": 0.3440963625907898, "step": 221 }, { "epoch": 0.14396887159533073, "grad_norm": 0.2216796875, "learning_rate": 1.9909759270918455e-05, "loss": 0.32642805576324463, "step": 222 }, { "epoch": 0.14461738002594035, "grad_norm": 0.2197265625, "learning_rate": 1.990834591791488e-05, "loss": 0.3491353988647461, "step": 223 }, { "epoch": 0.14526588845654995, "grad_norm": 0.216796875, "learning_rate": 1.990692163370629e-05, "loss": 0.35548603534698486, "step": 224 }, { "epoch": 0.14591439688715954, "grad_norm": 0.22265625, "learning_rate": 1.9905486419864003e-05, "loss": 0.3361803889274597, "step": 225 }, { "epoch": 0.14656290531776914, "grad_norm": 0.208984375, "learning_rate": 1.990404027797139e-05, "loss": 0.33447688817977905, "step": 226 }, { "epoch": 0.14721141374837873, "grad_norm": 0.2275390625, "learning_rate": 1.990258320962388e-05, "loss": 0.35223257541656494, "step": 227 }, { "epoch": 0.14785992217898833, "grad_norm": 0.2021484375, "learning_rate": 1.9901115216428965e-05, "loss": 0.3410983979701996, "step": 228 }, { "epoch": 0.14850843060959792, "grad_norm": 0.2021484375, "learning_rate": 1.9899636300006175e-05, "loss": 0.3233211934566498, "step": 229 }, { "epoch": 0.14915693904020752, "grad_norm": 0.2275390625, "learning_rate": 1.9898146461987102e-05, "loss": 0.3586883246898651, "step": 230 }, { "epoch": 0.14980544747081712, "grad_norm": 0.2099609375, "learning_rate": 1.989664570401538e-05, "loss": 0.3356105387210846, "step": 231 }, { "epoch": 0.1504539559014267, "grad_norm": 0.2099609375, "learning_rate": 1.9895134027746694e-05, "loss": 0.31310582160949707, "step": 232 }, { "epoch": 0.1511024643320363, "grad_norm": 0.2294921875, "learning_rate": 1.989361143484877e-05, "loss": 0.32391422986984253, "step": 233 }, { "epoch": 0.1517509727626459, "grad_norm": 0.21875, "learning_rate": 1.9892077927001395e-05, "loss": 0.3314436078071594, "step": 234 }, { "epoch": 0.15239948119325553, "grad_norm": 0.2041015625, "learning_rate": 1.9890533505896366e-05, "loss": 0.32836657762527466, "step": 235 }, { "epoch": 0.15304798962386512, "grad_norm": 0.2099609375, "learning_rate": 1.9888978173237552e-05, "loss": 0.34349796175956726, "step": 236 }, { "epoch": 0.15369649805447472, "grad_norm": 0.201171875, "learning_rate": 1.988741193074084e-05, "loss": 0.3389296531677246, "step": 237 }, { "epoch": 0.1543450064850843, "grad_norm": 0.21484375, "learning_rate": 1.9885834780134158e-05, "loss": 0.3639851212501526, "step": 238 }, { "epoch": 0.1549935149156939, "grad_norm": 0.2109375, "learning_rate": 1.988424672315747e-05, "loss": 0.3426707983016968, "step": 239 }, { "epoch": 0.1556420233463035, "grad_norm": 0.2158203125, "learning_rate": 1.9882647761562773e-05, "loss": 0.31762993335723877, "step": 240 }, { "epoch": 0.1562905317769131, "grad_norm": 0.205078125, "learning_rate": 1.988103789711409e-05, "loss": 0.3144069314002991, "step": 241 }, { "epoch": 0.1569390402075227, "grad_norm": 0.21875, "learning_rate": 1.987941713158748e-05, "loss": 0.3454737365245819, "step": 242 }, { "epoch": 0.1575875486381323, "grad_norm": 0.20703125, "learning_rate": 1.987778546677102e-05, "loss": 0.31825876235961914, "step": 243 }, { "epoch": 0.1582360570687419, "grad_norm": 0.2099609375, "learning_rate": 1.9876142904464816e-05, "loss": 0.32279831171035767, "step": 244 }, { "epoch": 0.15888456549935148, "grad_norm": 0.2275390625, "learning_rate": 1.987448944648099e-05, "loss": 0.33669722080230713, "step": 245 }, { "epoch": 0.15953307392996108, "grad_norm": 0.2177734375, "learning_rate": 1.98728250946437e-05, "loss": 0.32144689559936523, "step": 246 }, { "epoch": 0.1601815823605707, "grad_norm": 0.224609375, "learning_rate": 1.9871149850789102e-05, "loss": 0.3412940204143524, "step": 247 }, { "epoch": 0.1608300907911803, "grad_norm": 0.205078125, "learning_rate": 1.9869463716765388e-05, "loss": 0.332040011882782, "step": 248 }, { "epoch": 0.1614785992217899, "grad_norm": 0.216796875, "learning_rate": 1.9867766694432745e-05, "loss": 0.33092084527015686, "step": 249 }, { "epoch": 0.1621271076523995, "grad_norm": 0.2265625, "learning_rate": 1.9866058785663392e-05, "loss": 0.334977388381958, "step": 250 }, { "epoch": 0.16277561608300908, "grad_norm": 0.2275390625, "learning_rate": 1.9864339992341546e-05, "loss": 0.3184294104576111, "step": 251 }, { "epoch": 0.16342412451361868, "grad_norm": 0.2197265625, "learning_rate": 1.9862610316363434e-05, "loss": 0.3104742765426636, "step": 252 }, { "epoch": 0.16407263294422827, "grad_norm": 0.224609375, "learning_rate": 1.986086975963729e-05, "loss": 0.33989375829696655, "step": 253 }, { "epoch": 0.16472114137483787, "grad_norm": 0.220703125, "learning_rate": 1.985911832408335e-05, "loss": 0.3605601191520691, "step": 254 }, { "epoch": 0.16536964980544747, "grad_norm": 0.2255859375, "learning_rate": 1.9857356011633856e-05, "loss": 0.31649842858314514, "step": 255 }, { "epoch": 0.16601815823605706, "grad_norm": 0.224609375, "learning_rate": 1.9855582824233047e-05, "loss": 0.31772151589393616, "step": 256 }, { "epoch": 0.16666666666666666, "grad_norm": 0.240234375, "learning_rate": 1.9853798763837165e-05, "loss": 0.3584485650062561, "step": 257 }, { "epoch": 0.16731517509727625, "grad_norm": 0.2236328125, "learning_rate": 1.9852003832414433e-05, "loss": 0.330280065536499, "step": 258 }, { "epoch": 0.16796368352788585, "grad_norm": 0.228515625, "learning_rate": 1.985019803194508e-05, "loss": 0.3294772207736969, "step": 259 }, { "epoch": 0.16861219195849547, "grad_norm": 0.248046875, "learning_rate": 1.9848381364421332e-05, "loss": 0.34626948833465576, "step": 260 }, { "epoch": 0.16926070038910507, "grad_norm": 0.2314453125, "learning_rate": 1.9846553831847387e-05, "loss": 0.3282998204231262, "step": 261 }, { "epoch": 0.16990920881971466, "grad_norm": 0.212890625, "learning_rate": 1.9844715436239438e-05, "loss": 0.34251439571380615, "step": 262 }, { "epoch": 0.17055771725032426, "grad_norm": 0.212890625, "learning_rate": 1.9842866179625662e-05, "loss": 0.3270256519317627, "step": 263 }, { "epoch": 0.17120622568093385, "grad_norm": 0.216796875, "learning_rate": 1.9841006064046216e-05, "loss": 0.33206215500831604, "step": 264 }, { "epoch": 0.17185473411154345, "grad_norm": 0.21875, "learning_rate": 1.9839135091553247e-05, "loss": 0.33136963844299316, "step": 265 }, { "epoch": 0.17250324254215305, "grad_norm": 0.26953125, "learning_rate": 1.9837253264210863e-05, "loss": 0.32983633875846863, "step": 266 }, { "epoch": 0.17315175097276264, "grad_norm": 0.216796875, "learning_rate": 1.983536058409516e-05, "loss": 0.305320680141449, "step": 267 }, { "epoch": 0.17380025940337224, "grad_norm": 0.2265625, "learning_rate": 1.9833457053294207e-05, "loss": 0.3301853835582733, "step": 268 }, { "epoch": 0.17444876783398183, "grad_norm": 0.2470703125, "learning_rate": 1.9831542673908032e-05, "loss": 0.3378753662109375, "step": 269 }, { "epoch": 0.17509727626459143, "grad_norm": 0.2109375, "learning_rate": 1.982961744804865e-05, "loss": 0.32982805371284485, "step": 270 }, { "epoch": 0.17574578469520102, "grad_norm": 0.21875, "learning_rate": 1.9827681377840023e-05, "loss": 0.3273736536502838, "step": 271 }, { "epoch": 0.17639429312581065, "grad_norm": 0.2216796875, "learning_rate": 1.982573446541809e-05, "loss": 0.3558015823364258, "step": 272 }, { "epoch": 0.17704280155642024, "grad_norm": 0.2119140625, "learning_rate": 1.9823776712930748e-05, "loss": 0.31839442253112793, "step": 273 }, { "epoch": 0.17769130998702984, "grad_norm": 0.2099609375, "learning_rate": 1.982180812253785e-05, "loss": 0.312683641910553, "step": 274 }, { "epoch": 0.17833981841763943, "grad_norm": 0.2265625, "learning_rate": 1.9819828696411207e-05, "loss": 0.351976215839386, "step": 275 }, { "epoch": 0.17898832684824903, "grad_norm": 0.23828125, "learning_rate": 1.9817838436734588e-05, "loss": 0.33706462383270264, "step": 276 }, { "epoch": 0.17963683527885863, "grad_norm": 0.2314453125, "learning_rate": 1.981583734570371e-05, "loss": 0.32768383622169495, "step": 277 }, { "epoch": 0.18028534370946822, "grad_norm": 0.21484375, "learning_rate": 1.9813825425526244e-05, "loss": 0.32490551471710205, "step": 278 }, { "epoch": 0.18093385214007782, "grad_norm": 0.23046875, "learning_rate": 1.9811802678421797e-05, "loss": 0.3098565638065338, "step": 279 }, { "epoch": 0.1815823605706874, "grad_norm": 0.2109375, "learning_rate": 1.980976910662194e-05, "loss": 0.3191128373146057, "step": 280 }, { "epoch": 0.182230869001297, "grad_norm": 0.2099609375, "learning_rate": 1.9807724712370164e-05, "loss": 0.3159150779247284, "step": 281 }, { "epoch": 0.1828793774319066, "grad_norm": 0.2275390625, "learning_rate": 1.980566949792192e-05, "loss": 0.32881003618240356, "step": 282 }, { "epoch": 0.1835278858625162, "grad_norm": 0.216796875, "learning_rate": 1.9803603465544574e-05, "loss": 0.3375019431114197, "step": 283 }, { "epoch": 0.18417639429312582, "grad_norm": 0.2275390625, "learning_rate": 1.9801526617517452e-05, "loss": 0.3486555516719818, "step": 284 }, { "epoch": 0.18482490272373542, "grad_norm": 0.2578125, "learning_rate": 1.979943895613179e-05, "loss": 0.31987130641937256, "step": 285 }, { "epoch": 0.185473411154345, "grad_norm": 0.2099609375, "learning_rate": 1.9797340483690765e-05, "loss": 0.3171629309654236, "step": 286 }, { "epoch": 0.1861219195849546, "grad_norm": 0.2275390625, "learning_rate": 1.9795231202509485e-05, "loss": 0.3165263831615448, "step": 287 }, { "epoch": 0.1867704280155642, "grad_norm": 0.2275390625, "learning_rate": 1.979311111491497e-05, "loss": 0.3224771022796631, "step": 288 }, { "epoch": 0.1874189364461738, "grad_norm": 0.228515625, "learning_rate": 1.979098022324617e-05, "loss": 0.34661364555358887, "step": 289 }, { "epoch": 0.1880674448767834, "grad_norm": 0.232421875, "learning_rate": 1.978883852985396e-05, "loss": 0.29364949464797974, "step": 290 }, { "epoch": 0.188715953307393, "grad_norm": 0.2392578125, "learning_rate": 1.9786686037101114e-05, "loss": 0.3293208181858063, "step": 291 }, { "epoch": 0.1893644617380026, "grad_norm": 0.216796875, "learning_rate": 1.9784522747362337e-05, "loss": 0.3318045139312744, "step": 292 }, { "epoch": 0.19001297016861218, "grad_norm": 0.244140625, "learning_rate": 1.9782348663024238e-05, "loss": 0.3355390727519989, "step": 293 }, { "epoch": 0.19066147859922178, "grad_norm": 0.2373046875, "learning_rate": 1.9780163786485338e-05, "loss": 0.3346158266067505, "step": 294 }, { "epoch": 0.19130998702983137, "grad_norm": 0.236328125, "learning_rate": 1.977796812015606e-05, "loss": 0.3441377282142639, "step": 295 }, { "epoch": 0.191958495460441, "grad_norm": 0.2236328125, "learning_rate": 1.977576166645874e-05, "loss": 0.33501026034355164, "step": 296 }, { "epoch": 0.1926070038910506, "grad_norm": 0.220703125, "learning_rate": 1.9773544427827604e-05, "loss": 0.31328707933425903, "step": 297 }, { "epoch": 0.1932555123216602, "grad_norm": 0.2265625, "learning_rate": 1.9771316406708777e-05, "loss": 0.3063465356826782, "step": 298 }, { "epoch": 0.19390402075226978, "grad_norm": 0.2236328125, "learning_rate": 1.9769077605560287e-05, "loss": 0.31411999464035034, "step": 299 }, { "epoch": 0.19455252918287938, "grad_norm": 0.28125, "learning_rate": 1.9766828026852054e-05, "loss": 0.3090721666812897, "step": 300 }, { "epoch": 0.19520103761348898, "grad_norm": 0.255859375, "learning_rate": 1.9764567673065882e-05, "loss": 0.3278522789478302, "step": 301 }, { "epoch": 0.19584954604409857, "grad_norm": 0.2236328125, "learning_rate": 1.976229654669547e-05, "loss": 0.3367612659931183, "step": 302 }, { "epoch": 0.19649805447470817, "grad_norm": 0.2333984375, "learning_rate": 1.9760014650246386e-05, "loss": 0.3306860029697418, "step": 303 }, { "epoch": 0.19714656290531776, "grad_norm": 0.220703125, "learning_rate": 1.9757721986236103e-05, "loss": 0.31661728024482727, "step": 304 }, { "epoch": 0.19779507133592736, "grad_norm": 0.20703125, "learning_rate": 1.9755418557193963e-05, "loss": 0.3153969645500183, "step": 305 }, { "epoch": 0.19844357976653695, "grad_norm": 0.21875, "learning_rate": 1.9753104365661172e-05, "loss": 0.31304991245269775, "step": 306 }, { "epoch": 0.19909208819714655, "grad_norm": 0.2421875, "learning_rate": 1.9750779414190827e-05, "loss": 0.3166106343269348, "step": 307 }, { "epoch": 0.19974059662775617, "grad_norm": 0.2119140625, "learning_rate": 1.974844370534789e-05, "loss": 0.29556772112846375, "step": 308 }, { "epoch": 0.20038910505836577, "grad_norm": 0.2177734375, "learning_rate": 1.9746097241709185e-05, "loss": 0.31287243962287903, "step": 309 }, { "epoch": 0.20103761348897536, "grad_norm": 0.2119140625, "learning_rate": 1.974374002586341e-05, "loss": 0.3038344383239746, "step": 310 }, { "epoch": 0.20168612191958496, "grad_norm": 0.212890625, "learning_rate": 1.9741372060411122e-05, "loss": 0.3108871281147003, "step": 311 }, { "epoch": 0.20233463035019456, "grad_norm": 0.22265625, "learning_rate": 1.9738993347964732e-05, "loss": 0.3076733350753784, "step": 312 }, { "epoch": 0.20298313878080415, "grad_norm": 0.2265625, "learning_rate": 1.9736603891148515e-05, "loss": 0.3141556680202484, "step": 313 }, { "epoch": 0.20363164721141375, "grad_norm": 0.2470703125, "learning_rate": 1.9734203692598597e-05, "loss": 0.33132052421569824, "step": 314 }, { "epoch": 0.20428015564202334, "grad_norm": 0.2177734375, "learning_rate": 1.973179275496295e-05, "loss": 0.3149304986000061, "step": 315 }, { "epoch": 0.20492866407263294, "grad_norm": 0.2177734375, "learning_rate": 1.9729371080901403e-05, "loss": 0.3376978039741516, "step": 316 }, { "epoch": 0.20557717250324253, "grad_norm": 0.2392578125, "learning_rate": 1.972693867308562e-05, "loss": 0.32132595777511597, "step": 317 }, { "epoch": 0.20622568093385213, "grad_norm": 0.2373046875, "learning_rate": 1.9724495534199116e-05, "loss": 0.32048070430755615, "step": 318 }, { "epoch": 0.20687418936446172, "grad_norm": 0.2197265625, "learning_rate": 1.9722041666937236e-05, "loss": 0.3308355212211609, "step": 319 }, { "epoch": 0.20752269779507135, "grad_norm": 0.220703125, "learning_rate": 1.9719577074007166e-05, "loss": 0.31627902388572693, "step": 320 }, { "epoch": 0.20817120622568094, "grad_norm": 0.2177734375, "learning_rate": 1.9717101758127923e-05, "loss": 0.29440391063690186, "step": 321 }, { "epoch": 0.20881971465629054, "grad_norm": 0.2236328125, "learning_rate": 1.971461572203036e-05, "loss": 0.30840179324150085, "step": 322 }, { "epoch": 0.20946822308690013, "grad_norm": 0.220703125, "learning_rate": 1.9712118968457146e-05, "loss": 0.31594425439834595, "step": 323 }, { "epoch": 0.21011673151750973, "grad_norm": 0.244140625, "learning_rate": 1.9709611500162783e-05, "loss": 0.3456932306289673, "step": 324 }, { "epoch": 0.21076523994811933, "grad_norm": 0.232421875, "learning_rate": 1.9707093319913587e-05, "loss": 0.3097022473812103, "step": 325 }, { "epoch": 0.21141374837872892, "grad_norm": 0.2197265625, "learning_rate": 1.97045644304877e-05, "loss": 0.31464600563049316, "step": 326 }, { "epoch": 0.21206225680933852, "grad_norm": 0.2421875, "learning_rate": 1.970202483467507e-05, "loss": 0.2989755868911743, "step": 327 }, { "epoch": 0.2127107652399481, "grad_norm": 0.21875, "learning_rate": 1.9699474535277462e-05, "loss": 0.29494136571884155, "step": 328 }, { "epoch": 0.2133592736705577, "grad_norm": 0.220703125, "learning_rate": 1.969691353510845e-05, "loss": 0.30434101819992065, "step": 329 }, { "epoch": 0.2140077821011673, "grad_norm": 0.23046875, "learning_rate": 1.9694341836993406e-05, "loss": 0.3083377480506897, "step": 330 }, { "epoch": 0.2146562905317769, "grad_norm": 0.25, "learning_rate": 1.9691759443769514e-05, "loss": 0.32230234146118164, "step": 331 }, { "epoch": 0.21530479896238652, "grad_norm": 0.251953125, "learning_rate": 1.9689166358285753e-05, "loss": 0.3127240538597107, "step": 332 }, { "epoch": 0.21595330739299612, "grad_norm": 0.240234375, "learning_rate": 1.96865625834029e-05, "loss": 0.3335818946361542, "step": 333 }, { "epoch": 0.21660181582360571, "grad_norm": 0.2314453125, "learning_rate": 1.9683948121993518e-05, "loss": 0.33556732535362244, "step": 334 }, { "epoch": 0.2172503242542153, "grad_norm": 0.28125, "learning_rate": 1.9681322976941964e-05, "loss": 0.30278268456459045, "step": 335 }, { "epoch": 0.2178988326848249, "grad_norm": 0.2099609375, "learning_rate": 1.9678687151144393e-05, "loss": 0.29217416048049927, "step": 336 }, { "epoch": 0.2185473411154345, "grad_norm": 0.251953125, "learning_rate": 1.9676040647508718e-05, "loss": 0.3232361972332001, "step": 337 }, { "epoch": 0.2191958495460441, "grad_norm": 0.2412109375, "learning_rate": 1.9673383468954655e-05, "loss": 0.31238648295402527, "step": 338 }, { "epoch": 0.2198443579766537, "grad_norm": 0.2392578125, "learning_rate": 1.967071561841369e-05, "loss": 0.31114840507507324, "step": 339 }, { "epoch": 0.2204928664072633, "grad_norm": 0.2099609375, "learning_rate": 1.9668037098829077e-05, "loss": 0.29439088702201843, "step": 340 }, { "epoch": 0.22114137483787288, "grad_norm": 0.26171875, "learning_rate": 1.9665347913155844e-05, "loss": 0.29134148359298706, "step": 341 }, { "epoch": 0.22178988326848248, "grad_norm": 0.240234375, "learning_rate": 1.966264806436079e-05, "loss": 0.3068786859512329, "step": 342 }, { "epoch": 0.22243839169909208, "grad_norm": 0.2265625, "learning_rate": 1.9659937555422478e-05, "loss": 0.3025660216808319, "step": 343 }, { "epoch": 0.2230869001297017, "grad_norm": 0.212890625, "learning_rate": 1.9657216389331223e-05, "loss": 0.29440781474113464, "step": 344 }, { "epoch": 0.2237354085603113, "grad_norm": 0.244140625, "learning_rate": 1.96544845690891e-05, "loss": 0.30195996165275574, "step": 345 }, { "epoch": 0.2243839169909209, "grad_norm": 0.2236328125, "learning_rate": 1.9651742097709948e-05, "loss": 0.3108524680137634, "step": 346 }, { "epoch": 0.22503242542153049, "grad_norm": 0.22265625, "learning_rate": 1.9648988978219345e-05, "loss": 0.2844770550727844, "step": 347 }, { "epoch": 0.22568093385214008, "grad_norm": 0.22265625, "learning_rate": 1.9646225213654622e-05, "loss": 0.29939234256744385, "step": 348 }, { "epoch": 0.22632944228274968, "grad_norm": 0.2421875, "learning_rate": 1.9643450807064853e-05, "loss": 0.3031744956970215, "step": 349 }, { "epoch": 0.22697795071335927, "grad_norm": 0.21484375, "learning_rate": 1.964066576151085e-05, "loss": 0.300373911857605, "step": 350 }, { "epoch": 0.22762645914396887, "grad_norm": 0.232421875, "learning_rate": 1.9637870080065168e-05, "loss": 0.3034243583679199, "step": 351 }, { "epoch": 0.22827496757457846, "grad_norm": 0.2392578125, "learning_rate": 1.9635063765812093e-05, "loss": 0.32531341910362244, "step": 352 }, { "epoch": 0.22892347600518806, "grad_norm": 0.23046875, "learning_rate": 1.9632246821847633e-05, "loss": 0.291816771030426, "step": 353 }, { "epoch": 0.22957198443579765, "grad_norm": 0.2255859375, "learning_rate": 1.962941925127954e-05, "loss": 0.2934528887271881, "step": 354 }, { "epoch": 0.23022049286640725, "grad_norm": 0.2255859375, "learning_rate": 1.9626581057227278e-05, "loss": 0.2891886830329895, "step": 355 }, { "epoch": 0.23086900129701687, "grad_norm": 0.22265625, "learning_rate": 1.9623732242822032e-05, "loss": 0.2864113450050354, "step": 356 }, { "epoch": 0.23151750972762647, "grad_norm": 0.228515625, "learning_rate": 1.9620872811206707e-05, "loss": 0.2933658957481384, "step": 357 }, { "epoch": 0.23216601815823606, "grad_norm": 0.2177734375, "learning_rate": 1.961800276553592e-05, "loss": 0.28219059109687805, "step": 358 }, { "epoch": 0.23281452658884566, "grad_norm": 0.228515625, "learning_rate": 1.9615122108975994e-05, "loss": 0.31413906812667847, "step": 359 }, { "epoch": 0.23346303501945526, "grad_norm": 0.2294921875, "learning_rate": 1.9612230844704966e-05, "loss": 0.3028283715248108, "step": 360 }, { "epoch": 0.23411154345006485, "grad_norm": 0.2216796875, "learning_rate": 1.9609328975912566e-05, "loss": 0.29991239309310913, "step": 361 }, { "epoch": 0.23476005188067445, "grad_norm": 0.220703125, "learning_rate": 1.9606416505800235e-05, "loss": 0.30291974544525146, "step": 362 }, { "epoch": 0.23540856031128404, "grad_norm": 0.234375, "learning_rate": 1.9603493437581104e-05, "loss": 0.29566454887390137, "step": 363 }, { "epoch": 0.23605706874189364, "grad_norm": 0.2353515625, "learning_rate": 1.960055977447999e-05, "loss": 0.3031010627746582, "step": 364 }, { "epoch": 0.23670557717250323, "grad_norm": 0.220703125, "learning_rate": 1.9597615519733407e-05, "loss": 0.27916961908340454, "step": 365 }, { "epoch": 0.23735408560311283, "grad_norm": 0.255859375, "learning_rate": 1.959466067658955e-05, "loss": 0.3081715703010559, "step": 366 }, { "epoch": 0.23800259403372243, "grad_norm": 0.2177734375, "learning_rate": 1.95916952483083e-05, "loss": 0.284905344247818, "step": 367 }, { "epoch": 0.23865110246433205, "grad_norm": 0.224609375, "learning_rate": 1.9588719238161205e-05, "loss": 0.29053884744644165, "step": 368 }, { "epoch": 0.23929961089494164, "grad_norm": 0.25, "learning_rate": 1.9585732649431503e-05, "loss": 0.303033709526062, "step": 369 }, { "epoch": 0.23994811932555124, "grad_norm": 0.2294921875, "learning_rate": 1.958273548541409e-05, "loss": 0.3077862858772278, "step": 370 }, { "epoch": 0.24059662775616084, "grad_norm": 0.236328125, "learning_rate": 1.957972774941554e-05, "loss": 0.2822905480861664, "step": 371 }, { "epoch": 0.24124513618677043, "grad_norm": 0.2392578125, "learning_rate": 1.9576709444754076e-05, "loss": 0.30563682317733765, "step": 372 }, { "epoch": 0.24189364461738003, "grad_norm": 0.2578125, "learning_rate": 1.957368057475959e-05, "loss": 0.30904221534729004, "step": 373 }, { "epoch": 0.24254215304798962, "grad_norm": 0.248046875, "learning_rate": 1.957064114277363e-05, "loss": 0.3022066056728363, "step": 374 }, { "epoch": 0.24319066147859922, "grad_norm": 0.2275390625, "learning_rate": 1.95675911521494e-05, "loss": 0.29943978786468506, "step": 375 }, { "epoch": 0.2438391699092088, "grad_norm": 0.2255859375, "learning_rate": 1.9564530606251737e-05, "loss": 0.31113627552986145, "step": 376 }, { "epoch": 0.2444876783398184, "grad_norm": 0.2451171875, "learning_rate": 1.9561459508457138e-05, "loss": 0.3054104447364807, "step": 377 }, { "epoch": 0.245136186770428, "grad_norm": 0.2412109375, "learning_rate": 1.9558377862153742e-05, "loss": 0.29187512397766113, "step": 378 }, { "epoch": 0.2457846952010376, "grad_norm": 0.22265625, "learning_rate": 1.955528567074131e-05, "loss": 0.2890707850456238, "step": 379 }, { "epoch": 0.24643320363164722, "grad_norm": 0.2353515625, "learning_rate": 1.9552182937631256e-05, "loss": 0.2926119565963745, "step": 380 }, { "epoch": 0.24708171206225682, "grad_norm": 0.23046875, "learning_rate": 1.9549069666246606e-05, "loss": 0.29435408115386963, "step": 381 }, { "epoch": 0.24773022049286642, "grad_norm": 0.2392578125, "learning_rate": 1.954594586002203e-05, "loss": 0.30043599009513855, "step": 382 }, { "epoch": 0.248378728923476, "grad_norm": 0.240234375, "learning_rate": 1.9542811522403808e-05, "loss": 0.3046703338623047, "step": 383 }, { "epoch": 0.2490272373540856, "grad_norm": 0.25390625, "learning_rate": 1.9539666656849835e-05, "loss": 0.3197944760322571, "step": 384 }, { "epoch": 0.2496757457846952, "grad_norm": 0.2314453125, "learning_rate": 1.9536511266829637e-05, "loss": 0.29312247037887573, "step": 385 }, { "epoch": 0.2503242542153048, "grad_norm": 0.2314453125, "learning_rate": 1.953334535582434e-05, "loss": 0.3138100504875183, "step": 386 }, { "epoch": 0.2509727626459144, "grad_norm": 0.2392578125, "learning_rate": 1.953016892732667e-05, "loss": 0.27828964591026306, "step": 387 }, { "epoch": 0.251621271076524, "grad_norm": 0.24609375, "learning_rate": 1.9526981984840975e-05, "loss": 0.2880305349826813, "step": 388 }, { "epoch": 0.2522697795071336, "grad_norm": 0.2236328125, "learning_rate": 1.9523784531883186e-05, "loss": 0.2988007366657257, "step": 389 }, { "epoch": 0.2529182879377432, "grad_norm": 0.228515625, "learning_rate": 1.952057657198084e-05, "loss": 0.30961209535598755, "step": 390 }, { "epoch": 0.2535667963683528, "grad_norm": 0.2275390625, "learning_rate": 1.9517358108673056e-05, "loss": 0.2905673682689667, "step": 391 }, { "epoch": 0.25421530479896237, "grad_norm": 0.25, "learning_rate": 1.9514129145510553e-05, "loss": 0.2925402820110321, "step": 392 }, { "epoch": 0.25486381322957197, "grad_norm": 0.24609375, "learning_rate": 1.951088968605562e-05, "loss": 0.2875504195690155, "step": 393 }, { "epoch": 0.25551232166018156, "grad_norm": 0.248046875, "learning_rate": 1.9507639733882135e-05, "loss": 0.30179286003112793, "step": 394 }, { "epoch": 0.25616083009079116, "grad_norm": 0.2353515625, "learning_rate": 1.950437929257555e-05, "loss": 0.2847699522972107, "step": 395 }, { "epoch": 0.25680933852140075, "grad_norm": 0.2275390625, "learning_rate": 1.950110836573289e-05, "loss": 0.2986961901187897, "step": 396 }, { "epoch": 0.25745784695201035, "grad_norm": 0.234375, "learning_rate": 1.9497826956962746e-05, "loss": 0.2713472247123718, "step": 397 }, { "epoch": 0.25810635538262, "grad_norm": 0.236328125, "learning_rate": 1.9494535069885267e-05, "loss": 0.2813692092895508, "step": 398 }, { "epoch": 0.2587548638132296, "grad_norm": 0.24609375, "learning_rate": 1.9491232708132176e-05, "loss": 0.31626665592193604, "step": 399 }, { "epoch": 0.2594033722438392, "grad_norm": 0.234375, "learning_rate": 1.948791987534674e-05, "loss": 0.29580527544021606, "step": 400 }, { "epoch": 0.2600518806744488, "grad_norm": 0.23046875, "learning_rate": 1.9484596575183786e-05, "loss": 0.28170454502105713, "step": 401 }, { "epoch": 0.2607003891050584, "grad_norm": 0.2099609375, "learning_rate": 1.9481262811309684e-05, "loss": 0.27898213267326355, "step": 402 }, { "epoch": 0.261348897535668, "grad_norm": 0.248046875, "learning_rate": 1.9477918587402348e-05, "loss": 0.310768723487854, "step": 403 }, { "epoch": 0.2619974059662776, "grad_norm": 0.27734375, "learning_rate": 1.9474563907151233e-05, "loss": 0.3049668073654175, "step": 404 }, { "epoch": 0.26264591439688717, "grad_norm": 0.2392578125, "learning_rate": 1.9471198774257335e-05, "loss": 0.29258808493614197, "step": 405 }, { "epoch": 0.26329442282749677, "grad_norm": 0.263671875, "learning_rate": 1.9467823192433166e-05, "loss": 0.29570332169532776, "step": 406 }, { "epoch": 0.26394293125810636, "grad_norm": 0.2578125, "learning_rate": 1.9464437165402787e-05, "loss": 0.3204503059387207, "step": 407 }, { "epoch": 0.26459143968871596, "grad_norm": 0.228515625, "learning_rate": 1.9461040696901766e-05, "loss": 0.29513004422187805, "step": 408 }, { "epoch": 0.26523994811932555, "grad_norm": 0.24609375, "learning_rate": 1.9457633790677194e-05, "loss": 0.29267966747283936, "step": 409 }, { "epoch": 0.26588845654993515, "grad_norm": 0.259765625, "learning_rate": 1.9454216450487684e-05, "loss": 0.30821526050567627, "step": 410 }, { "epoch": 0.26653696498054474, "grad_norm": 0.232421875, "learning_rate": 1.9450788680103354e-05, "loss": 0.28317421674728394, "step": 411 }, { "epoch": 0.26718547341115434, "grad_norm": 0.2392578125, "learning_rate": 1.944735048330583e-05, "loss": 0.29808902740478516, "step": 412 }, { "epoch": 0.26783398184176394, "grad_norm": 0.287109375, "learning_rate": 1.944390186388824e-05, "loss": 0.2961675524711609, "step": 413 }, { "epoch": 0.26848249027237353, "grad_norm": 0.232421875, "learning_rate": 1.9440442825655214e-05, "loss": 0.2632056772708893, "step": 414 }, { "epoch": 0.2691309987029831, "grad_norm": 0.27734375, "learning_rate": 1.943697337242287e-05, "loss": 0.2745027244091034, "step": 415 }, { "epoch": 0.2697795071335927, "grad_norm": 0.24609375, "learning_rate": 1.9433493508018822e-05, "loss": 0.29136374592781067, "step": 416 }, { "epoch": 0.2704280155642023, "grad_norm": 0.23046875, "learning_rate": 1.943000323628217e-05, "loss": 0.2998250722885132, "step": 417 }, { "epoch": 0.2710765239948119, "grad_norm": 0.228515625, "learning_rate": 1.942650256106349e-05, "loss": 0.2857832908630371, "step": 418 }, { "epoch": 0.2717250324254215, "grad_norm": 0.21484375, "learning_rate": 1.942299148622484e-05, "loss": 0.26691943407058716, "step": 419 }, { "epoch": 0.2723735408560311, "grad_norm": 0.220703125, "learning_rate": 1.9419470015639756e-05, "loss": 0.2944003939628601, "step": 420 }, { "epoch": 0.2730220492866407, "grad_norm": 0.21484375, "learning_rate": 1.941593815319323e-05, "loss": 0.27150046825408936, "step": 421 }, { "epoch": 0.27367055771725035, "grad_norm": 0.228515625, "learning_rate": 1.9412395902781732e-05, "loss": 0.27966761589050293, "step": 422 }, { "epoch": 0.27431906614785995, "grad_norm": 0.2216796875, "learning_rate": 1.9408843268313177e-05, "loss": 0.2818008065223694, "step": 423 }, { "epoch": 0.27496757457846954, "grad_norm": 0.2158203125, "learning_rate": 1.9405280253706955e-05, "loss": 0.2839128375053406, "step": 424 }, { "epoch": 0.27561608300907914, "grad_norm": 0.2236328125, "learning_rate": 1.9401706862893897e-05, "loss": 0.30021578073501587, "step": 425 }, { "epoch": 0.27626459143968873, "grad_norm": 0.271484375, "learning_rate": 1.9398123099816276e-05, "loss": 0.2926483750343323, "step": 426 }, { "epoch": 0.27691309987029833, "grad_norm": 0.236328125, "learning_rate": 1.9394528968427817e-05, "loss": 0.2945653796195984, "step": 427 }, { "epoch": 0.2775616083009079, "grad_norm": 0.2451171875, "learning_rate": 1.9390924472693685e-05, "loss": 0.27791616320610046, "step": 428 }, { "epoch": 0.2782101167315175, "grad_norm": 0.224609375, "learning_rate": 1.9387309616590473e-05, "loss": 0.2711021304130554, "step": 429 }, { "epoch": 0.2788586251621271, "grad_norm": 0.23828125, "learning_rate": 1.9383684404106204e-05, "loss": 0.2817571461200714, "step": 430 }, { "epoch": 0.2795071335927367, "grad_norm": 0.259765625, "learning_rate": 1.938004883924033e-05, "loss": 0.27956560254096985, "step": 431 }, { "epoch": 0.2801556420233463, "grad_norm": 0.275390625, "learning_rate": 1.9376402926003725e-05, "loss": 0.29066500067710876, "step": 432 }, { "epoch": 0.2808041504539559, "grad_norm": 0.2734375, "learning_rate": 1.937274666841867e-05, "loss": 0.29365652799606323, "step": 433 }, { "epoch": 0.2814526588845655, "grad_norm": 0.23046875, "learning_rate": 1.9369080070518877e-05, "loss": 0.2950628399848938, "step": 434 }, { "epoch": 0.2821011673151751, "grad_norm": 0.2265625, "learning_rate": 1.936540313634945e-05, "loss": 0.2710784673690796, "step": 435 }, { "epoch": 0.2827496757457847, "grad_norm": 0.2578125, "learning_rate": 1.9361715869966892e-05, "loss": 0.2984054684638977, "step": 436 }, { "epoch": 0.2833981841763943, "grad_norm": 0.265625, "learning_rate": 1.935801827543912e-05, "loss": 0.3047255277633667, "step": 437 }, { "epoch": 0.2840466926070039, "grad_norm": 0.248046875, "learning_rate": 1.935431035684545e-05, "loss": 0.2708868384361267, "step": 438 }, { "epoch": 0.2846952010376135, "grad_norm": 0.2451171875, "learning_rate": 1.935059211827656e-05, "loss": 0.3094037175178528, "step": 439 }, { "epoch": 0.2853437094682231, "grad_norm": 0.2294921875, "learning_rate": 1.9346863563834537e-05, "loss": 0.2826778292655945, "step": 440 }, { "epoch": 0.28599221789883267, "grad_norm": 0.2578125, "learning_rate": 1.934312469763284e-05, "loss": 0.30942949652671814, "step": 441 }, { "epoch": 0.28664072632944226, "grad_norm": 0.220703125, "learning_rate": 1.933937552379631e-05, "loss": 0.26447421312332153, "step": 442 }, { "epoch": 0.28728923476005186, "grad_norm": 0.318359375, "learning_rate": 1.9335616046461152e-05, "loss": 0.28429916501045227, "step": 443 }, { "epoch": 0.28793774319066145, "grad_norm": 0.25, "learning_rate": 1.9331846269774945e-05, "loss": 0.3185134530067444, "step": 444 }, { "epoch": 0.28858625162127105, "grad_norm": 0.23828125, "learning_rate": 1.9328066197896623e-05, "loss": 0.28799208998680115, "step": 445 }, { "epoch": 0.2892347600518807, "grad_norm": 0.267578125, "learning_rate": 1.9324275834996486e-05, "loss": 0.2888827621936798, "step": 446 }, { "epoch": 0.2898832684824903, "grad_norm": 0.2392578125, "learning_rate": 1.932047518525618e-05, "loss": 0.2912513315677643, "step": 447 }, { "epoch": 0.2905317769130999, "grad_norm": 0.2412109375, "learning_rate": 1.9316664252868712e-05, "loss": 0.28574490547180176, "step": 448 }, { "epoch": 0.2911802853437095, "grad_norm": 0.240234375, "learning_rate": 1.9312843042038415e-05, "loss": 0.2768983840942383, "step": 449 }, { "epoch": 0.2918287937743191, "grad_norm": 0.25390625, "learning_rate": 1.930901155698098e-05, "loss": 0.30494269728660583, "step": 450 }, { "epoch": 0.2924773022049287, "grad_norm": 0.263671875, "learning_rate": 1.930516980192342e-05, "loss": 0.29532772302627563, "step": 451 }, { "epoch": 0.2931258106355383, "grad_norm": 0.251953125, "learning_rate": 1.930131778110408e-05, "loss": 0.29028698801994324, "step": 452 }, { "epoch": 0.29377431906614787, "grad_norm": 0.2275390625, "learning_rate": 1.929745549877264e-05, "loss": 0.2830733358860016, "step": 453 }, { "epoch": 0.29442282749675747, "grad_norm": 0.23046875, "learning_rate": 1.9293582959190086e-05, "loss": 0.26716575026512146, "step": 454 }, { "epoch": 0.29507133592736706, "grad_norm": 0.2314453125, "learning_rate": 1.928970016662873e-05, "loss": 0.2805415391921997, "step": 455 }, { "epoch": 0.29571984435797666, "grad_norm": 0.2294921875, "learning_rate": 1.92858071253722e-05, "loss": 0.2673115134239197, "step": 456 }, { "epoch": 0.29636835278858625, "grad_norm": 0.2197265625, "learning_rate": 1.9281903839715413e-05, "loss": 0.28085118532180786, "step": 457 }, { "epoch": 0.29701686121919585, "grad_norm": 0.2333984375, "learning_rate": 1.9277990313964607e-05, "loss": 0.30207595229148865, "step": 458 }, { "epoch": 0.29766536964980544, "grad_norm": 0.267578125, "learning_rate": 1.9274066552437303e-05, "loss": 0.29515212774276733, "step": 459 }, { "epoch": 0.29831387808041504, "grad_norm": 0.2333984375, "learning_rate": 1.9270132559462325e-05, "loss": 0.27699923515319824, "step": 460 }, { "epoch": 0.29896238651102464, "grad_norm": 0.244140625, "learning_rate": 1.9266188339379782e-05, "loss": 0.28386765718460083, "step": 461 }, { "epoch": 0.29961089494163423, "grad_norm": 0.2275390625, "learning_rate": 1.926223389654106e-05, "loss": 0.28587639331817627, "step": 462 }, { "epoch": 0.3002594033722438, "grad_norm": 0.2294921875, "learning_rate": 1.925826923530883e-05, "loss": 0.29401570558547974, "step": 463 }, { "epoch": 0.3009079118028534, "grad_norm": 0.2265625, "learning_rate": 1.925429436005703e-05, "loss": 0.28549814224243164, "step": 464 }, { "epoch": 0.301556420233463, "grad_norm": 0.23046875, "learning_rate": 1.9250309275170876e-05, "loss": 0.2894708514213562, "step": 465 }, { "epoch": 0.3022049286640726, "grad_norm": 0.3046875, "learning_rate": 1.9246313985046833e-05, "loss": 0.27185335755348206, "step": 466 }, { "epoch": 0.3028534370946822, "grad_norm": 0.2294921875, "learning_rate": 1.924230849409264e-05, "loss": 0.27790164947509766, "step": 467 }, { "epoch": 0.3035019455252918, "grad_norm": 0.228515625, "learning_rate": 1.9238292806727277e-05, "loss": 0.2594006657600403, "step": 468 }, { "epoch": 0.3041504539559014, "grad_norm": 0.2314453125, "learning_rate": 1.923426692738099e-05, "loss": 0.30137962102890015, "step": 469 }, { "epoch": 0.30479896238651105, "grad_norm": 0.2392578125, "learning_rate": 1.9230230860495245e-05, "loss": 0.2914367914199829, "step": 470 }, { "epoch": 0.30544747081712065, "grad_norm": 0.2333984375, "learning_rate": 1.922618461052277e-05, "loss": 0.29894542694091797, "step": 471 }, { "epoch": 0.30609597924773024, "grad_norm": 0.23046875, "learning_rate": 1.9222128181927512e-05, "loss": 0.2631731629371643, "step": 472 }, { "epoch": 0.30674448767833984, "grad_norm": 0.2333984375, "learning_rate": 1.921806157918465e-05, "loss": 0.2810553014278412, "step": 473 }, { "epoch": 0.30739299610894943, "grad_norm": 0.23828125, "learning_rate": 1.9213984806780606e-05, "loss": 0.2870325744152069, "step": 474 }, { "epoch": 0.30804150453955903, "grad_norm": 0.228515625, "learning_rate": 1.920989786921299e-05, "loss": 0.277665913105011, "step": 475 }, { "epoch": 0.3086900129701686, "grad_norm": 0.25390625, "learning_rate": 1.9205800770990647e-05, "loss": 0.27994000911712646, "step": 476 }, { "epoch": 0.3093385214007782, "grad_norm": 0.2294921875, "learning_rate": 1.9201693516633635e-05, "loss": 0.28040751814842224, "step": 477 }, { "epoch": 0.3099870298313878, "grad_norm": 0.224609375, "learning_rate": 1.9197576110673198e-05, "loss": 0.2787296175956726, "step": 478 }, { "epoch": 0.3106355382619974, "grad_norm": 0.2197265625, "learning_rate": 1.9193448557651794e-05, "loss": 0.27137133479118347, "step": 479 }, { "epoch": 0.311284046692607, "grad_norm": 0.234375, "learning_rate": 1.9189310862123076e-05, "loss": 0.2663111686706543, "step": 480 }, { "epoch": 0.3119325551232166, "grad_norm": 0.2470703125, "learning_rate": 1.9185163028651878e-05, "loss": 0.3029720187187195, "step": 481 }, { "epoch": 0.3125810635538262, "grad_norm": 0.2255859375, "learning_rate": 1.9181005061814223e-05, "loss": 0.271523118019104, "step": 482 }, { "epoch": 0.3132295719844358, "grad_norm": 0.2177734375, "learning_rate": 1.9176836966197318e-05, "loss": 0.29047006368637085, "step": 483 }, { "epoch": 0.3138780804150454, "grad_norm": 0.2353515625, "learning_rate": 1.917265874639953e-05, "loss": 0.28538036346435547, "step": 484 }, { "epoch": 0.314526588845655, "grad_norm": 0.224609375, "learning_rate": 1.9168470407030416e-05, "loss": 0.2743898928165436, "step": 485 }, { "epoch": 0.3151750972762646, "grad_norm": 0.2158203125, "learning_rate": 1.916427195271068e-05, "loss": 0.27812623977661133, "step": 486 }, { "epoch": 0.3158236057068742, "grad_norm": 0.2216796875, "learning_rate": 1.9160063388072192e-05, "loss": 0.271104633808136, "step": 487 }, { "epoch": 0.3164721141374838, "grad_norm": 0.2314453125, "learning_rate": 1.9155844717757977e-05, "loss": 0.273567795753479, "step": 488 }, { "epoch": 0.31712062256809337, "grad_norm": 0.2158203125, "learning_rate": 1.915161594642221e-05, "loss": 0.278580904006958, "step": 489 }, { "epoch": 0.31776913099870296, "grad_norm": 0.2333984375, "learning_rate": 1.91473770787302e-05, "loss": 0.27896571159362793, "step": 490 }, { "epoch": 0.31841763942931256, "grad_norm": 0.21484375, "learning_rate": 1.9143128119358407e-05, "loss": 0.2643428444862366, "step": 491 }, { "epoch": 0.31906614785992216, "grad_norm": 0.2431640625, "learning_rate": 1.913886907299442e-05, "loss": 0.28314852714538574, "step": 492 }, { "epoch": 0.31971465629053175, "grad_norm": 0.2333984375, "learning_rate": 1.913459994433695e-05, "loss": 0.2874375581741333, "step": 493 }, { "epoch": 0.3203631647211414, "grad_norm": 0.2373046875, "learning_rate": 1.9130320738095844e-05, "loss": 0.30206790566444397, "step": 494 }, { "epoch": 0.321011673151751, "grad_norm": 0.2275390625, "learning_rate": 1.9126031458992058e-05, "loss": 0.28514862060546875, "step": 495 }, { "epoch": 0.3216601815823606, "grad_norm": 0.224609375, "learning_rate": 1.9121732111757654e-05, "loss": 0.2761240303516388, "step": 496 }, { "epoch": 0.3223086900129702, "grad_norm": 0.2265625, "learning_rate": 1.9117422701135816e-05, "loss": 0.27630919218063354, "step": 497 }, { "epoch": 0.3229571984435798, "grad_norm": 0.2255859375, "learning_rate": 1.911310323188083e-05, "loss": 0.27804285287857056, "step": 498 }, { "epoch": 0.3236057068741894, "grad_norm": 0.2314453125, "learning_rate": 1.9108773708758063e-05, "loss": 0.2681125998497009, "step": 499 }, { "epoch": 0.324254215304799, "grad_norm": 0.2373046875, "learning_rate": 1.9104434136543987e-05, "loss": 0.2708478569984436, "step": 500 }, { "epoch": 0.32490272373540857, "grad_norm": 0.228515625, "learning_rate": 1.9100084520026164e-05, "loss": 0.28275227546691895, "step": 501 }, { "epoch": 0.32555123216601817, "grad_norm": 0.234375, "learning_rate": 1.9095724864003218e-05, "loss": 0.2647738754749298, "step": 502 }, { "epoch": 0.32619974059662776, "grad_norm": 0.224609375, "learning_rate": 1.909135517328487e-05, "loss": 0.28028982877731323, "step": 503 }, { "epoch": 0.32684824902723736, "grad_norm": 0.2314453125, "learning_rate": 1.90869754526919e-05, "loss": 0.28068646788597107, "step": 504 }, { "epoch": 0.32749675745784695, "grad_norm": 0.23046875, "learning_rate": 1.9082585707056157e-05, "loss": 0.26066550612449646, "step": 505 }, { "epoch": 0.32814526588845655, "grad_norm": 0.244140625, "learning_rate": 1.9078185941220557e-05, "loss": 0.26525288820266724, "step": 506 }, { "epoch": 0.32879377431906615, "grad_norm": 0.21875, "learning_rate": 1.9073776160039043e-05, "loss": 0.2457423359155655, "step": 507 }, { "epoch": 0.32944228274967574, "grad_norm": 0.2294921875, "learning_rate": 1.9069356368376645e-05, "loss": 0.2608604431152344, "step": 508 }, { "epoch": 0.33009079118028534, "grad_norm": 0.263671875, "learning_rate": 1.9064926571109416e-05, "loss": 0.29162269830703735, "step": 509 }, { "epoch": 0.33073929961089493, "grad_norm": 0.244140625, "learning_rate": 1.9060486773124444e-05, "loss": 0.26603347063064575, "step": 510 }, { "epoch": 0.33138780804150453, "grad_norm": 0.25390625, "learning_rate": 1.905603697931986e-05, "loss": 0.2721555829048157, "step": 511 }, { "epoch": 0.3320363164721141, "grad_norm": 0.2265625, "learning_rate": 1.9051577194604816e-05, "loss": 0.2646275460720062, "step": 512 }, { "epoch": 0.3326848249027237, "grad_norm": 0.240234375, "learning_rate": 1.9047107423899497e-05, "loss": 0.28752362728118896, "step": 513 }, { "epoch": 0.3333333333333333, "grad_norm": 0.2412109375, "learning_rate": 1.904262767213509e-05, "loss": 0.2762068510055542, "step": 514 }, { "epoch": 0.3339818417639429, "grad_norm": 0.2353515625, "learning_rate": 1.9038137944253808e-05, "loss": 0.2695223391056061, "step": 515 }, { "epoch": 0.3346303501945525, "grad_norm": 0.2294921875, "learning_rate": 1.9033638245208856e-05, "loss": 0.2743101716041565, "step": 516 }, { "epoch": 0.3352788586251621, "grad_norm": 0.26171875, "learning_rate": 1.902912857996445e-05, "loss": 0.24928617477416992, "step": 517 }, { "epoch": 0.3359273670557717, "grad_norm": 0.25, "learning_rate": 1.9024608953495796e-05, "loss": 0.2735181748867035, "step": 518 }, { "epoch": 0.33657587548638135, "grad_norm": 0.232421875, "learning_rate": 1.902007937078909e-05, "loss": 0.26258164644241333, "step": 519 }, { "epoch": 0.33722438391699094, "grad_norm": 0.2138671875, "learning_rate": 1.9015539836841516e-05, "loss": 0.25755342841148376, "step": 520 }, { "epoch": 0.33787289234760054, "grad_norm": 0.220703125, "learning_rate": 1.901099035666123e-05, "loss": 0.28055351972579956, "step": 521 }, { "epoch": 0.33852140077821014, "grad_norm": 0.224609375, "learning_rate": 1.9006430935267367e-05, "loss": 0.27009910345077515, "step": 522 }, { "epoch": 0.33916990920881973, "grad_norm": 0.2412109375, "learning_rate": 1.9001861577690028e-05, "loss": 0.2706766128540039, "step": 523 }, { "epoch": 0.3398184176394293, "grad_norm": 0.2099609375, "learning_rate": 1.8997282288970273e-05, "loss": 0.2900887131690979, "step": 524 }, { "epoch": 0.3404669260700389, "grad_norm": 0.234375, "learning_rate": 1.899269307416012e-05, "loss": 0.27185535430908203, "step": 525 }, { "epoch": 0.3411154345006485, "grad_norm": 0.2353515625, "learning_rate": 1.8988093938322533e-05, "loss": 0.27740374207496643, "step": 526 }, { "epoch": 0.3417639429312581, "grad_norm": 0.23828125, "learning_rate": 1.8983484886531437e-05, "loss": 0.2829630970954895, "step": 527 }, { "epoch": 0.3424124513618677, "grad_norm": 0.251953125, "learning_rate": 1.8978865923871676e-05, "loss": 0.27555108070373535, "step": 528 }, { "epoch": 0.3430609597924773, "grad_norm": 0.2294921875, "learning_rate": 1.8974237055439045e-05, "loss": 0.29424959421157837, "step": 529 }, { "epoch": 0.3437094682230869, "grad_norm": 0.216796875, "learning_rate": 1.8969598286340254e-05, "loss": 0.2604690492153168, "step": 530 }, { "epoch": 0.3443579766536965, "grad_norm": 0.251953125, "learning_rate": 1.8964949621692946e-05, "loss": 0.2805781364440918, "step": 531 }, { "epoch": 0.3450064850843061, "grad_norm": 0.21875, "learning_rate": 1.8960291066625674e-05, "loss": 0.26896440982818604, "step": 532 }, { "epoch": 0.3456549935149157, "grad_norm": 0.2158203125, "learning_rate": 1.8955622626277908e-05, "loss": 0.28967252373695374, "step": 533 }, { "epoch": 0.3463035019455253, "grad_norm": 0.2265625, "learning_rate": 1.8950944305800025e-05, "loss": 0.28978431224823, "step": 534 }, { "epoch": 0.3469520103761349, "grad_norm": 0.234375, "learning_rate": 1.8946256110353287e-05, "loss": 0.27188223600387573, "step": 535 }, { "epoch": 0.3476005188067445, "grad_norm": 0.21484375, "learning_rate": 1.8941558045109868e-05, "loss": 0.2666720747947693, "step": 536 }, { "epoch": 0.34824902723735407, "grad_norm": 0.236328125, "learning_rate": 1.8936850115252827e-05, "loss": 0.24734994769096375, "step": 537 }, { "epoch": 0.34889753566796367, "grad_norm": 0.2333984375, "learning_rate": 1.8932132325976102e-05, "loss": 0.2679750919342041, "step": 538 }, { "epoch": 0.34954604409857326, "grad_norm": 0.23828125, "learning_rate": 1.8927404682484504e-05, "loss": 0.2873380184173584, "step": 539 }, { "epoch": 0.35019455252918286, "grad_norm": 0.2265625, "learning_rate": 1.8922667189993726e-05, "loss": 0.2693762481212616, "step": 540 }, { "epoch": 0.35084306095979245, "grad_norm": 0.212890625, "learning_rate": 1.891791985373032e-05, "loss": 0.27440381050109863, "step": 541 }, { "epoch": 0.35149156939040205, "grad_norm": 0.248046875, "learning_rate": 1.8913162678931703e-05, "loss": 0.2749295234680176, "step": 542 }, { "epoch": 0.3521400778210117, "grad_norm": 0.2158203125, "learning_rate": 1.8908395670846137e-05, "loss": 0.254534512758255, "step": 543 }, { "epoch": 0.3527885862516213, "grad_norm": 0.259765625, "learning_rate": 1.8903618834732744e-05, "loss": 0.26520875096321106, "step": 544 }, { "epoch": 0.3534370946822309, "grad_norm": 0.25390625, "learning_rate": 1.8898832175861475e-05, "loss": 0.28729546070098877, "step": 545 }, { "epoch": 0.3540856031128405, "grad_norm": 0.23828125, "learning_rate": 1.8894035699513135e-05, "loss": 0.27736058831214905, "step": 546 }, { "epoch": 0.3547341115434501, "grad_norm": 0.2412109375, "learning_rate": 1.8889229410979344e-05, "loss": 0.26611819863319397, "step": 547 }, { "epoch": 0.3553826199740597, "grad_norm": 0.2392578125, "learning_rate": 1.8884413315562555e-05, "loss": 0.25900793075561523, "step": 548 }, { "epoch": 0.3560311284046693, "grad_norm": 0.2275390625, "learning_rate": 1.887958741857604e-05, "loss": 0.27665942907333374, "step": 549 }, { "epoch": 0.35667963683527887, "grad_norm": 0.232421875, "learning_rate": 1.8874751725343885e-05, "loss": 0.27783018350601196, "step": 550 }, { "epoch": 0.35732814526588846, "grad_norm": 0.26953125, "learning_rate": 1.886990624120098e-05, "loss": 0.2722920775413513, "step": 551 }, { "epoch": 0.35797665369649806, "grad_norm": 0.275390625, "learning_rate": 1.8865050971493014e-05, "loss": 0.2649890184402466, "step": 552 }, { "epoch": 0.35862516212710766, "grad_norm": 0.2294921875, "learning_rate": 1.8860185921576483e-05, "loss": 0.25693780183792114, "step": 553 }, { "epoch": 0.35927367055771725, "grad_norm": 0.2470703125, "learning_rate": 1.8855311096818667e-05, "loss": 0.29062920808792114, "step": 554 }, { "epoch": 0.35992217898832685, "grad_norm": 0.244140625, "learning_rate": 1.885042650259762e-05, "loss": 0.2734842598438263, "step": 555 }, { "epoch": 0.36057068741893644, "grad_norm": 0.228515625, "learning_rate": 1.8845532144302195e-05, "loss": 0.26427415013313293, "step": 556 }, { "epoch": 0.36121919584954604, "grad_norm": 0.2109375, "learning_rate": 1.8840628027331995e-05, "loss": 0.2644352912902832, "step": 557 }, { "epoch": 0.36186770428015563, "grad_norm": 0.2265625, "learning_rate": 1.8835714157097403e-05, "loss": 0.26060667634010315, "step": 558 }, { "epoch": 0.36251621271076523, "grad_norm": 0.2373046875, "learning_rate": 1.883079053901956e-05, "loss": 0.24303029477596283, "step": 559 }, { "epoch": 0.3631647211413748, "grad_norm": 0.2236328125, "learning_rate": 1.882585717853036e-05, "loss": 0.28026220202445984, "step": 560 }, { "epoch": 0.3638132295719844, "grad_norm": 0.2294921875, "learning_rate": 1.8820914081072437e-05, "loss": 0.2852172255516052, "step": 561 }, { "epoch": 0.364461738002594, "grad_norm": 0.2275390625, "learning_rate": 1.881596125209918e-05, "loss": 0.2908170819282532, "step": 562 }, { "epoch": 0.3651102464332036, "grad_norm": 0.2392578125, "learning_rate": 1.8810998697074713e-05, "loss": 0.27331292629241943, "step": 563 }, { "epoch": 0.3657587548638132, "grad_norm": 0.228515625, "learning_rate": 1.8806026421473878e-05, "loss": 0.2715567946434021, "step": 564 }, { "epoch": 0.3664072632944228, "grad_norm": 0.2255859375, "learning_rate": 1.880104443078225e-05, "loss": 0.28132930397987366, "step": 565 }, { "epoch": 0.3670557717250324, "grad_norm": 0.2216796875, "learning_rate": 1.879605273049613e-05, "loss": 0.28199344873428345, "step": 566 }, { "epoch": 0.36770428015564205, "grad_norm": 0.220703125, "learning_rate": 1.879105132612251e-05, "loss": 0.25307005643844604, "step": 567 }, { "epoch": 0.36835278858625164, "grad_norm": 0.220703125, "learning_rate": 1.8786040223179106e-05, "loss": 0.26062431931495667, "step": 568 }, { "epoch": 0.36900129701686124, "grad_norm": 0.265625, "learning_rate": 1.878101942719433e-05, "loss": 0.2760327458381653, "step": 569 }, { "epoch": 0.36964980544747084, "grad_norm": 0.228515625, "learning_rate": 1.877598894370728e-05, "loss": 0.26406168937683105, "step": 570 }, { "epoch": 0.37029831387808043, "grad_norm": 0.2197265625, "learning_rate": 1.8770948778267744e-05, "loss": 0.26075440645217896, "step": 571 }, { "epoch": 0.37094682230869, "grad_norm": 0.2275390625, "learning_rate": 1.87658989364362e-05, "loss": 0.2654181122779846, "step": 572 }, { "epoch": 0.3715953307392996, "grad_norm": 0.2333984375, "learning_rate": 1.8760839423783796e-05, "loss": 0.2753872275352478, "step": 573 }, { "epoch": 0.3722438391699092, "grad_norm": 0.224609375, "learning_rate": 1.8755770245892345e-05, "loss": 0.2629868686199188, "step": 574 }, { "epoch": 0.3728923476005188, "grad_norm": 0.2314453125, "learning_rate": 1.8750691408354332e-05, "loss": 0.28653058409690857, "step": 575 }, { "epoch": 0.3735408560311284, "grad_norm": 0.2734375, "learning_rate": 1.8745602916772884e-05, "loss": 0.27308058738708496, "step": 576 }, { "epoch": 0.374189364461738, "grad_norm": 0.2236328125, "learning_rate": 1.8740504776761795e-05, "loss": 0.26945924758911133, "step": 577 }, { "epoch": 0.3748378728923476, "grad_norm": 0.236328125, "learning_rate": 1.8735396993945502e-05, "loss": 0.27014094591140747, "step": 578 }, { "epoch": 0.3754863813229572, "grad_norm": 0.2197265625, "learning_rate": 1.873027957395906e-05, "loss": 0.27467191219329834, "step": 579 }, { "epoch": 0.3761348897535668, "grad_norm": 0.2333984375, "learning_rate": 1.872515252244818e-05, "loss": 0.2852683961391449, "step": 580 }, { "epoch": 0.3767833981841764, "grad_norm": 0.220703125, "learning_rate": 1.8720015845069194e-05, "loss": 0.2728208005428314, "step": 581 }, { "epoch": 0.377431906614786, "grad_norm": 0.2353515625, "learning_rate": 1.871486954748904e-05, "loss": 0.25440341234207153, "step": 582 }, { "epoch": 0.3780804150453956, "grad_norm": 0.21875, "learning_rate": 1.8709713635385282e-05, "loss": 0.2647070586681366, "step": 583 }, { "epoch": 0.3787289234760052, "grad_norm": 0.208984375, "learning_rate": 1.870454811444609e-05, "loss": 0.2678894102573395, "step": 584 }, { "epoch": 0.37937743190661477, "grad_norm": 0.2412109375, "learning_rate": 1.869937299037023e-05, "loss": 0.25251859426498413, "step": 585 }, { "epoch": 0.38002594033722437, "grad_norm": 0.23046875, "learning_rate": 1.8694188268867063e-05, "loss": 0.2684122323989868, "step": 586 }, { "epoch": 0.38067444876783396, "grad_norm": 0.232421875, "learning_rate": 1.8688993955656548e-05, "loss": 0.28381258249282837, "step": 587 }, { "epoch": 0.38132295719844356, "grad_norm": 0.2109375, "learning_rate": 1.8683790056469208e-05, "loss": 0.253908634185791, "step": 588 }, { "epoch": 0.38197146562905315, "grad_norm": 0.23046875, "learning_rate": 1.8678576577046158e-05, "loss": 0.25856703519821167, "step": 589 }, { "epoch": 0.38261997405966275, "grad_norm": 0.236328125, "learning_rate": 1.8673353523139073e-05, "loss": 0.26157838106155396, "step": 590 }, { "epoch": 0.3832684824902724, "grad_norm": 0.24609375, "learning_rate": 1.8668120900510193e-05, "loss": 0.2577868103981018, "step": 591 }, { "epoch": 0.383916990920882, "grad_norm": 0.2216796875, "learning_rate": 1.8662878714932315e-05, "loss": 0.26218026876449585, "step": 592 }, { "epoch": 0.3845654993514916, "grad_norm": 0.2373046875, "learning_rate": 1.865762697218879e-05, "loss": 0.26802363991737366, "step": 593 }, { "epoch": 0.3852140077821012, "grad_norm": 0.2392578125, "learning_rate": 1.8652365678073505e-05, "loss": 0.2719504237174988, "step": 594 }, { "epoch": 0.3858625162127108, "grad_norm": 0.2236328125, "learning_rate": 1.8647094838390894e-05, "loss": 0.25193920731544495, "step": 595 }, { "epoch": 0.3865110246433204, "grad_norm": 0.255859375, "learning_rate": 1.864181445895591e-05, "loss": 0.27372318506240845, "step": 596 }, { "epoch": 0.38715953307393, "grad_norm": 0.2216796875, "learning_rate": 1.8636524545594036e-05, "loss": 0.25786399841308594, "step": 597 }, { "epoch": 0.38780804150453957, "grad_norm": 0.2294921875, "learning_rate": 1.863122510414128e-05, "loss": 0.26325762271881104, "step": 598 }, { "epoch": 0.38845654993514916, "grad_norm": 0.224609375, "learning_rate": 1.8625916140444152e-05, "loss": 0.2703898549079895, "step": 599 }, { "epoch": 0.38910505836575876, "grad_norm": 0.2265625, "learning_rate": 1.8620597660359677e-05, "loss": 0.2566010355949402, "step": 600 }, { "epoch": 0.38975356679636836, "grad_norm": 0.23046875, "learning_rate": 1.861526966975536e-05, "loss": 0.26704978942871094, "step": 601 }, { "epoch": 0.39040207522697795, "grad_norm": 0.255859375, "learning_rate": 1.8609932174509228e-05, "loss": 0.26858243346214294, "step": 602 }, { "epoch": 0.39105058365758755, "grad_norm": 0.2177734375, "learning_rate": 1.8604585180509762e-05, "loss": 0.2640794813632965, "step": 603 }, { "epoch": 0.39169909208819714, "grad_norm": 0.248046875, "learning_rate": 1.8599228693655944e-05, "loss": 0.2757962942123413, "step": 604 }, { "epoch": 0.39234760051880674, "grad_norm": 0.244140625, "learning_rate": 1.8593862719857223e-05, "loss": 0.27895021438598633, "step": 605 }, { "epoch": 0.39299610894941633, "grad_norm": 0.23046875, "learning_rate": 1.8588487265033514e-05, "loss": 0.25440484285354614, "step": 606 }, { "epoch": 0.39364461738002593, "grad_norm": 0.2275390625, "learning_rate": 1.8583102335115186e-05, "loss": 0.2513465881347656, "step": 607 }, { "epoch": 0.3942931258106355, "grad_norm": 0.2216796875, "learning_rate": 1.8577707936043068e-05, "loss": 0.24205714464187622, "step": 608 }, { "epoch": 0.3949416342412451, "grad_norm": 0.21875, "learning_rate": 1.8572304073768437e-05, "loss": 0.2589496374130249, "step": 609 }, { "epoch": 0.3955901426718547, "grad_norm": 0.2236328125, "learning_rate": 1.856689075425301e-05, "loss": 0.2580423951148987, "step": 610 }, { "epoch": 0.3962386511024643, "grad_norm": 0.2197265625, "learning_rate": 1.8561467983468926e-05, "loss": 0.25096550583839417, "step": 611 }, { "epoch": 0.3968871595330739, "grad_norm": 0.25, "learning_rate": 1.8556035767398764e-05, "loss": 0.2650999128818512, "step": 612 }, { "epoch": 0.3975356679636835, "grad_norm": 0.26953125, "learning_rate": 1.8550594112035522e-05, "loss": 0.2976752519607544, "step": 613 }, { "epoch": 0.3981841763942931, "grad_norm": 0.2158203125, "learning_rate": 1.8545143023382603e-05, "loss": 0.2693478465080261, "step": 614 }, { "epoch": 0.39883268482490275, "grad_norm": 0.220703125, "learning_rate": 1.8539682507453826e-05, "loss": 0.2557649612426758, "step": 615 }, { "epoch": 0.39948119325551235, "grad_norm": 0.2412109375, "learning_rate": 1.8534212570273408e-05, "loss": 0.26261693239212036, "step": 616 }, { "epoch": 0.40012970168612194, "grad_norm": 0.2177734375, "learning_rate": 1.8528733217875957e-05, "loss": 0.2498488873243332, "step": 617 }, { "epoch": 0.40077821011673154, "grad_norm": 0.2275390625, "learning_rate": 1.8523244456306474e-05, "loss": 0.2657491862773895, "step": 618 }, { "epoch": 0.40142671854734113, "grad_norm": 0.234375, "learning_rate": 1.851774629162033e-05, "loss": 0.27482739090919495, "step": 619 }, { "epoch": 0.40207522697795073, "grad_norm": 0.26171875, "learning_rate": 1.8512238729883286e-05, "loss": 0.26619023084640503, "step": 620 }, { "epoch": 0.4027237354085603, "grad_norm": 0.2421875, "learning_rate": 1.8506721777171453e-05, "loss": 0.2926812767982483, "step": 621 }, { "epoch": 0.4033722438391699, "grad_norm": 0.228515625, "learning_rate": 1.8501195439571314e-05, "loss": 0.2855931520462036, "step": 622 }, { "epoch": 0.4040207522697795, "grad_norm": 0.25390625, "learning_rate": 1.8495659723179696e-05, "loss": 0.27419668436050415, "step": 623 }, { "epoch": 0.4046692607003891, "grad_norm": 0.2255859375, "learning_rate": 1.849011463410379e-05, "loss": 0.27069157361984253, "step": 624 }, { "epoch": 0.4053177691309987, "grad_norm": 0.2236328125, "learning_rate": 1.8484560178461107e-05, "loss": 0.25000548362731934, "step": 625 }, { "epoch": 0.4059662775616083, "grad_norm": 0.2216796875, "learning_rate": 1.84789963623795e-05, "loss": 0.2559022903442383, "step": 626 }, { "epoch": 0.4066147859922179, "grad_norm": 0.2265625, "learning_rate": 1.8473423191997156e-05, "loss": 0.25913703441619873, "step": 627 }, { "epoch": 0.4072632944228275, "grad_norm": 0.21875, "learning_rate": 1.846784067346257e-05, "loss": 0.23663902282714844, "step": 628 }, { "epoch": 0.4079118028534371, "grad_norm": 0.2314453125, "learning_rate": 1.846224881293456e-05, "loss": 0.2616436183452606, "step": 629 }, { "epoch": 0.4085603112840467, "grad_norm": 0.25390625, "learning_rate": 1.8456647616582242e-05, "loss": 0.26892969012260437, "step": 630 }, { "epoch": 0.4092088197146563, "grad_norm": 0.23828125, "learning_rate": 1.845103709058504e-05, "loss": 0.26319366693496704, "step": 631 }, { "epoch": 0.4098573281452659, "grad_norm": 0.2470703125, "learning_rate": 1.8445417241132663e-05, "loss": 0.2579922378063202, "step": 632 }, { "epoch": 0.41050583657587547, "grad_norm": 0.2431640625, "learning_rate": 1.8439788074425105e-05, "loss": 0.2548098564147949, "step": 633 }, { "epoch": 0.41115434500648507, "grad_norm": 0.224609375, "learning_rate": 1.843414959667265e-05, "loss": 0.2641475200653076, "step": 634 }, { "epoch": 0.41180285343709466, "grad_norm": 0.2216796875, "learning_rate": 1.842850181409584e-05, "loss": 0.24372395873069763, "step": 635 }, { "epoch": 0.41245136186770426, "grad_norm": 0.2294921875, "learning_rate": 1.8422844732925503e-05, "loss": 0.24120034277439117, "step": 636 }, { "epoch": 0.41309987029831385, "grad_norm": 0.2734375, "learning_rate": 1.84171783594027e-05, "loss": 0.2788400650024414, "step": 637 }, { "epoch": 0.41374837872892345, "grad_norm": 0.25, "learning_rate": 1.841150269977876e-05, "loss": 0.2587830424308777, "step": 638 }, { "epoch": 0.4143968871595331, "grad_norm": 0.2197265625, "learning_rate": 1.8405817760315255e-05, "loss": 0.24614320695400238, "step": 639 }, { "epoch": 0.4150453955901427, "grad_norm": 0.234375, "learning_rate": 1.840012354728399e-05, "loss": 0.24267099797725677, "step": 640 }, { "epoch": 0.4156939040207523, "grad_norm": 0.216796875, "learning_rate": 1.8394420066967003e-05, "loss": 0.2598766088485718, "step": 641 }, { "epoch": 0.4163424124513619, "grad_norm": 0.2333984375, "learning_rate": 1.838870732565656e-05, "loss": 0.271318256855011, "step": 642 }, { "epoch": 0.4169909208819715, "grad_norm": 0.236328125, "learning_rate": 1.8382985329655132e-05, "loss": 0.28252264857292175, "step": 643 }, { "epoch": 0.4176394293125811, "grad_norm": 0.2333984375, "learning_rate": 1.837725408527542e-05, "loss": 0.25201451778411865, "step": 644 }, { "epoch": 0.4182879377431907, "grad_norm": 0.2314453125, "learning_rate": 1.8371513598840307e-05, "loss": 0.2542056739330292, "step": 645 }, { "epoch": 0.41893644617380027, "grad_norm": 0.21875, "learning_rate": 1.836576387668289e-05, "loss": 0.25016891956329346, "step": 646 }, { "epoch": 0.41958495460440987, "grad_norm": 0.2353515625, "learning_rate": 1.836000492514644e-05, "loss": 0.26977819204330444, "step": 647 }, { "epoch": 0.42023346303501946, "grad_norm": 0.263671875, "learning_rate": 1.835423675058442e-05, "loss": 0.2653461694717407, "step": 648 }, { "epoch": 0.42088197146562906, "grad_norm": 0.2236328125, "learning_rate": 1.8348459359360467e-05, "loss": 0.27749326825141907, "step": 649 }, { "epoch": 0.42153047989623865, "grad_norm": 0.220703125, "learning_rate": 1.8342672757848377e-05, "loss": 0.25108766555786133, "step": 650 }, { "epoch": 0.42217898832684825, "grad_norm": 0.236328125, "learning_rate": 1.8336876952432125e-05, "loss": 0.27162158489227295, "step": 651 }, { "epoch": 0.42282749675745784, "grad_norm": 0.22265625, "learning_rate": 1.833107194950582e-05, "loss": 0.27731579542160034, "step": 652 }, { "epoch": 0.42347600518806744, "grad_norm": 0.228515625, "learning_rate": 1.8325257755473735e-05, "loss": 0.25708386301994324, "step": 653 }, { "epoch": 0.42412451361867703, "grad_norm": 0.234375, "learning_rate": 1.831943437675027e-05, "loss": 0.2874174118041992, "step": 654 }, { "epoch": 0.42477302204928663, "grad_norm": 0.21484375, "learning_rate": 1.8313601819759967e-05, "loss": 0.25844547152519226, "step": 655 }, { "epoch": 0.4254215304798962, "grad_norm": 0.259765625, "learning_rate": 1.8307760090937486e-05, "loss": 0.2667010724544525, "step": 656 }, { "epoch": 0.4260700389105058, "grad_norm": 0.240234375, "learning_rate": 1.8301909196727613e-05, "loss": 0.26200398802757263, "step": 657 }, { "epoch": 0.4267185473411154, "grad_norm": 0.23046875, "learning_rate": 1.8296049143585237e-05, "loss": 0.25926074385643005, "step": 658 }, { "epoch": 0.427367055771725, "grad_norm": 0.23828125, "learning_rate": 1.8290179937975364e-05, "loss": 0.273723304271698, "step": 659 }, { "epoch": 0.4280155642023346, "grad_norm": 0.228515625, "learning_rate": 1.8284301586373082e-05, "loss": 0.26151466369628906, "step": 660 }, { "epoch": 0.4286640726329442, "grad_norm": 0.23046875, "learning_rate": 1.8278414095263586e-05, "loss": 0.26056110858917236, "step": 661 }, { "epoch": 0.4293125810635538, "grad_norm": 0.216796875, "learning_rate": 1.8272517471142136e-05, "loss": 0.2507365942001343, "step": 662 }, { "epoch": 0.42996108949416345, "grad_norm": 0.21875, "learning_rate": 1.8266611720514085e-05, "loss": 0.28002113103866577, "step": 663 }, { "epoch": 0.43060959792477305, "grad_norm": 0.2197265625, "learning_rate": 1.826069684989484e-05, "loss": 0.26374149322509766, "step": 664 }, { "epoch": 0.43125810635538264, "grad_norm": 0.2138671875, "learning_rate": 1.825477286580988e-05, "loss": 0.25413697957992554, "step": 665 }, { "epoch": 0.43190661478599224, "grad_norm": 0.2138671875, "learning_rate": 1.8248839774794732e-05, "loss": 0.2442082166671753, "step": 666 }, { "epoch": 0.43255512321660183, "grad_norm": 0.248046875, "learning_rate": 1.8242897583394975e-05, "loss": 0.25871801376342773, "step": 667 }, { "epoch": 0.43320363164721143, "grad_norm": 0.2431640625, "learning_rate": 1.8236946298166217e-05, "loss": 0.25211721658706665, "step": 668 }, { "epoch": 0.433852140077821, "grad_norm": 0.216796875, "learning_rate": 1.823098592567412e-05, "loss": 0.28030920028686523, "step": 669 }, { "epoch": 0.4345006485084306, "grad_norm": 0.25390625, "learning_rate": 1.8225016472494348e-05, "loss": 0.26751983165740967, "step": 670 }, { "epoch": 0.4351491569390402, "grad_norm": 0.2392578125, "learning_rate": 1.8219037945212595e-05, "loss": 0.2555464506149292, "step": 671 }, { "epoch": 0.4357976653696498, "grad_norm": 0.2294921875, "learning_rate": 1.8213050350424567e-05, "loss": 0.25078654289245605, "step": 672 }, { "epoch": 0.4364461738002594, "grad_norm": 0.2236328125, "learning_rate": 1.820705369473597e-05, "loss": 0.2714647650718689, "step": 673 }, { "epoch": 0.437094682230869, "grad_norm": 0.267578125, "learning_rate": 1.8201047984762503e-05, "loss": 0.2691151201725006, "step": 674 }, { "epoch": 0.4377431906614786, "grad_norm": 0.2373046875, "learning_rate": 1.8195033227129863e-05, "loss": 0.2522677481174469, "step": 675 }, { "epoch": 0.4383916990920882, "grad_norm": 0.224609375, "learning_rate": 1.818900942847372e-05, "loss": 0.26131200790405273, "step": 676 }, { "epoch": 0.4390402075226978, "grad_norm": 0.2265625, "learning_rate": 1.8182976595439726e-05, "loss": 0.27142566442489624, "step": 677 }, { "epoch": 0.4396887159533074, "grad_norm": 0.2236328125, "learning_rate": 1.817693473468349e-05, "loss": 0.2690189778804779, "step": 678 }, { "epoch": 0.440337224383917, "grad_norm": 0.251953125, "learning_rate": 1.8170883852870593e-05, "loss": 0.2595691978931427, "step": 679 }, { "epoch": 0.4409857328145266, "grad_norm": 0.2353515625, "learning_rate": 1.8164823956676553e-05, "loss": 0.2668459415435791, "step": 680 }, { "epoch": 0.44163424124513617, "grad_norm": 0.224609375, "learning_rate": 1.815875505278685e-05, "loss": 0.2561210095882416, "step": 681 }, { "epoch": 0.44228274967574577, "grad_norm": 0.2392578125, "learning_rate": 1.8152677147896893e-05, "loss": 0.2508721649646759, "step": 682 }, { "epoch": 0.44293125810635536, "grad_norm": 0.228515625, "learning_rate": 1.8146590248712017e-05, "loss": 0.2660960257053375, "step": 683 }, { "epoch": 0.44357976653696496, "grad_norm": 0.2314453125, "learning_rate": 1.8140494361947486e-05, "loss": 0.29863590002059937, "step": 684 }, { "epoch": 0.44422827496757455, "grad_norm": 0.2373046875, "learning_rate": 1.8134389494328483e-05, "loss": 0.2517477869987488, "step": 685 }, { "epoch": 0.44487678339818415, "grad_norm": 0.2119140625, "learning_rate": 1.8128275652590085e-05, "loss": 0.2702222466468811, "step": 686 }, { "epoch": 0.4455252918287938, "grad_norm": 0.234375, "learning_rate": 1.8122152843477282e-05, "loss": 0.2465229332447052, "step": 687 }, { "epoch": 0.4461738002594034, "grad_norm": 0.25390625, "learning_rate": 1.8116021073744957e-05, "loss": 0.2706555128097534, "step": 688 }, { "epoch": 0.446822308690013, "grad_norm": 0.216796875, "learning_rate": 1.810988035015787e-05, "loss": 0.2614952325820923, "step": 689 }, { "epoch": 0.4474708171206226, "grad_norm": 0.220703125, "learning_rate": 1.8103730679490667e-05, "loss": 0.2554285526275635, "step": 690 }, { "epoch": 0.4481193255512322, "grad_norm": 0.25, "learning_rate": 1.8097572068527863e-05, "loss": 0.25971710681915283, "step": 691 }, { "epoch": 0.4487678339818418, "grad_norm": 0.2421875, "learning_rate": 1.809140452406383e-05, "loss": 0.25769227743148804, "step": 692 }, { "epoch": 0.4494163424124514, "grad_norm": 0.2138671875, "learning_rate": 1.8085228052902806e-05, "loss": 0.25769588351249695, "step": 693 }, { "epoch": 0.45006485084306097, "grad_norm": 0.2197265625, "learning_rate": 1.807904266185887e-05, "loss": 0.26629507541656494, "step": 694 }, { "epoch": 0.45071335927367057, "grad_norm": 0.2099609375, "learning_rate": 1.8072848357755945e-05, "loss": 0.24739420413970947, "step": 695 }, { "epoch": 0.45136186770428016, "grad_norm": 0.310546875, "learning_rate": 1.8066645147427782e-05, "loss": 0.24358151853084564, "step": 696 }, { "epoch": 0.45201037613488976, "grad_norm": 0.2197265625, "learning_rate": 1.806043303771797e-05, "loss": 0.2619495987892151, "step": 697 }, { "epoch": 0.45265888456549935, "grad_norm": 0.2080078125, "learning_rate": 1.80542120354799e-05, "loss": 0.23797577619552612, "step": 698 }, { "epoch": 0.45330739299610895, "grad_norm": 0.2197265625, "learning_rate": 1.804798214757678e-05, "loss": 0.23617073893547058, "step": 699 }, { "epoch": 0.45395590142671854, "grad_norm": 0.232421875, "learning_rate": 1.804174338088163e-05, "loss": 0.258662611246109, "step": 700 }, { "epoch": 0.45460440985732814, "grad_norm": 0.2294921875, "learning_rate": 1.8035495742277252e-05, "loss": 0.23804756999015808, "step": 701 }, { "epoch": 0.45525291828793774, "grad_norm": 0.22265625, "learning_rate": 1.8029239238656246e-05, "loss": 0.2583202123641968, "step": 702 }, { "epoch": 0.45590142671854733, "grad_norm": 0.21875, "learning_rate": 1.802297387692098e-05, "loss": 0.26310306787490845, "step": 703 }, { "epoch": 0.4565499351491569, "grad_norm": 0.2265625, "learning_rate": 1.8016699663983602e-05, "loss": 0.2551477551460266, "step": 704 }, { "epoch": 0.4571984435797665, "grad_norm": 0.240234375, "learning_rate": 1.8010416606766034e-05, "loss": 0.23326310515403748, "step": 705 }, { "epoch": 0.4578469520103761, "grad_norm": 0.2177734375, "learning_rate": 1.800412471219994e-05, "loss": 0.24993138015270233, "step": 706 }, { "epoch": 0.4584954604409857, "grad_norm": 0.2109375, "learning_rate": 1.799782398722674e-05, "loss": 0.24932679533958435, "step": 707 }, { "epoch": 0.4591439688715953, "grad_norm": 0.23828125, "learning_rate": 1.79915144387976e-05, "loss": 0.25192174315452576, "step": 708 }, { "epoch": 0.4597924773022049, "grad_norm": 0.236328125, "learning_rate": 1.7985196073873414e-05, "loss": 0.2543199956417084, "step": 709 }, { "epoch": 0.4604409857328145, "grad_norm": 0.212890625, "learning_rate": 1.79788688994248e-05, "loss": 0.24767664074897766, "step": 710 }, { "epoch": 0.46108949416342415, "grad_norm": 0.2333984375, "learning_rate": 1.7972532922432105e-05, "loss": 0.26216065883636475, "step": 711 }, { "epoch": 0.46173800259403375, "grad_norm": 0.2265625, "learning_rate": 1.796618814988538e-05, "loss": 0.25524991750717163, "step": 712 }, { "epoch": 0.46238651102464334, "grad_norm": 0.2197265625, "learning_rate": 1.7959834588784386e-05, "loss": 0.25457489490509033, "step": 713 }, { "epoch": 0.46303501945525294, "grad_norm": 0.20703125, "learning_rate": 1.795347224613857e-05, "loss": 0.2699052095413208, "step": 714 }, { "epoch": 0.46368352788586253, "grad_norm": 0.2001953125, "learning_rate": 1.7947101128967074e-05, "loss": 0.22784000635147095, "step": 715 }, { "epoch": 0.46433203631647213, "grad_norm": 0.212890625, "learning_rate": 1.794072124429872e-05, "loss": 0.24393342435359955, "step": 716 }, { "epoch": 0.4649805447470817, "grad_norm": 0.2197265625, "learning_rate": 1.7934332599171997e-05, "loss": 0.2393975555896759, "step": 717 }, { "epoch": 0.4656290531776913, "grad_norm": 0.19921875, "learning_rate": 1.792793520063507e-05, "loss": 0.24963811039924622, "step": 718 }, { "epoch": 0.4662775616083009, "grad_norm": 0.2138671875, "learning_rate": 1.792152905574575e-05, "loss": 0.2523779273033142, "step": 719 }, { "epoch": 0.4669260700389105, "grad_norm": 0.212890625, "learning_rate": 1.79151141715715e-05, "loss": 0.24576711654663086, "step": 720 }, { "epoch": 0.4675745784695201, "grad_norm": 0.212890625, "learning_rate": 1.790869055518943e-05, "loss": 0.26632195711135864, "step": 721 }, { "epoch": 0.4682230869001297, "grad_norm": 0.26171875, "learning_rate": 1.790225821368628e-05, "loss": 0.25126737356185913, "step": 722 }, { "epoch": 0.4688715953307393, "grad_norm": 0.22265625, "learning_rate": 1.789581715415841e-05, "loss": 0.2613705098628998, "step": 723 }, { "epoch": 0.4695201037613489, "grad_norm": 0.232421875, "learning_rate": 1.788936738371181e-05, "loss": 0.2879320979118347, "step": 724 }, { "epoch": 0.4701686121919585, "grad_norm": 0.2109375, "learning_rate": 1.788290890946207e-05, "loss": 0.2542335093021393, "step": 725 }, { "epoch": 0.4708171206225681, "grad_norm": 0.220703125, "learning_rate": 1.7876441738534386e-05, "loss": 0.27183058857917786, "step": 726 }, { "epoch": 0.4714656290531777, "grad_norm": 0.2265625, "learning_rate": 1.7869965878063546e-05, "loss": 0.24853459000587463, "step": 727 }, { "epoch": 0.4721141374837873, "grad_norm": 0.216796875, "learning_rate": 1.7863481335193937e-05, "loss": 0.2545422315597534, "step": 728 }, { "epoch": 0.4727626459143969, "grad_norm": 0.212890625, "learning_rate": 1.78569881170795e-05, "loss": 0.23794987797737122, "step": 729 }, { "epoch": 0.47341115434500647, "grad_norm": 0.2109375, "learning_rate": 1.7850486230883773e-05, "loss": 0.26679521799087524, "step": 730 }, { "epoch": 0.47405966277561606, "grad_norm": 0.2314453125, "learning_rate": 1.784397568377984e-05, "loss": 0.2428193837404251, "step": 731 }, { "epoch": 0.47470817120622566, "grad_norm": 0.2255859375, "learning_rate": 1.783745648295035e-05, "loss": 0.245649516582489, "step": 732 }, { "epoch": 0.47535667963683526, "grad_norm": 0.2177734375, "learning_rate": 1.7830928635587488e-05, "loss": 0.25833919644355774, "step": 733 }, { "epoch": 0.47600518806744485, "grad_norm": 0.228515625, "learning_rate": 1.7824392148892986e-05, "loss": 0.2794002294540405, "step": 734 }, { "epoch": 0.4766536964980545, "grad_norm": 0.2216796875, "learning_rate": 1.7817847030078112e-05, "loss": 0.2471138834953308, "step": 735 }, { "epoch": 0.4773022049286641, "grad_norm": 0.2119140625, "learning_rate": 1.7811293286363646e-05, "loss": 0.2571690082550049, "step": 736 }, { "epoch": 0.4779507133592737, "grad_norm": 0.23046875, "learning_rate": 1.7804730924979888e-05, "loss": 0.24564313888549805, "step": 737 }, { "epoch": 0.4785992217898833, "grad_norm": 0.2177734375, "learning_rate": 1.7798159953166646e-05, "loss": 0.2686495780944824, "step": 738 }, { "epoch": 0.4792477302204929, "grad_norm": 0.2119140625, "learning_rate": 1.7791580378173224e-05, "loss": 0.2721078097820282, "step": 739 }, { "epoch": 0.4798962386511025, "grad_norm": 0.2099609375, "learning_rate": 1.778499220725843e-05, "loss": 0.250704288482666, "step": 740 }, { "epoch": 0.4805447470817121, "grad_norm": 0.2197265625, "learning_rate": 1.7778395447690535e-05, "loss": 0.24144311249256134, "step": 741 }, { "epoch": 0.48119325551232167, "grad_norm": 0.22265625, "learning_rate": 1.77717901067473e-05, "loss": 0.24581509828567505, "step": 742 }, { "epoch": 0.48184176394293127, "grad_norm": 0.236328125, "learning_rate": 1.7765176191715948e-05, "loss": 0.2638018727302551, "step": 743 }, { "epoch": 0.48249027237354086, "grad_norm": 0.2275390625, "learning_rate": 1.7758553709893168e-05, "loss": 0.262343168258667, "step": 744 }, { "epoch": 0.48313878080415046, "grad_norm": 0.208984375, "learning_rate": 1.7751922668585083e-05, "loss": 0.2531052827835083, "step": 745 }, { "epoch": 0.48378728923476005, "grad_norm": 0.2236328125, "learning_rate": 1.7745283075107277e-05, "loss": 0.25088465213775635, "step": 746 }, { "epoch": 0.48443579766536965, "grad_norm": 0.2109375, "learning_rate": 1.7738634936784768e-05, "loss": 0.2619387209415436, "step": 747 }, { "epoch": 0.48508430609597925, "grad_norm": 0.2216796875, "learning_rate": 1.7731978260951985e-05, "loss": 0.25315597653388977, "step": 748 }, { "epoch": 0.48573281452658884, "grad_norm": 0.2177734375, "learning_rate": 1.7725313054952787e-05, "loss": 0.2598324120044708, "step": 749 }, { "epoch": 0.48638132295719844, "grad_norm": 0.2216796875, "learning_rate": 1.7718639326140455e-05, "loss": 0.27035975456237793, "step": 750 }, { "epoch": 0.48702983138780803, "grad_norm": 0.234375, "learning_rate": 1.771195708187765e-05, "loss": 0.26308852434158325, "step": 751 }, { "epoch": 0.4876783398184176, "grad_norm": 0.2353515625, "learning_rate": 1.770526632953644e-05, "loss": 0.26169878244400024, "step": 752 }, { "epoch": 0.4883268482490272, "grad_norm": 0.21875, "learning_rate": 1.7698567076498276e-05, "loss": 0.23757131397724152, "step": 753 }, { "epoch": 0.4889753566796368, "grad_norm": 0.21484375, "learning_rate": 1.7691859330153992e-05, "loss": 0.2526874542236328, "step": 754 }, { "epoch": 0.4896238651102464, "grad_norm": 0.2158203125, "learning_rate": 1.768514309790379e-05, "loss": 0.2701413631439209, "step": 755 }, { "epoch": 0.490272373540856, "grad_norm": 0.2080078125, "learning_rate": 1.767841838715723e-05, "loss": 0.24036994576454163, "step": 756 }, { "epoch": 0.4909208819714656, "grad_norm": 0.208984375, "learning_rate": 1.7671685205333232e-05, "loss": 0.23691552877426147, "step": 757 }, { "epoch": 0.4915693904020752, "grad_norm": 0.2021484375, "learning_rate": 1.7664943559860052e-05, "loss": 0.2451799511909485, "step": 758 }, { "epoch": 0.49221789883268485, "grad_norm": 0.216796875, "learning_rate": 1.7658193458175294e-05, "loss": 0.23674803972244263, "step": 759 }, { "epoch": 0.49286640726329445, "grad_norm": 0.216796875, "learning_rate": 1.7651434907725885e-05, "loss": 0.24700142443180084, "step": 760 }, { "epoch": 0.49351491569390404, "grad_norm": 0.2109375, "learning_rate": 1.7644667915968077e-05, "loss": 0.27151116728782654, "step": 761 }, { "epoch": 0.49416342412451364, "grad_norm": 0.228515625, "learning_rate": 1.7637892490367428e-05, "loss": 0.2425975650548935, "step": 762 }, { "epoch": 0.49481193255512324, "grad_norm": 0.2158203125, "learning_rate": 1.7631108638398812e-05, "loss": 0.24186061322689056, "step": 763 }, { "epoch": 0.49546044098573283, "grad_norm": 0.2080078125, "learning_rate": 1.7624316367546387e-05, "loss": 0.2570067346096039, "step": 764 }, { "epoch": 0.4961089494163424, "grad_norm": 0.2138671875, "learning_rate": 1.7617515685303603e-05, "loss": 0.25335216522216797, "step": 765 }, { "epoch": 0.496757457846952, "grad_norm": 0.2275390625, "learning_rate": 1.7610706599173194e-05, "loss": 0.2574220597743988, "step": 766 }, { "epoch": 0.4974059662775616, "grad_norm": 0.21484375, "learning_rate": 1.760388911666716e-05, "loss": 0.25293251872062683, "step": 767 }, { "epoch": 0.4980544747081712, "grad_norm": 0.2099609375, "learning_rate": 1.7597063245306766e-05, "loss": 0.24504058063030243, "step": 768 }, { "epoch": 0.4987029831387808, "grad_norm": 0.216796875, "learning_rate": 1.7590228992622535e-05, "loss": 0.2496173083782196, "step": 769 }, { "epoch": 0.4993514915693904, "grad_norm": 0.255859375, "learning_rate": 1.758338636615423e-05, "loss": 0.2623802423477173, "step": 770 }, { "epoch": 0.5, "grad_norm": 0.2333984375, "learning_rate": 1.757653537345086e-05, "loss": 0.234059676527977, "step": 771 }, { "epoch": 0.5006485084306096, "grad_norm": 0.2197265625, "learning_rate": 1.756967602207066e-05, "loss": 0.26016756892204285, "step": 772 }, { "epoch": 0.5012970168612192, "grad_norm": 0.2001953125, "learning_rate": 1.756280831958108e-05, "loss": 0.24600207805633545, "step": 773 }, { "epoch": 0.5019455252918288, "grad_norm": 0.2314453125, "learning_rate": 1.7555932273558797e-05, "loss": 0.2642427384853363, "step": 774 }, { "epoch": 0.5025940337224384, "grad_norm": 0.203125, "learning_rate": 1.754904789158968e-05, "loss": 0.25622379779815674, "step": 775 }, { "epoch": 0.503242542153048, "grad_norm": 0.212890625, "learning_rate": 1.7542155181268805e-05, "loss": 0.22302496433258057, "step": 776 }, { "epoch": 0.5038910505836576, "grad_norm": 0.2099609375, "learning_rate": 1.7535254150200428e-05, "loss": 0.2439330518245697, "step": 777 }, { "epoch": 0.5045395590142672, "grad_norm": 0.2138671875, "learning_rate": 1.752834480599799e-05, "loss": 0.23718202114105225, "step": 778 }, { "epoch": 0.5051880674448768, "grad_norm": 0.2314453125, "learning_rate": 1.7521427156284096e-05, "loss": 0.256733775138855, "step": 779 }, { "epoch": 0.5058365758754864, "grad_norm": 0.2060546875, "learning_rate": 1.7514501208690527e-05, "loss": 0.2448139488697052, "step": 780 }, { "epoch": 0.506485084306096, "grad_norm": 0.20703125, "learning_rate": 1.7507566970858202e-05, "loss": 0.2518021762371063, "step": 781 }, { "epoch": 0.5071335927367056, "grad_norm": 0.2197265625, "learning_rate": 1.7500624450437202e-05, "loss": 0.2322305142879486, "step": 782 }, { "epoch": 0.5077821011673151, "grad_norm": 0.2080078125, "learning_rate": 1.7493673655086734e-05, "loss": 0.24691671133041382, "step": 783 }, { "epoch": 0.5084306095979247, "grad_norm": 0.212890625, "learning_rate": 1.7486714592475137e-05, "loss": 0.2665014863014221, "step": 784 }, { "epoch": 0.5090791180285343, "grad_norm": 0.2080078125, "learning_rate": 1.747974727027988e-05, "loss": 0.26431363821029663, "step": 785 }, { "epoch": 0.5097276264591439, "grad_norm": 0.2138671875, "learning_rate": 1.7472771696187523e-05, "loss": 0.2596772313117981, "step": 786 }, { "epoch": 0.5103761348897535, "grad_norm": 0.2451171875, "learning_rate": 1.746578787789376e-05, "loss": 0.259757399559021, "step": 787 }, { "epoch": 0.5110246433203631, "grad_norm": 0.2109375, "learning_rate": 1.7458795823103348e-05, "loss": 0.23468446731567383, "step": 788 }, { "epoch": 0.5116731517509727, "grad_norm": 0.2216796875, "learning_rate": 1.7451795539530156e-05, "loss": 0.25615498423576355, "step": 789 }, { "epoch": 0.5123216601815823, "grad_norm": 0.2158203125, "learning_rate": 1.7444787034897114e-05, "loss": 0.25098350644111633, "step": 790 }, { "epoch": 0.5129701686121919, "grad_norm": 0.2099609375, "learning_rate": 1.7437770316936234e-05, "loss": 0.26461946964263916, "step": 791 }, { "epoch": 0.5136186770428015, "grad_norm": 0.208984375, "learning_rate": 1.743074539338858e-05, "loss": 0.23960307240486145, "step": 792 }, { "epoch": 0.5142671854734111, "grad_norm": 0.2216796875, "learning_rate": 1.7423712272004282e-05, "loss": 0.26992717385292053, "step": 793 }, { "epoch": 0.5149156939040207, "grad_norm": 0.21484375, "learning_rate": 1.7416670960542498e-05, "loss": 0.25818514823913574, "step": 794 }, { "epoch": 0.5155642023346303, "grad_norm": 0.212890625, "learning_rate": 1.7409621466771425e-05, "loss": 0.25449085235595703, "step": 795 }, { "epoch": 0.51621271076524, "grad_norm": 0.2080078125, "learning_rate": 1.7402563798468297e-05, "loss": 0.25367507338523865, "step": 796 }, { "epoch": 0.5168612191958496, "grad_norm": 0.2216796875, "learning_rate": 1.7395497963419362e-05, "loss": 0.27120909094810486, "step": 797 }, { "epoch": 0.5175097276264592, "grad_norm": 0.2080078125, "learning_rate": 1.738842396941987e-05, "loss": 0.24565419554710388, "step": 798 }, { "epoch": 0.5181582360570688, "grad_norm": 0.203125, "learning_rate": 1.738134182427408e-05, "loss": 0.23051393032073975, "step": 799 }, { "epoch": 0.5188067444876784, "grad_norm": 0.224609375, "learning_rate": 1.7374251535795244e-05, "loss": 0.24349388480186462, "step": 800 }, { "epoch": 0.519455252918288, "grad_norm": 0.2001953125, "learning_rate": 1.736715311180559e-05, "loss": 0.23808160424232483, "step": 801 }, { "epoch": 0.5201037613488976, "grad_norm": 0.205078125, "learning_rate": 1.736004656013633e-05, "loss": 0.2502765953540802, "step": 802 }, { "epoch": 0.5207522697795072, "grad_norm": 0.2041015625, "learning_rate": 1.7352931888627648e-05, "loss": 0.23216818273067474, "step": 803 }, { "epoch": 0.5214007782101168, "grad_norm": 0.2158203125, "learning_rate": 1.7345809105128665e-05, "loss": 0.25561437010765076, "step": 804 }, { "epoch": 0.5220492866407264, "grad_norm": 0.21875, "learning_rate": 1.7338678217497468e-05, "loss": 0.2508404850959778, "step": 805 }, { "epoch": 0.522697795071336, "grad_norm": 0.22265625, "learning_rate": 1.7331539233601084e-05, "loss": 0.26383522152900696, "step": 806 }, { "epoch": 0.5233463035019456, "grad_norm": 0.23828125, "learning_rate": 1.7324392161315468e-05, "loss": 0.2545105814933777, "step": 807 }, { "epoch": 0.5239948119325551, "grad_norm": 0.25, "learning_rate": 1.73172370085255e-05, "loss": 0.27660003304481506, "step": 808 }, { "epoch": 0.5246433203631647, "grad_norm": 0.2119140625, "learning_rate": 1.731007378312497e-05, "loss": 0.2372470498085022, "step": 809 }, { "epoch": 0.5252918287937743, "grad_norm": 0.212890625, "learning_rate": 1.7302902493016583e-05, "loss": 0.25344038009643555, "step": 810 }, { "epoch": 0.5259403372243839, "grad_norm": 0.2216796875, "learning_rate": 1.7295723146111934e-05, "loss": 0.24009867012500763, "step": 811 }, { "epoch": 0.5265888456549935, "grad_norm": 0.2177734375, "learning_rate": 1.7288535750331507e-05, "loss": 0.2599325180053711, "step": 812 }, { "epoch": 0.5272373540856031, "grad_norm": 0.1982421875, "learning_rate": 1.728134031360467e-05, "loss": 0.23909229040145874, "step": 813 }, { "epoch": 0.5278858625162127, "grad_norm": 0.2001953125, "learning_rate": 1.7274136843869662e-05, "loss": 0.23628994822502136, "step": 814 }, { "epoch": 0.5285343709468223, "grad_norm": 0.2109375, "learning_rate": 1.7266925349073574e-05, "loss": 0.25099682807922363, "step": 815 }, { "epoch": 0.5291828793774319, "grad_norm": 0.224609375, "learning_rate": 1.7259705837172366e-05, "loss": 0.268869549036026, "step": 816 }, { "epoch": 0.5298313878080415, "grad_norm": 0.2197265625, "learning_rate": 1.7252478316130834e-05, "loss": 0.2530663013458252, "step": 817 }, { "epoch": 0.5304798962386511, "grad_norm": 0.2177734375, "learning_rate": 1.7245242793922606e-05, "loss": 0.23891159892082214, "step": 818 }, { "epoch": 0.5311284046692607, "grad_norm": 0.216796875, "learning_rate": 1.7237999278530146e-05, "loss": 0.24446305632591248, "step": 819 }, { "epoch": 0.5317769130998703, "grad_norm": 0.2060546875, "learning_rate": 1.7230747777944735e-05, "loss": 0.2474980354309082, "step": 820 }, { "epoch": 0.5324254215304799, "grad_norm": 0.240234375, "learning_rate": 1.7223488300166456e-05, "loss": 0.25447648763656616, "step": 821 }, { "epoch": 0.5330739299610895, "grad_norm": 0.251953125, "learning_rate": 1.72162208532042e-05, "loss": 0.2578514516353607, "step": 822 }, { "epoch": 0.5337224383916991, "grad_norm": 0.2119140625, "learning_rate": 1.7208945445075648e-05, "loss": 0.23854947090148926, "step": 823 }, { "epoch": 0.5343709468223087, "grad_norm": 0.205078125, "learning_rate": 1.720166208380726e-05, "loss": 0.24505779147148132, "step": 824 }, { "epoch": 0.5350194552529183, "grad_norm": 0.2197265625, "learning_rate": 1.719437077743428e-05, "loss": 0.2505459785461426, "step": 825 }, { "epoch": 0.5356679636835279, "grad_norm": 0.2041015625, "learning_rate": 1.7187071534000704e-05, "loss": 0.23384061455726624, "step": 826 }, { "epoch": 0.5363164721141375, "grad_norm": 0.220703125, "learning_rate": 1.71797643615593e-05, "loss": 0.26251477003097534, "step": 827 }, { "epoch": 0.5369649805447471, "grad_norm": 0.208984375, "learning_rate": 1.717244926817157e-05, "loss": 0.2499566674232483, "step": 828 }, { "epoch": 0.5376134889753567, "grad_norm": 0.2119140625, "learning_rate": 1.7165126261907755e-05, "loss": 0.2355017066001892, "step": 829 }, { "epoch": 0.5382619974059663, "grad_norm": 0.2255859375, "learning_rate": 1.7157795350846837e-05, "loss": 0.23951615393161774, "step": 830 }, { "epoch": 0.5389105058365758, "grad_norm": 0.2177734375, "learning_rate": 1.7150456543076513e-05, "loss": 0.2398923635482788, "step": 831 }, { "epoch": 0.5395590142671854, "grad_norm": 0.224609375, "learning_rate": 1.714310984669319e-05, "loss": 0.23710858821868896, "step": 832 }, { "epoch": 0.540207522697795, "grad_norm": 0.212890625, "learning_rate": 1.7135755269801972e-05, "loss": 0.2742719054222107, "step": 833 }, { "epoch": 0.5408560311284046, "grad_norm": 0.2275390625, "learning_rate": 1.7128392820516674e-05, "loss": 0.24416588246822357, "step": 834 }, { "epoch": 0.5415045395590142, "grad_norm": 0.212890625, "learning_rate": 1.712102250695978e-05, "loss": 0.25250375270843506, "step": 835 }, { "epoch": 0.5421530479896238, "grad_norm": 0.220703125, "learning_rate": 1.711364433726246e-05, "loss": 0.2595706582069397, "step": 836 }, { "epoch": 0.5428015564202334, "grad_norm": 0.2158203125, "learning_rate": 1.7106258319564542e-05, "loss": 0.23573431372642517, "step": 837 }, { "epoch": 0.543450064850843, "grad_norm": 0.2216796875, "learning_rate": 1.709886446201453e-05, "loss": 0.24604499340057373, "step": 838 }, { "epoch": 0.5440985732814526, "grad_norm": 0.212890625, "learning_rate": 1.709146277276955e-05, "loss": 0.2520371973514557, "step": 839 }, { "epoch": 0.5447470817120622, "grad_norm": 0.234375, "learning_rate": 1.7084053259995387e-05, "loss": 0.2414272278547287, "step": 840 }, { "epoch": 0.5453955901426718, "grad_norm": 0.201171875, "learning_rate": 1.707663593186646e-05, "loss": 0.23957416415214539, "step": 841 }, { "epoch": 0.5460440985732814, "grad_norm": 0.2138671875, "learning_rate": 1.7069210796565796e-05, "loss": 0.25629985332489014, "step": 842 }, { "epoch": 0.546692607003891, "grad_norm": 0.2333984375, "learning_rate": 1.7061777862285046e-05, "loss": 0.25050121545791626, "step": 843 }, { "epoch": 0.5473411154345007, "grad_norm": 0.224609375, "learning_rate": 1.705433713722446e-05, "loss": 0.2497149556875229, "step": 844 }, { "epoch": 0.5479896238651103, "grad_norm": 0.21484375, "learning_rate": 1.7046888629592883e-05, "loss": 0.26282402873039246, "step": 845 }, { "epoch": 0.5486381322957199, "grad_norm": 0.2490234375, "learning_rate": 1.703943234760775e-05, "loss": 0.22858166694641113, "step": 846 }, { "epoch": 0.5492866407263295, "grad_norm": 0.216796875, "learning_rate": 1.7031968299495073e-05, "loss": 0.23788544535636902, "step": 847 }, { "epoch": 0.5499351491569391, "grad_norm": 0.240234375, "learning_rate": 1.7024496493489427e-05, "loss": 0.2616792917251587, "step": 848 }, { "epoch": 0.5505836575875487, "grad_norm": 0.2080078125, "learning_rate": 1.7017016937833944e-05, "loss": 0.2187148630619049, "step": 849 }, { "epoch": 0.5512321660181583, "grad_norm": 0.2255859375, "learning_rate": 1.7009529640780312e-05, "loss": 0.25052139163017273, "step": 850 }, { "epoch": 0.5518806744487679, "grad_norm": 0.203125, "learning_rate": 1.7002034610588762e-05, "loss": 0.24965092539787292, "step": 851 }, { "epoch": 0.5525291828793775, "grad_norm": 0.212890625, "learning_rate": 1.6994531855528047e-05, "loss": 0.2385530173778534, "step": 852 }, { "epoch": 0.5531776913099871, "grad_norm": 0.2177734375, "learning_rate": 1.6987021383875446e-05, "loss": 0.24725677073001862, "step": 853 }, { "epoch": 0.5538261997405967, "grad_norm": 0.21484375, "learning_rate": 1.6979503203916755e-05, "loss": 0.2512688934803009, "step": 854 }, { "epoch": 0.5544747081712063, "grad_norm": 0.208984375, "learning_rate": 1.6971977323946273e-05, "loss": 0.24122266471385956, "step": 855 }, { "epoch": 0.5551232166018158, "grad_norm": 0.23046875, "learning_rate": 1.6964443752266787e-05, "loss": 0.2502886652946472, "step": 856 }, { "epoch": 0.5557717250324254, "grad_norm": 0.2119140625, "learning_rate": 1.695690249718958e-05, "loss": 0.2380983829498291, "step": 857 }, { "epoch": 0.556420233463035, "grad_norm": 0.2099609375, "learning_rate": 1.69493535670344e-05, "loss": 0.2564305067062378, "step": 858 }, { "epoch": 0.5570687418936446, "grad_norm": 0.2294921875, "learning_rate": 1.6941796970129477e-05, "loss": 0.246547669172287, "step": 859 }, { "epoch": 0.5577172503242542, "grad_norm": 0.21484375, "learning_rate": 1.6934232714811486e-05, "loss": 0.2500418424606323, "step": 860 }, { "epoch": 0.5583657587548638, "grad_norm": 0.2021484375, "learning_rate": 1.6926660809425554e-05, "loss": 0.22617794573307037, "step": 861 }, { "epoch": 0.5590142671854734, "grad_norm": 0.224609375, "learning_rate": 1.6919081262325257e-05, "loss": 0.24113288521766663, "step": 862 }, { "epoch": 0.559662775616083, "grad_norm": 0.2099609375, "learning_rate": 1.6911494081872588e-05, "loss": 0.237762913107872, "step": 863 }, { "epoch": 0.5603112840466926, "grad_norm": 0.20703125, "learning_rate": 1.690389927643797e-05, "loss": 0.24261987209320068, "step": 864 }, { "epoch": 0.5609597924773022, "grad_norm": 0.2080078125, "learning_rate": 1.6896296854400242e-05, "loss": 0.24458621442317963, "step": 865 }, { "epoch": 0.5616083009079118, "grad_norm": 0.25390625, "learning_rate": 1.6888686824146627e-05, "loss": 0.2588699162006378, "step": 866 }, { "epoch": 0.5622568093385214, "grad_norm": 0.2099609375, "learning_rate": 1.688106919407276e-05, "loss": 0.2398909628391266, "step": 867 }, { "epoch": 0.562905317769131, "grad_norm": 0.2041015625, "learning_rate": 1.6873443972582662e-05, "loss": 0.24092964828014374, "step": 868 }, { "epoch": 0.5635538261997406, "grad_norm": 0.21875, "learning_rate": 1.6865811168088715e-05, "loss": 0.23532766103744507, "step": 869 }, { "epoch": 0.5642023346303502, "grad_norm": 0.23046875, "learning_rate": 1.6858170789011673e-05, "loss": 0.24494582414627075, "step": 870 }, { "epoch": 0.5648508430609598, "grad_norm": 0.203125, "learning_rate": 1.685052284378065e-05, "loss": 0.23574741184711456, "step": 871 }, { "epoch": 0.5654993514915694, "grad_norm": 0.2119140625, "learning_rate": 1.6842867340833106e-05, "loss": 0.2533760368824005, "step": 872 }, { "epoch": 0.566147859922179, "grad_norm": 0.2265625, "learning_rate": 1.683520428861483e-05, "loss": 0.25927090644836426, "step": 873 }, { "epoch": 0.5667963683527886, "grad_norm": 0.2001953125, "learning_rate": 1.6827533695579958e-05, "loss": 0.23820379376411438, "step": 874 }, { "epoch": 0.5674448767833982, "grad_norm": 0.205078125, "learning_rate": 1.6819855570190923e-05, "loss": 0.2488861382007599, "step": 875 }, { "epoch": 0.5680933852140078, "grad_norm": 0.2119140625, "learning_rate": 1.6812169920918486e-05, "loss": 0.2422334849834442, "step": 876 }, { "epoch": 0.5687418936446174, "grad_norm": 0.2138671875, "learning_rate": 1.68044767562417e-05, "loss": 0.25252050161361694, "step": 877 }, { "epoch": 0.569390402075227, "grad_norm": 0.2021484375, "learning_rate": 1.6796776084647915e-05, "loss": 0.2371557652950287, "step": 878 }, { "epoch": 0.5700389105058365, "grad_norm": 0.2197265625, "learning_rate": 1.678906791463275e-05, "loss": 0.2525731325149536, "step": 879 }, { "epoch": 0.5706874189364461, "grad_norm": 0.1962890625, "learning_rate": 1.6781352254700114e-05, "loss": 0.2461223304271698, "step": 880 }, { "epoch": 0.5713359273670557, "grad_norm": 0.216796875, "learning_rate": 1.6773629113362167e-05, "loss": 0.23937997221946716, "step": 881 }, { "epoch": 0.5719844357976653, "grad_norm": 0.20703125, "learning_rate": 1.6765898499139327e-05, "loss": 0.24828499555587769, "step": 882 }, { "epoch": 0.5726329442282749, "grad_norm": 0.2255859375, "learning_rate": 1.6758160420560253e-05, "loss": 0.2394510805606842, "step": 883 }, { "epoch": 0.5732814526588845, "grad_norm": 0.216796875, "learning_rate": 1.6750414886161844e-05, "loss": 0.2649855315685272, "step": 884 }, { "epoch": 0.5739299610894941, "grad_norm": 0.2119140625, "learning_rate": 1.674266190448922e-05, "loss": 0.23506863415241241, "step": 885 }, { "epoch": 0.5745784695201037, "grad_norm": 0.216796875, "learning_rate": 1.6734901484095722e-05, "loss": 0.2537495493888855, "step": 886 }, { "epoch": 0.5752269779507133, "grad_norm": 0.2255859375, "learning_rate": 1.6727133633542892e-05, "loss": 0.25819021463394165, "step": 887 }, { "epoch": 0.5758754863813229, "grad_norm": 0.208984375, "learning_rate": 1.6719358361400474e-05, "loss": 0.22767531871795654, "step": 888 }, { "epoch": 0.5765239948119325, "grad_norm": 0.2158203125, "learning_rate": 1.6711575676246398e-05, "loss": 0.231440007686615, "step": 889 }, { "epoch": 0.5771725032425421, "grad_norm": 0.201171875, "learning_rate": 1.670378558666677e-05, "loss": 0.2477472722530365, "step": 890 }, { "epoch": 0.5778210116731517, "grad_norm": 0.236328125, "learning_rate": 1.6695988101255865e-05, "loss": 0.2643510103225708, "step": 891 }, { "epoch": 0.5784695201037614, "grad_norm": 0.21875, "learning_rate": 1.668818322861612e-05, "loss": 0.25123530626296997, "step": 892 }, { "epoch": 0.579118028534371, "grad_norm": 0.212890625, "learning_rate": 1.6680370977358126e-05, "loss": 0.2710804343223572, "step": 893 }, { "epoch": 0.5797665369649806, "grad_norm": 0.2109375, "learning_rate": 1.6672551356100603e-05, "loss": 0.24202676117420197, "step": 894 }, { "epoch": 0.5804150453955902, "grad_norm": 0.2021484375, "learning_rate": 1.666472437347041e-05, "loss": 0.24139884114265442, "step": 895 }, { "epoch": 0.5810635538261998, "grad_norm": 0.2177734375, "learning_rate": 1.6656890038102526e-05, "loss": 0.26074016094207764, "step": 896 }, { "epoch": 0.5817120622568094, "grad_norm": 0.2099609375, "learning_rate": 1.664904835864004e-05, "loss": 0.24852514266967773, "step": 897 }, { "epoch": 0.582360570687419, "grad_norm": 0.2001953125, "learning_rate": 1.6641199343734142e-05, "loss": 0.22754469513893127, "step": 898 }, { "epoch": 0.5830090791180286, "grad_norm": 0.2275390625, "learning_rate": 1.6633343002044124e-05, "loss": 0.25681132078170776, "step": 899 }, { "epoch": 0.5836575875486382, "grad_norm": 0.2265625, "learning_rate": 1.6625479342237348e-05, "loss": 0.23638150095939636, "step": 900 }, { "epoch": 0.5843060959792478, "grad_norm": 0.22265625, "learning_rate": 1.6617608372989258e-05, "loss": 0.2735379934310913, "step": 901 }, { "epoch": 0.5849546044098574, "grad_norm": 0.220703125, "learning_rate": 1.660973010298336e-05, "loss": 0.26309484243392944, "step": 902 }, { "epoch": 0.585603112840467, "grad_norm": 0.2236328125, "learning_rate": 1.660184454091121e-05, "loss": 0.2643967270851135, "step": 903 }, { "epoch": 0.5862516212710766, "grad_norm": 0.2109375, "learning_rate": 1.659395169547242e-05, "loss": 0.23725301027297974, "step": 904 }, { "epoch": 0.5869001297016861, "grad_norm": 0.2216796875, "learning_rate": 1.6586051575374624e-05, "loss": 0.22938942909240723, "step": 905 }, { "epoch": 0.5875486381322957, "grad_norm": 0.2060546875, "learning_rate": 1.6578144189333494e-05, "loss": 0.24473069608211517, "step": 906 }, { "epoch": 0.5881971465629053, "grad_norm": 0.2177734375, "learning_rate": 1.6570229546072707e-05, "loss": 0.24889063835144043, "step": 907 }, { "epoch": 0.5888456549935149, "grad_norm": 0.2080078125, "learning_rate": 1.656230765432395e-05, "loss": 0.25221115350723267, "step": 908 }, { "epoch": 0.5894941634241245, "grad_norm": 0.25, "learning_rate": 1.6554378522826918e-05, "loss": 0.2419426292181015, "step": 909 }, { "epoch": 0.5901426718547341, "grad_norm": 0.212890625, "learning_rate": 1.654644216032927e-05, "loss": 0.25629162788391113, "step": 910 }, { "epoch": 0.5907911802853437, "grad_norm": 0.2197265625, "learning_rate": 1.6538498575586662e-05, "loss": 0.2606733441352844, "step": 911 }, { "epoch": 0.5914396887159533, "grad_norm": 0.228515625, "learning_rate": 1.653054777736271e-05, "loss": 0.25323033332824707, "step": 912 }, { "epoch": 0.5920881971465629, "grad_norm": 0.2275390625, "learning_rate": 1.6522589774428993e-05, "loss": 0.24328389763832092, "step": 913 }, { "epoch": 0.5927367055771725, "grad_norm": 0.2216796875, "learning_rate": 1.6514624575565035e-05, "loss": 0.24086147546768188, "step": 914 }, { "epoch": 0.5933852140077821, "grad_norm": 0.23828125, "learning_rate": 1.650665218955829e-05, "loss": 0.23695909976959229, "step": 915 }, { "epoch": 0.5940337224383917, "grad_norm": 0.24609375, "learning_rate": 1.6498672625204165e-05, "loss": 0.24361476302146912, "step": 916 }, { "epoch": 0.5946822308690013, "grad_norm": 0.21875, "learning_rate": 1.6490685891305957e-05, "loss": 0.23210017383098602, "step": 917 }, { "epoch": 0.5953307392996109, "grad_norm": 0.2412109375, "learning_rate": 1.6482691996674896e-05, "loss": 0.23873919248580933, "step": 918 }, { "epoch": 0.5959792477302205, "grad_norm": 0.2353515625, "learning_rate": 1.64746909501301e-05, "loss": 0.24996428191661835, "step": 919 }, { "epoch": 0.5966277561608301, "grad_norm": 0.2294921875, "learning_rate": 1.6466682760498578e-05, "loss": 0.24698016047477722, "step": 920 }, { "epoch": 0.5972762645914397, "grad_norm": 0.2314453125, "learning_rate": 1.6458667436615227e-05, "loss": 0.25858718156814575, "step": 921 }, { "epoch": 0.5979247730220493, "grad_norm": 0.21875, "learning_rate": 1.64506449873228e-05, "loss": 0.25404664874076843, "step": 922 }, { "epoch": 0.5985732814526589, "grad_norm": 0.2265625, "learning_rate": 1.644261542147193e-05, "loss": 0.24432627856731415, "step": 923 }, { "epoch": 0.5992217898832685, "grad_norm": 0.2177734375, "learning_rate": 1.6434578747921087e-05, "loss": 0.25290077924728394, "step": 924 }, { "epoch": 0.5998702983138781, "grad_norm": 0.2197265625, "learning_rate": 1.6426534975536593e-05, "loss": 0.25577667355537415, "step": 925 }, { "epoch": 0.6005188067444877, "grad_norm": 0.22265625, "learning_rate": 1.641848411319259e-05, "loss": 0.25071048736572266, "step": 926 }, { "epoch": 0.6011673151750972, "grad_norm": 0.205078125, "learning_rate": 1.6410426169771043e-05, "loss": 0.2417571097612381, "step": 927 }, { "epoch": 0.6018158236057068, "grad_norm": 0.2373046875, "learning_rate": 1.6402361154161742e-05, "loss": 0.2351555973291397, "step": 928 }, { "epoch": 0.6024643320363164, "grad_norm": 0.203125, "learning_rate": 1.6394289075262265e-05, "loss": 0.23941874504089355, "step": 929 }, { "epoch": 0.603112840466926, "grad_norm": 0.2060546875, "learning_rate": 1.6386209941977992e-05, "loss": 0.22745655477046967, "step": 930 }, { "epoch": 0.6037613488975356, "grad_norm": 0.212890625, "learning_rate": 1.6378123763222084e-05, "loss": 0.24072733521461487, "step": 931 }, { "epoch": 0.6044098573281452, "grad_norm": 0.234375, "learning_rate": 1.637003054791547e-05, "loss": 0.25102531909942627, "step": 932 }, { "epoch": 0.6050583657587548, "grad_norm": 0.2177734375, "learning_rate": 1.6361930304986846e-05, "loss": 0.24363845586776733, "step": 933 }, { "epoch": 0.6057068741893644, "grad_norm": 0.2431640625, "learning_rate": 1.6353823043372656e-05, "loss": 0.2514728903770447, "step": 934 }, { "epoch": 0.606355382619974, "grad_norm": 0.2138671875, "learning_rate": 1.6345708772017094e-05, "loss": 0.2561870813369751, "step": 935 }, { "epoch": 0.6070038910505836, "grad_norm": 0.205078125, "learning_rate": 1.6337587499872085e-05, "loss": 0.2306516468524933, "step": 936 }, { "epoch": 0.6076523994811932, "grad_norm": 0.1962890625, "learning_rate": 1.632945923589727e-05, "loss": 0.23316578567028046, "step": 937 }, { "epoch": 0.6083009079118028, "grad_norm": 0.201171875, "learning_rate": 1.6321323989060022e-05, "loss": 0.23764556646347046, "step": 938 }, { "epoch": 0.6089494163424124, "grad_norm": 0.2392578125, "learning_rate": 1.6313181768335397e-05, "loss": 0.24057886004447937, "step": 939 }, { "epoch": 0.6095979247730221, "grad_norm": 0.2177734375, "learning_rate": 1.6305032582706163e-05, "loss": 0.2430863380432129, "step": 940 }, { "epoch": 0.6102464332036317, "grad_norm": 0.2216796875, "learning_rate": 1.6296876441162752e-05, "loss": 0.25168585777282715, "step": 941 }, { "epoch": 0.6108949416342413, "grad_norm": 0.244140625, "learning_rate": 1.628871335270329e-05, "loss": 0.26666826009750366, "step": 942 }, { "epoch": 0.6115434500648509, "grad_norm": 0.224609375, "learning_rate": 1.6280543326333553e-05, "loss": 0.2578209638595581, "step": 943 }, { "epoch": 0.6121919584954605, "grad_norm": 0.2158203125, "learning_rate": 1.627236637106698e-05, "loss": 0.2298002541065216, "step": 944 }, { "epoch": 0.6128404669260701, "grad_norm": 0.263671875, "learning_rate": 1.6264182495924648e-05, "loss": 0.2266928106546402, "step": 945 }, { "epoch": 0.6134889753566797, "grad_norm": 0.1962890625, "learning_rate": 1.6255991709935268e-05, "loss": 0.24492314457893372, "step": 946 }, { "epoch": 0.6141374837872893, "grad_norm": 0.20703125, "learning_rate": 1.624779402213518e-05, "loss": 0.2477463334798813, "step": 947 }, { "epoch": 0.6147859922178989, "grad_norm": 0.20703125, "learning_rate": 1.6239589441568338e-05, "loss": 0.25315093994140625, "step": 948 }, { "epoch": 0.6154345006485085, "grad_norm": 0.205078125, "learning_rate": 1.6231377977286298e-05, "loss": 0.22410587966442108, "step": 949 }, { "epoch": 0.6160830090791181, "grad_norm": 0.212890625, "learning_rate": 1.622315963834821e-05, "loss": 0.24820604920387268, "step": 950 }, { "epoch": 0.6167315175097277, "grad_norm": 0.26953125, "learning_rate": 1.6214934433820805e-05, "loss": 0.24918755888938904, "step": 951 }, { "epoch": 0.6173800259403373, "grad_norm": 0.203125, "learning_rate": 1.6206702372778398e-05, "loss": 0.23209059238433838, "step": 952 }, { "epoch": 0.6180285343709468, "grad_norm": 0.224609375, "learning_rate": 1.619846346430286e-05, "loss": 0.2538565695285797, "step": 953 }, { "epoch": 0.6186770428015564, "grad_norm": 0.224609375, "learning_rate": 1.619021771748362e-05, "loss": 0.24861663579940796, "step": 954 }, { "epoch": 0.619325551232166, "grad_norm": 0.216796875, "learning_rate": 1.6181965141417656e-05, "loss": 0.24744021892547607, "step": 955 }, { "epoch": 0.6199740596627756, "grad_norm": 0.2119140625, "learning_rate": 1.6173705745209464e-05, "loss": 0.25656771659851074, "step": 956 }, { "epoch": 0.6206225680933852, "grad_norm": 0.21875, "learning_rate": 1.6165439537971082e-05, "loss": 0.23495203256607056, "step": 957 }, { "epoch": 0.6212710765239948, "grad_norm": 0.19140625, "learning_rate": 1.615716652882205e-05, "loss": 0.22860679030418396, "step": 958 }, { "epoch": 0.6219195849546044, "grad_norm": 0.201171875, "learning_rate": 1.614888672688942e-05, "loss": 0.23767365515232086, "step": 959 }, { "epoch": 0.622568093385214, "grad_norm": 0.244140625, "learning_rate": 1.6140600141307738e-05, "loss": 0.252236932516098, "step": 960 }, { "epoch": 0.6232166018158236, "grad_norm": 0.1962890625, "learning_rate": 1.613230678121903e-05, "loss": 0.2317807525396347, "step": 961 }, { "epoch": 0.6238651102464332, "grad_norm": 0.203125, "learning_rate": 1.612400665577279e-05, "loss": 0.23425838351249695, "step": 962 }, { "epoch": 0.6245136186770428, "grad_norm": 0.2294921875, "learning_rate": 1.611569977412599e-05, "loss": 0.24979113042354584, "step": 963 }, { "epoch": 0.6251621271076524, "grad_norm": 0.2021484375, "learning_rate": 1.6107386145443044e-05, "loss": 0.22391779720783234, "step": 964 }, { "epoch": 0.625810635538262, "grad_norm": 0.2021484375, "learning_rate": 1.609906577889582e-05, "loss": 0.23095038533210754, "step": 965 }, { "epoch": 0.6264591439688716, "grad_norm": 0.212890625, "learning_rate": 1.6090738683663598e-05, "loss": 0.24096065759658813, "step": 966 }, { "epoch": 0.6271076523994812, "grad_norm": 0.224609375, "learning_rate": 1.6082404868933114e-05, "loss": 0.2564721405506134, "step": 967 }, { "epoch": 0.6277561608300908, "grad_norm": 0.2294921875, "learning_rate": 1.6074064343898494e-05, "loss": 0.27196916937828064, "step": 968 }, { "epoch": 0.6284046692607004, "grad_norm": 0.234375, "learning_rate": 1.606571711776127e-05, "loss": 0.2635185122489929, "step": 969 }, { "epoch": 0.62905317769131, "grad_norm": 0.208984375, "learning_rate": 1.6057363199730374e-05, "loss": 0.24167633056640625, "step": 970 }, { "epoch": 0.6297016861219196, "grad_norm": 0.2041015625, "learning_rate": 1.604900259902211e-05, "loss": 0.24424105882644653, "step": 971 }, { "epoch": 0.6303501945525292, "grad_norm": 0.2109375, "learning_rate": 1.6040635324860167e-05, "loss": 0.23373281955718994, "step": 972 }, { "epoch": 0.6309987029831388, "grad_norm": 0.23828125, "learning_rate": 1.6032261386475586e-05, "loss": 0.24833741784095764, "step": 973 }, { "epoch": 0.6316472114137484, "grad_norm": 0.2236328125, "learning_rate": 1.6023880793106767e-05, "loss": 0.2330552488565445, "step": 974 }, { "epoch": 0.632295719844358, "grad_norm": 0.205078125, "learning_rate": 1.601549355399945e-05, "loss": 0.24411743879318237, "step": 975 }, { "epoch": 0.6329442282749675, "grad_norm": 0.208984375, "learning_rate": 1.60070996784067e-05, "loss": 0.2550343871116638, "step": 976 }, { "epoch": 0.6335927367055771, "grad_norm": 0.19921875, "learning_rate": 1.5998699175588917e-05, "loss": 0.2517588436603546, "step": 977 }, { "epoch": 0.6342412451361867, "grad_norm": 0.212890625, "learning_rate": 1.5990292054813802e-05, "loss": 0.252142995595932, "step": 978 }, { "epoch": 0.6348897535667963, "grad_norm": 0.2216796875, "learning_rate": 1.5981878325356363e-05, "loss": 0.26113659143447876, "step": 979 }, { "epoch": 0.6355382619974059, "grad_norm": 0.2138671875, "learning_rate": 1.5973457996498895e-05, "loss": 0.23606835305690765, "step": 980 }, { "epoch": 0.6361867704280155, "grad_norm": 0.2099609375, "learning_rate": 1.596503107753097e-05, "loss": 0.24093079566955566, "step": 981 }, { "epoch": 0.6368352788586251, "grad_norm": 0.2197265625, "learning_rate": 1.595659757774944e-05, "loss": 0.25118762254714966, "step": 982 }, { "epoch": 0.6374837872892347, "grad_norm": 0.21484375, "learning_rate": 1.5948157506458414e-05, "loss": 0.24482783675193787, "step": 983 }, { "epoch": 0.6381322957198443, "grad_norm": 0.22265625, "learning_rate": 1.593971087296925e-05, "loss": 0.25862377882003784, "step": 984 }, { "epoch": 0.6387808041504539, "grad_norm": 0.21484375, "learning_rate": 1.5931257686600533e-05, "loss": 0.2673421800136566, "step": 985 }, { "epoch": 0.6394293125810635, "grad_norm": 0.2060546875, "learning_rate": 1.5922797956678104e-05, "loss": 0.236227884888649, "step": 986 }, { "epoch": 0.6400778210116731, "grad_norm": 0.2158203125, "learning_rate": 1.5914331692535004e-05, "loss": 0.26872777938842773, "step": 987 }, { "epoch": 0.6407263294422828, "grad_norm": 0.1923828125, "learning_rate": 1.5905858903511483e-05, "loss": 0.24116933345794678, "step": 988 }, { "epoch": 0.6413748378728924, "grad_norm": 0.208984375, "learning_rate": 1.5897379598954995e-05, "loss": 0.24039828777313232, "step": 989 }, { "epoch": 0.642023346303502, "grad_norm": 0.228515625, "learning_rate": 1.5888893788220187e-05, "loss": 0.23400892317295074, "step": 990 }, { "epoch": 0.6426718547341116, "grad_norm": 0.2119140625, "learning_rate": 1.5880401480668874e-05, "loss": 0.22052066028118134, "step": 991 }, { "epoch": 0.6433203631647212, "grad_norm": 0.21875, "learning_rate": 1.5871902685670035e-05, "loss": 0.2549007534980774, "step": 992 }, { "epoch": 0.6439688715953308, "grad_norm": 0.212890625, "learning_rate": 1.586339741259982e-05, "loss": 0.24077144265174866, "step": 993 }, { "epoch": 0.6446173800259404, "grad_norm": 0.26953125, "learning_rate": 1.585488567084152e-05, "loss": 0.26484382152557373, "step": 994 }, { "epoch": 0.64526588845655, "grad_norm": 0.216796875, "learning_rate": 1.584636746978556e-05, "loss": 0.23701173067092896, "step": 995 }, { "epoch": 0.6459143968871596, "grad_norm": 0.2001953125, "learning_rate": 1.5837842818829492e-05, "loss": 0.23978611826896667, "step": 996 }, { "epoch": 0.6465629053177692, "grad_norm": 0.21875, "learning_rate": 1.5829311727377984e-05, "loss": 0.25713050365448, "step": 997 }, { "epoch": 0.6472114137483788, "grad_norm": 0.248046875, "learning_rate": 1.582077420484281e-05, "loss": 0.24291223287582397, "step": 998 }, { "epoch": 0.6478599221789884, "grad_norm": 0.19921875, "learning_rate": 1.5812230260642842e-05, "loss": 0.22655750811100006, "step": 999 }, { "epoch": 0.648508430609598, "grad_norm": 0.2373046875, "learning_rate": 1.5803679904204027e-05, "loss": 0.24812042713165283, "step": 1000 }, { "epoch": 0.6491569390402075, "grad_norm": 0.24609375, "learning_rate": 1.5795123144959396e-05, "loss": 0.2401857078075409, "step": 1001 }, { "epoch": 0.6498054474708171, "grad_norm": 0.2177734375, "learning_rate": 1.5786559992349042e-05, "loss": 0.26080623269081116, "step": 1002 }, { "epoch": 0.6504539559014267, "grad_norm": 0.240234375, "learning_rate": 1.5777990455820104e-05, "loss": 0.26343584060668945, "step": 1003 }, { "epoch": 0.6511024643320363, "grad_norm": 0.2041015625, "learning_rate": 1.5769414544826777e-05, "loss": 0.23838604986667633, "step": 1004 }, { "epoch": 0.6517509727626459, "grad_norm": 0.2080078125, "learning_rate": 1.5760832268830277e-05, "loss": 0.24723772704601288, "step": 1005 }, { "epoch": 0.6523994811932555, "grad_norm": 0.228515625, "learning_rate": 1.5752243637298844e-05, "loss": 0.24971215426921844, "step": 1006 }, { "epoch": 0.6530479896238651, "grad_norm": 0.20703125, "learning_rate": 1.574364865970774e-05, "loss": 0.24666659533977509, "step": 1007 }, { "epoch": 0.6536964980544747, "grad_norm": 0.2392578125, "learning_rate": 1.5735047345539206e-05, "loss": 0.2503644526004791, "step": 1008 }, { "epoch": 0.6543450064850843, "grad_norm": 0.2001953125, "learning_rate": 1.57264397042825e-05, "loss": 0.22295141220092773, "step": 1009 }, { "epoch": 0.6549935149156939, "grad_norm": 0.21484375, "learning_rate": 1.5717825745433848e-05, "loss": 0.26306670904159546, "step": 1010 }, { "epoch": 0.6556420233463035, "grad_norm": 0.2197265625, "learning_rate": 1.5709205478496436e-05, "loss": 0.2389674186706543, "step": 1011 }, { "epoch": 0.6562905317769131, "grad_norm": 0.25390625, "learning_rate": 1.5700578912980425e-05, "loss": 0.2550007998943329, "step": 1012 }, { "epoch": 0.6569390402075227, "grad_norm": 0.234375, "learning_rate": 1.569194605840292e-05, "loss": 0.24747136235237122, "step": 1013 }, { "epoch": 0.6575875486381323, "grad_norm": 0.2109375, "learning_rate": 1.568330692428796e-05, "loss": 0.23528584837913513, "step": 1014 }, { "epoch": 0.6582360570687419, "grad_norm": 0.212890625, "learning_rate": 1.5674661520166515e-05, "loss": 0.24975493550300598, "step": 1015 }, { "epoch": 0.6588845654993515, "grad_norm": 0.203125, "learning_rate": 1.566600985557647e-05, "loss": 0.2330969274044037, "step": 1016 }, { "epoch": 0.6595330739299611, "grad_norm": 0.21875, "learning_rate": 1.565735194006263e-05, "loss": 0.24115385115146637, "step": 1017 }, { "epoch": 0.6601815823605707, "grad_norm": 0.20703125, "learning_rate": 1.564868778317667e-05, "loss": 0.23121526837348938, "step": 1018 }, { "epoch": 0.6608300907911803, "grad_norm": 0.2138671875, "learning_rate": 1.5640017394477178e-05, "loss": 0.25866633653640747, "step": 1019 }, { "epoch": 0.6614785992217899, "grad_norm": 0.2177734375, "learning_rate": 1.56313407835296e-05, "loss": 0.2552535831928253, "step": 1020 }, { "epoch": 0.6621271076523995, "grad_norm": 0.2255859375, "learning_rate": 1.5622657959906248e-05, "loss": 0.2605186104774475, "step": 1021 }, { "epoch": 0.6627756160830091, "grad_norm": 0.201171875, "learning_rate": 1.5613968933186294e-05, "loss": 0.24104833602905273, "step": 1022 }, { "epoch": 0.6634241245136187, "grad_norm": 0.2041015625, "learning_rate": 1.5605273712955754e-05, "loss": 0.23090413212776184, "step": 1023 }, { "epoch": 0.6640726329442282, "grad_norm": 0.216796875, "learning_rate": 1.5596572308807473e-05, "loss": 0.24509474635124207, "step": 1024 }, { "epoch": 0.6647211413748378, "grad_norm": 0.203125, "learning_rate": 1.5587864730341116e-05, "loss": 0.22246524691581726, "step": 1025 }, { "epoch": 0.6653696498054474, "grad_norm": 0.220703125, "learning_rate": 1.5579150987163166e-05, "loss": 0.24175064265727997, "step": 1026 }, { "epoch": 0.666018158236057, "grad_norm": 0.203125, "learning_rate": 1.55704310888869e-05, "loss": 0.23722146451473236, "step": 1027 }, { "epoch": 0.6666666666666666, "grad_norm": 0.2119140625, "learning_rate": 1.5561705045132393e-05, "loss": 0.2465820461511612, "step": 1028 }, { "epoch": 0.6673151750972762, "grad_norm": 0.2138671875, "learning_rate": 1.5552972865526497e-05, "loss": 0.2562980651855469, "step": 1029 }, { "epoch": 0.6679636835278858, "grad_norm": 0.2080078125, "learning_rate": 1.554423455970283e-05, "loss": 0.2358611524105072, "step": 1030 }, { "epoch": 0.6686121919584954, "grad_norm": 0.23046875, "learning_rate": 1.553549013730177e-05, "loss": 0.23255601525306702, "step": 1031 }, { "epoch": 0.669260700389105, "grad_norm": 0.2109375, "learning_rate": 1.5526739607970446e-05, "loss": 0.25363093614578247, "step": 1032 }, { "epoch": 0.6699092088197146, "grad_norm": 0.22265625, "learning_rate": 1.551798298136273e-05, "loss": 0.25353097915649414, "step": 1033 }, { "epoch": 0.6705577172503242, "grad_norm": 0.2041015625, "learning_rate": 1.55092202671392e-05, "loss": 0.23048332333564758, "step": 1034 }, { "epoch": 0.6712062256809338, "grad_norm": 0.2392578125, "learning_rate": 1.5500451474967174e-05, "loss": 0.25789695978164673, "step": 1035 }, { "epoch": 0.6718547341115434, "grad_norm": 0.2099609375, "learning_rate": 1.549167661452066e-05, "loss": 0.2564896047115326, "step": 1036 }, { "epoch": 0.6725032425421531, "grad_norm": 0.2197265625, "learning_rate": 1.5482895695480362e-05, "loss": 0.24368982017040253, "step": 1037 }, { "epoch": 0.6731517509727627, "grad_norm": 0.205078125, "learning_rate": 1.5474108727533678e-05, "loss": 0.25381791591644287, "step": 1038 }, { "epoch": 0.6738002594033723, "grad_norm": 0.2236328125, "learning_rate": 1.546531572037467e-05, "loss": 0.2507246434688568, "step": 1039 }, { "epoch": 0.6744487678339819, "grad_norm": 0.2177734375, "learning_rate": 1.5456516683704067e-05, "loss": 0.25004440546035767, "step": 1040 }, { "epoch": 0.6750972762645915, "grad_norm": 0.20703125, "learning_rate": 1.544771162722925e-05, "loss": 0.22876980900764465, "step": 1041 }, { "epoch": 0.6757457846952011, "grad_norm": 0.203125, "learning_rate": 1.5438900560664232e-05, "loss": 0.24831464886665344, "step": 1042 }, { "epoch": 0.6763942931258107, "grad_norm": 0.20703125, "learning_rate": 1.5430083493729674e-05, "loss": 0.2504825294017792, "step": 1043 }, { "epoch": 0.6770428015564203, "grad_norm": 0.2353515625, "learning_rate": 1.542126043615284e-05, "loss": 0.2515137195587158, "step": 1044 }, { "epoch": 0.6776913099870299, "grad_norm": 0.236328125, "learning_rate": 1.541243139766761e-05, "loss": 0.23138058185577393, "step": 1045 }, { "epoch": 0.6783398184176395, "grad_norm": 0.20703125, "learning_rate": 1.5403596388014472e-05, "loss": 0.24187029898166656, "step": 1046 }, { "epoch": 0.6789883268482491, "grad_norm": 0.205078125, "learning_rate": 1.539475541694048e-05, "loss": 0.24560734629631042, "step": 1047 }, { "epoch": 0.6796368352788587, "grad_norm": 0.19921875, "learning_rate": 1.5385908494199282e-05, "loss": 0.23160380125045776, "step": 1048 }, { "epoch": 0.6802853437094682, "grad_norm": 0.208984375, "learning_rate": 1.5377055629551088e-05, "loss": 0.24524863064289093, "step": 1049 }, { "epoch": 0.6809338521400778, "grad_norm": 0.2109375, "learning_rate": 1.5368196832762663e-05, "loss": 0.2585134208202362, "step": 1050 }, { "epoch": 0.6815823605706874, "grad_norm": 0.2041015625, "learning_rate": 1.535933211360731e-05, "loss": 0.2424941062927246, "step": 1051 }, { "epoch": 0.682230869001297, "grad_norm": 0.2041015625, "learning_rate": 1.5350461481864875e-05, "loss": 0.24960201978683472, "step": 1052 }, { "epoch": 0.6828793774319066, "grad_norm": 0.212890625, "learning_rate": 1.5341584947321728e-05, "loss": 0.2471892237663269, "step": 1053 }, { "epoch": 0.6835278858625162, "grad_norm": 0.19921875, "learning_rate": 1.5332702519770738e-05, "loss": 0.24612781405448914, "step": 1054 }, { "epoch": 0.6841763942931258, "grad_norm": 0.2216796875, "learning_rate": 1.5323814209011294e-05, "loss": 0.25724560022354126, "step": 1055 }, { "epoch": 0.6848249027237354, "grad_norm": 0.24609375, "learning_rate": 1.531492002484926e-05, "loss": 0.22893445193767548, "step": 1056 }, { "epoch": 0.685473411154345, "grad_norm": 0.201171875, "learning_rate": 1.5306019977096975e-05, "loss": 0.22114534676074982, "step": 1057 }, { "epoch": 0.6861219195849546, "grad_norm": 0.2216796875, "learning_rate": 1.5297114075573274e-05, "loss": 0.2378731369972229, "step": 1058 }, { "epoch": 0.6867704280155642, "grad_norm": 0.2177734375, "learning_rate": 1.5288202330103426e-05, "loss": 0.22106698155403137, "step": 1059 }, { "epoch": 0.6874189364461738, "grad_norm": 0.2138671875, "learning_rate": 1.5279284750519158e-05, "loss": 0.23315545916557312, "step": 1060 }, { "epoch": 0.6880674448767834, "grad_norm": 0.2236328125, "learning_rate": 1.527036134665862e-05, "loss": 0.2361375093460083, "step": 1061 }, { "epoch": 0.688715953307393, "grad_norm": 0.23046875, "learning_rate": 1.5261432128366407e-05, "loss": 0.22495751082897186, "step": 1062 }, { "epoch": 0.6893644617380026, "grad_norm": 0.232421875, "learning_rate": 1.525249710549352e-05, "loss": 0.24723400175571442, "step": 1063 }, { "epoch": 0.6900129701686122, "grad_norm": 0.2099609375, "learning_rate": 1.5243556287897355e-05, "loss": 0.24925045669078827, "step": 1064 }, { "epoch": 0.6906614785992218, "grad_norm": 0.2197265625, "learning_rate": 1.5234609685441712e-05, "loss": 0.2540687918663025, "step": 1065 }, { "epoch": 0.6913099870298314, "grad_norm": 0.236328125, "learning_rate": 1.5225657307996771e-05, "loss": 0.25700825452804565, "step": 1066 }, { "epoch": 0.691958495460441, "grad_norm": 0.2255859375, "learning_rate": 1.5216699165439082e-05, "loss": 0.24329723417758942, "step": 1067 }, { "epoch": 0.6926070038910506, "grad_norm": 0.2060546875, "learning_rate": 1.5207735267651553e-05, "loss": 0.24940873682498932, "step": 1068 }, { "epoch": 0.6932555123216602, "grad_norm": 0.2021484375, "learning_rate": 1.5198765624523448e-05, "loss": 0.2479928731918335, "step": 1069 }, { "epoch": 0.6939040207522698, "grad_norm": 0.2138671875, "learning_rate": 1.5189790245950362e-05, "loss": 0.2497437298297882, "step": 1070 }, { "epoch": 0.6945525291828794, "grad_norm": 0.2099609375, "learning_rate": 1.5180809141834219e-05, "loss": 0.23261414468288422, "step": 1071 }, { "epoch": 0.695201037613489, "grad_norm": 0.203125, "learning_rate": 1.5171822322083261e-05, "loss": 0.23651325702667236, "step": 1072 }, { "epoch": 0.6958495460440985, "grad_norm": 0.203125, "learning_rate": 1.5162829796612038e-05, "loss": 0.2304183542728424, "step": 1073 }, { "epoch": 0.6964980544747081, "grad_norm": 0.216796875, "learning_rate": 1.5153831575341395e-05, "loss": 0.24368254840373993, "step": 1074 }, { "epoch": 0.6971465629053177, "grad_norm": 0.208984375, "learning_rate": 1.5144827668198452e-05, "loss": 0.24891029298305511, "step": 1075 }, { "epoch": 0.6977950713359273, "grad_norm": 0.208984375, "learning_rate": 1.5135818085116612e-05, "loss": 0.22879308462142944, "step": 1076 }, { "epoch": 0.6984435797665369, "grad_norm": 0.2001953125, "learning_rate": 1.5126802836035537e-05, "loss": 0.23864015936851501, "step": 1077 }, { "epoch": 0.6990920881971465, "grad_norm": 0.2080078125, "learning_rate": 1.5117781930901134e-05, "loss": 0.2392130047082901, "step": 1078 }, { "epoch": 0.6997405966277561, "grad_norm": 0.19921875, "learning_rate": 1.5108755379665563e-05, "loss": 0.223332941532135, "step": 1079 }, { "epoch": 0.7003891050583657, "grad_norm": 0.2099609375, "learning_rate": 1.5099723192287199e-05, "loss": 0.24604745209217072, "step": 1080 }, { "epoch": 0.7010376134889753, "grad_norm": 0.2080078125, "learning_rate": 1.509068537873064e-05, "loss": 0.23165613412857056, "step": 1081 }, { "epoch": 0.7016861219195849, "grad_norm": 0.201171875, "learning_rate": 1.5081641948966697e-05, "loss": 0.24316132068634033, "step": 1082 }, { "epoch": 0.7023346303501945, "grad_norm": 0.25, "learning_rate": 1.5072592912972363e-05, "loss": 0.24107664823532104, "step": 1083 }, { "epoch": 0.7029831387808041, "grad_norm": 0.208984375, "learning_rate": 1.5063538280730833e-05, "loss": 0.21770314872264862, "step": 1084 }, { "epoch": 0.7036316472114138, "grad_norm": 0.22265625, "learning_rate": 1.5054478062231466e-05, "loss": 0.24924351274967194, "step": 1085 }, { "epoch": 0.7042801556420234, "grad_norm": 0.2119140625, "learning_rate": 1.5045412267469784e-05, "loss": 0.270181268453598, "step": 1086 }, { "epoch": 0.704928664072633, "grad_norm": 0.203125, "learning_rate": 1.5036340906447465e-05, "loss": 0.2319694608449936, "step": 1087 }, { "epoch": 0.7055771725032426, "grad_norm": 0.2041015625, "learning_rate": 1.5027263989172323e-05, "loss": 0.24028530716896057, "step": 1088 }, { "epoch": 0.7062256809338522, "grad_norm": 0.212890625, "learning_rate": 1.5018181525658299e-05, "loss": 0.24851751327514648, "step": 1089 }, { "epoch": 0.7068741893644618, "grad_norm": 0.197265625, "learning_rate": 1.5009093525925468e-05, "loss": 0.24208742380142212, "step": 1090 }, { "epoch": 0.7075226977950714, "grad_norm": 0.1982421875, "learning_rate": 1.5000000000000002e-05, "loss": 0.23976564407348633, "step": 1091 }, { "epoch": 0.708171206225681, "grad_norm": 0.203125, "learning_rate": 1.4990900957914165e-05, "loss": 0.23169094324111938, "step": 1092 }, { "epoch": 0.7088197146562906, "grad_norm": 0.21875, "learning_rate": 1.4981796409706313e-05, "loss": 0.2505793273448944, "step": 1093 }, { "epoch": 0.7094682230869002, "grad_norm": 0.234375, "learning_rate": 1.4972686365420877e-05, "loss": 0.24731498956680298, "step": 1094 }, { "epoch": 0.7101167315175098, "grad_norm": 0.197265625, "learning_rate": 1.496357083510835e-05, "loss": 0.22742053866386414, "step": 1095 }, { "epoch": 0.7107652399481194, "grad_norm": 0.2158203125, "learning_rate": 1.4954449828825277e-05, "loss": 0.25650885701179504, "step": 1096 }, { "epoch": 0.711413748378729, "grad_norm": 0.20703125, "learning_rate": 1.4945323356634248e-05, "loss": 0.2382233440876007, "step": 1097 }, { "epoch": 0.7120622568093385, "grad_norm": 0.216796875, "learning_rate": 1.4936191428603875e-05, "loss": 0.24704119563102722, "step": 1098 }, { "epoch": 0.7127107652399481, "grad_norm": 0.2080078125, "learning_rate": 1.4927054054808792e-05, "loss": 0.2417505979537964, "step": 1099 }, { "epoch": 0.7133592736705577, "grad_norm": 0.2099609375, "learning_rate": 1.491791124532965e-05, "loss": 0.24265319108963013, "step": 1100 }, { "epoch": 0.7140077821011673, "grad_norm": 0.201171875, "learning_rate": 1.4908763010253087e-05, "loss": 0.24794936180114746, "step": 1101 }, { "epoch": 0.7146562905317769, "grad_norm": 0.1953125, "learning_rate": 1.4899609359671724e-05, "loss": 0.22145724296569824, "step": 1102 }, { "epoch": 0.7153047989623865, "grad_norm": 0.205078125, "learning_rate": 1.4890450303684172e-05, "loss": 0.24929514527320862, "step": 1103 }, { "epoch": 0.7159533073929961, "grad_norm": 0.21484375, "learning_rate": 1.488128585239499e-05, "loss": 0.24464420974254608, "step": 1104 }, { "epoch": 0.7166018158236057, "grad_norm": 0.208984375, "learning_rate": 1.4872116015914688e-05, "loss": 0.238031804561615, "step": 1105 }, { "epoch": 0.7172503242542153, "grad_norm": 0.1943359375, "learning_rate": 1.4862940804359736e-05, "loss": 0.2344008982181549, "step": 1106 }, { "epoch": 0.7178988326848249, "grad_norm": 0.2109375, "learning_rate": 1.4853760227852514e-05, "loss": 0.2407316267490387, "step": 1107 }, { "epoch": 0.7185473411154345, "grad_norm": 0.20703125, "learning_rate": 1.484457429652133e-05, "loss": 0.2554226517677307, "step": 1108 }, { "epoch": 0.7191958495460441, "grad_norm": 0.216796875, "learning_rate": 1.48353830205004e-05, "loss": 0.2454633116722107, "step": 1109 }, { "epoch": 0.7198443579766537, "grad_norm": 0.2109375, "learning_rate": 1.482618640992983e-05, "loss": 0.23796170949935913, "step": 1110 }, { "epoch": 0.7204928664072633, "grad_norm": 0.2001953125, "learning_rate": 1.4816984474955617e-05, "loss": 0.24305769801139832, "step": 1111 }, { "epoch": 0.7211413748378729, "grad_norm": 0.2021484375, "learning_rate": 1.4807777225729638e-05, "loss": 0.23890580236911774, "step": 1112 }, { "epoch": 0.7217898832684825, "grad_norm": 0.2021484375, "learning_rate": 1.4798564672409618e-05, "loss": 0.24372133612632751, "step": 1113 }, { "epoch": 0.7224383916990921, "grad_norm": 0.2099609375, "learning_rate": 1.4789346825159143e-05, "loss": 0.24207955598831177, "step": 1114 }, { "epoch": 0.7230869001297017, "grad_norm": 0.201171875, "learning_rate": 1.4780123694147636e-05, "loss": 0.2532508671283722, "step": 1115 }, { "epoch": 0.7237354085603113, "grad_norm": 0.2158203125, "learning_rate": 1.4770895289550358e-05, "loss": 0.23976026475429535, "step": 1116 }, { "epoch": 0.7243839169909209, "grad_norm": 0.2099609375, "learning_rate": 1.4761661621548373e-05, "loss": 0.24064187705516815, "step": 1117 }, { "epoch": 0.7250324254215305, "grad_norm": 0.208984375, "learning_rate": 1.4752422700328562e-05, "loss": 0.2499132603406906, "step": 1118 }, { "epoch": 0.72568093385214, "grad_norm": 0.1943359375, "learning_rate": 1.4743178536083603e-05, "loss": 0.23140263557434082, "step": 1119 }, { "epoch": 0.7263294422827496, "grad_norm": 0.22265625, "learning_rate": 1.4733929139011944e-05, "loss": 0.25613880157470703, "step": 1120 }, { "epoch": 0.7269779507133592, "grad_norm": 0.21875, "learning_rate": 1.472467451931783e-05, "loss": 0.2628932595252991, "step": 1121 }, { "epoch": 0.7276264591439688, "grad_norm": 0.2197265625, "learning_rate": 1.4715414687211247e-05, "loss": 0.24071671068668365, "step": 1122 }, { "epoch": 0.7282749675745784, "grad_norm": 0.1904296875, "learning_rate": 1.470614965290794e-05, "loss": 0.22492963075637817, "step": 1123 }, { "epoch": 0.728923476005188, "grad_norm": 0.224609375, "learning_rate": 1.4696879426629393e-05, "loss": 0.2598830461502075, "step": 1124 }, { "epoch": 0.7295719844357976, "grad_norm": 0.19140625, "learning_rate": 1.4687604018602814e-05, "loss": 0.23324376344680786, "step": 1125 }, { "epoch": 0.7302204928664072, "grad_norm": 0.205078125, "learning_rate": 1.4678323439061133e-05, "loss": 0.2521976828575134, "step": 1126 }, { "epoch": 0.7308690012970168, "grad_norm": 0.20703125, "learning_rate": 1.4669037698242985e-05, "loss": 0.22464221715927124, "step": 1127 }, { "epoch": 0.7315175097276264, "grad_norm": 0.201171875, "learning_rate": 1.4659746806392691e-05, "loss": 0.244516983628273, "step": 1128 }, { "epoch": 0.732166018158236, "grad_norm": 0.2001953125, "learning_rate": 1.4650450773760265e-05, "loss": 0.26360440254211426, "step": 1129 }, { "epoch": 0.7328145265888456, "grad_norm": 0.189453125, "learning_rate": 1.4641149610601391e-05, "loss": 0.2330702692270279, "step": 1130 }, { "epoch": 0.7334630350194552, "grad_norm": 0.216796875, "learning_rate": 1.4631843327177405e-05, "loss": 0.23268386721611023, "step": 1131 }, { "epoch": 0.7341115434500648, "grad_norm": 0.2041015625, "learning_rate": 1.46225319337553e-05, "loss": 0.25410595536231995, "step": 1132 }, { "epoch": 0.7347600518806745, "grad_norm": 0.1904296875, "learning_rate": 1.4613215440607705e-05, "loss": 0.23102620244026184, "step": 1133 }, { "epoch": 0.7354085603112841, "grad_norm": 0.2236328125, "learning_rate": 1.4603893858012873e-05, "loss": 0.2390480786561966, "step": 1134 }, { "epoch": 0.7360570687418937, "grad_norm": 0.216796875, "learning_rate": 1.459456719625467e-05, "loss": 0.2563648223876953, "step": 1135 }, { "epoch": 0.7367055771725033, "grad_norm": 0.2041015625, "learning_rate": 1.458523546562257e-05, "loss": 0.2347560077905655, "step": 1136 }, { "epoch": 0.7373540856031129, "grad_norm": 0.1904296875, "learning_rate": 1.4575898676411643e-05, "loss": 0.22800175845623016, "step": 1137 }, { "epoch": 0.7380025940337225, "grad_norm": 0.203125, "learning_rate": 1.4566556838922526e-05, "loss": 0.23707500100135803, "step": 1138 }, { "epoch": 0.7386511024643321, "grad_norm": 0.1982421875, "learning_rate": 1.455720996346144e-05, "loss": 0.22214768826961517, "step": 1139 }, { "epoch": 0.7392996108949417, "grad_norm": 0.1875, "learning_rate": 1.4547858060340154e-05, "loss": 0.22250284254550934, "step": 1140 }, { "epoch": 0.7399481193255513, "grad_norm": 0.2060546875, "learning_rate": 1.4538501139875991e-05, "loss": 0.24481134116649628, "step": 1141 }, { "epoch": 0.7405966277561609, "grad_norm": 0.1962890625, "learning_rate": 1.4529139212391803e-05, "loss": 0.22954976558685303, "step": 1142 }, { "epoch": 0.7412451361867705, "grad_norm": 0.19921875, "learning_rate": 1.4519772288215967e-05, "loss": 0.23866605758666992, "step": 1143 }, { "epoch": 0.74189364461738, "grad_norm": 0.193359375, "learning_rate": 1.4510400377682378e-05, "loss": 0.223214253783226, "step": 1144 }, { "epoch": 0.7425421530479897, "grad_norm": 0.1953125, "learning_rate": 1.4501023491130428e-05, "loss": 0.2506139874458313, "step": 1145 }, { "epoch": 0.7431906614785992, "grad_norm": 0.1962890625, "learning_rate": 1.4491641638904996e-05, "loss": 0.22874194383621216, "step": 1146 }, { "epoch": 0.7438391699092088, "grad_norm": 0.197265625, "learning_rate": 1.4482254831356444e-05, "loss": 0.24326549470424652, "step": 1147 }, { "epoch": 0.7444876783398184, "grad_norm": 0.208984375, "learning_rate": 1.4472863078840602e-05, "loss": 0.23088383674621582, "step": 1148 }, { "epoch": 0.745136186770428, "grad_norm": 0.2197265625, "learning_rate": 1.4463466391718748e-05, "loss": 0.23228448629379272, "step": 1149 }, { "epoch": 0.7457846952010376, "grad_norm": 0.2265625, "learning_rate": 1.4454064780357611e-05, "loss": 0.23310664296150208, "step": 1150 }, { "epoch": 0.7464332036316472, "grad_norm": 0.208984375, "learning_rate": 1.4444658255129349e-05, "loss": 0.21661987900733948, "step": 1151 }, { "epoch": 0.7470817120622568, "grad_norm": 0.2236328125, "learning_rate": 1.4435246826411542e-05, "loss": 0.24868598580360413, "step": 1152 }, { "epoch": 0.7477302204928664, "grad_norm": 0.228515625, "learning_rate": 1.4425830504587183e-05, "loss": 0.24837586283683777, "step": 1153 }, { "epoch": 0.748378728923476, "grad_norm": 0.2109375, "learning_rate": 1.4416409300044658e-05, "loss": 0.249412402510643, "step": 1154 }, { "epoch": 0.7490272373540856, "grad_norm": 0.2099609375, "learning_rate": 1.4406983223177742e-05, "loss": 0.2388565093278885, "step": 1155 }, { "epoch": 0.7496757457846952, "grad_norm": 0.19921875, "learning_rate": 1.4397552284385586e-05, "loss": 0.23758858442306519, "step": 1156 }, { "epoch": 0.7503242542153048, "grad_norm": 0.20703125, "learning_rate": 1.4388116494072701e-05, "loss": 0.24787436425685883, "step": 1157 }, { "epoch": 0.7509727626459144, "grad_norm": 0.2021484375, "learning_rate": 1.4378675862648959e-05, "loss": 0.2325928658246994, "step": 1158 }, { "epoch": 0.751621271076524, "grad_norm": 0.197265625, "learning_rate": 1.4369230400529563e-05, "loss": 0.2421104907989502, "step": 1159 }, { "epoch": 0.7522697795071336, "grad_norm": 0.2255859375, "learning_rate": 1.4359780118135055e-05, "loss": 0.24455508589744568, "step": 1160 }, { "epoch": 0.7529182879377432, "grad_norm": 0.208984375, "learning_rate": 1.4350325025891285e-05, "loss": 0.22812843322753906, "step": 1161 }, { "epoch": 0.7535667963683528, "grad_norm": 0.1982421875, "learning_rate": 1.4340865134229412e-05, "loss": 0.2402144819498062, "step": 1162 }, { "epoch": 0.7542153047989624, "grad_norm": 0.205078125, "learning_rate": 1.4331400453585897e-05, "loss": 0.2275409996509552, "step": 1163 }, { "epoch": 0.754863813229572, "grad_norm": 0.2158203125, "learning_rate": 1.432193099440248e-05, "loss": 0.25028443336486816, "step": 1164 }, { "epoch": 0.7555123216601816, "grad_norm": 0.2080078125, "learning_rate": 1.4312456767126163e-05, "loss": 0.24327081441879272, "step": 1165 }, { "epoch": 0.7561608300907912, "grad_norm": 0.19921875, "learning_rate": 1.4302977782209228e-05, "loss": 0.26442751288414, "step": 1166 }, { "epoch": 0.7568093385214008, "grad_norm": 0.1982421875, "learning_rate": 1.4293494050109192e-05, "loss": 0.2385459840297699, "step": 1167 }, { "epoch": 0.7574578469520103, "grad_norm": 0.19921875, "learning_rate": 1.428400558128881e-05, "loss": 0.24077251553535461, "step": 1168 }, { "epoch": 0.75810635538262, "grad_norm": 0.2177734375, "learning_rate": 1.4274512386216065e-05, "loss": 0.23472771048545837, "step": 1169 }, { "epoch": 0.7587548638132295, "grad_norm": 0.208984375, "learning_rate": 1.4265014475364156e-05, "loss": 0.23935218155384064, "step": 1170 }, { "epoch": 0.7594033722438391, "grad_norm": 0.26171875, "learning_rate": 1.4255511859211486e-05, "loss": 0.2401164025068283, "step": 1171 }, { "epoch": 0.7600518806744487, "grad_norm": 0.216796875, "learning_rate": 1.4246004548241641e-05, "loss": 0.25283247232437134, "step": 1172 }, { "epoch": 0.7607003891050583, "grad_norm": 0.2021484375, "learning_rate": 1.423649255294339e-05, "loss": 0.2448616921901703, "step": 1173 }, { "epoch": 0.7613488975356679, "grad_norm": 0.19140625, "learning_rate": 1.4226975883810677e-05, "loss": 0.23736709356307983, "step": 1174 }, { "epoch": 0.7619974059662775, "grad_norm": 0.2197265625, "learning_rate": 1.4217454551342593e-05, "loss": 0.25324538350105286, "step": 1175 }, { "epoch": 0.7626459143968871, "grad_norm": 0.2109375, "learning_rate": 1.4207928566043379e-05, "loss": 0.24701756238937378, "step": 1176 }, { "epoch": 0.7632944228274967, "grad_norm": 0.208984375, "learning_rate": 1.4198397938422408e-05, "loss": 0.2420937567949295, "step": 1177 }, { "epoch": 0.7639429312581063, "grad_norm": 0.2373046875, "learning_rate": 1.4188862678994174e-05, "loss": 0.2278125286102295, "step": 1178 }, { "epoch": 0.7645914396887159, "grad_norm": 0.193359375, "learning_rate": 1.4179322798278275e-05, "loss": 0.22286386787891388, "step": 1179 }, { "epoch": 0.7652399481193255, "grad_norm": 0.2109375, "learning_rate": 1.4169778306799422e-05, "loss": 0.2328663021326065, "step": 1180 }, { "epoch": 0.7658884565499352, "grad_norm": 0.2099609375, "learning_rate": 1.41602292150874e-05, "loss": 0.22531378269195557, "step": 1181 }, { "epoch": 0.7665369649805448, "grad_norm": 0.212890625, "learning_rate": 1.4150675533677074e-05, "loss": 0.2514967918395996, "step": 1182 }, { "epoch": 0.7671854734111544, "grad_norm": 0.2080078125, "learning_rate": 1.4141117273108366e-05, "loss": 0.24470169842243195, "step": 1183 }, { "epoch": 0.767833981841764, "grad_norm": 0.2138671875, "learning_rate": 1.4131554443926266e-05, "loss": 0.22688905894756317, "step": 1184 }, { "epoch": 0.7684824902723736, "grad_norm": 0.2060546875, "learning_rate": 1.4121987056680788e-05, "loss": 0.2280483841896057, "step": 1185 }, { "epoch": 0.7691309987029832, "grad_norm": 0.2216796875, "learning_rate": 1.4112415121926983e-05, "loss": 0.2480226457118988, "step": 1186 }, { "epoch": 0.7697795071335928, "grad_norm": 0.1982421875, "learning_rate": 1.4102838650224915e-05, "loss": 0.24018071591854095, "step": 1187 }, { "epoch": 0.7704280155642024, "grad_norm": 0.2080078125, "learning_rate": 1.4093257652139653e-05, "loss": 0.25391000509262085, "step": 1188 }, { "epoch": 0.771076523994812, "grad_norm": 0.205078125, "learning_rate": 1.4083672138241263e-05, "loss": 0.2294105589389801, "step": 1189 }, { "epoch": 0.7717250324254216, "grad_norm": 0.2138671875, "learning_rate": 1.4074082119104793e-05, "loss": 0.25561997294425964, "step": 1190 }, { "epoch": 0.7723735408560312, "grad_norm": 0.208984375, "learning_rate": 1.4064487605310258e-05, "loss": 0.23002278804779053, "step": 1191 }, { "epoch": 0.7730220492866408, "grad_norm": 0.2216796875, "learning_rate": 1.405488860744263e-05, "loss": 0.24242472648620605, "step": 1192 }, { "epoch": 0.7736705577172504, "grad_norm": 0.2041015625, "learning_rate": 1.4045285136091838e-05, "loss": 0.23505809903144836, "step": 1193 }, { "epoch": 0.77431906614786, "grad_norm": 0.205078125, "learning_rate": 1.4035677201852736e-05, "loss": 0.23934566974639893, "step": 1194 }, { "epoch": 0.7749675745784695, "grad_norm": 0.208984375, "learning_rate": 1.4026064815325102e-05, "loss": 0.23741719126701355, "step": 1195 }, { "epoch": 0.7756160830090791, "grad_norm": 0.212890625, "learning_rate": 1.4016447987113635e-05, "loss": 0.22820980846881866, "step": 1196 }, { "epoch": 0.7762645914396887, "grad_norm": 0.220703125, "learning_rate": 1.400682672782793e-05, "loss": 0.24550655484199524, "step": 1197 }, { "epoch": 0.7769130998702983, "grad_norm": 0.201171875, "learning_rate": 1.399720104808246e-05, "loss": 0.22550266981124878, "step": 1198 }, { "epoch": 0.7775616083009079, "grad_norm": 0.21484375, "learning_rate": 1.3987570958496589e-05, "loss": 0.24413764476776123, "step": 1199 }, { "epoch": 0.7782101167315175, "grad_norm": 0.1982421875, "learning_rate": 1.3977936469694542e-05, "loss": 0.22118057310581207, "step": 1200 }, { "epoch": 0.7788586251621271, "grad_norm": 0.205078125, "learning_rate": 1.3968297592305391e-05, "loss": 0.22883647680282593, "step": 1201 }, { "epoch": 0.7795071335927367, "grad_norm": 0.201171875, "learning_rate": 1.395865433696306e-05, "loss": 0.25093817710876465, "step": 1202 }, { "epoch": 0.7801556420233463, "grad_norm": 0.1875, "learning_rate": 1.3949006714306297e-05, "loss": 0.21710696816444397, "step": 1203 }, { "epoch": 0.7808041504539559, "grad_norm": 0.2275390625, "learning_rate": 1.3939354734978665e-05, "loss": 0.24694989621639252, "step": 1204 }, { "epoch": 0.7814526588845655, "grad_norm": 0.20703125, "learning_rate": 1.3929698409628541e-05, "loss": 0.24508020281791687, "step": 1205 }, { "epoch": 0.7821011673151751, "grad_norm": 0.203125, "learning_rate": 1.392003774890909e-05, "loss": 0.2339121401309967, "step": 1206 }, { "epoch": 0.7827496757457847, "grad_norm": 0.2275390625, "learning_rate": 1.3910372763478263e-05, "loss": 0.22121059894561768, "step": 1207 }, { "epoch": 0.7833981841763943, "grad_norm": 0.19921875, "learning_rate": 1.3900703463998786e-05, "loss": 0.2374008595943451, "step": 1208 }, { "epoch": 0.7840466926070039, "grad_norm": 0.1982421875, "learning_rate": 1.3891029861138137e-05, "loss": 0.21340766549110413, "step": 1209 }, { "epoch": 0.7846952010376135, "grad_norm": 0.22265625, "learning_rate": 1.3881351965568542e-05, "loss": 0.24233976006507874, "step": 1210 }, { "epoch": 0.7853437094682231, "grad_norm": 0.2060546875, "learning_rate": 1.3871669787966968e-05, "loss": 0.2479827105998993, "step": 1211 }, { "epoch": 0.7859922178988327, "grad_norm": 0.20703125, "learning_rate": 1.386198333901511e-05, "loss": 0.25009965896606445, "step": 1212 }, { "epoch": 0.7866407263294423, "grad_norm": 0.2060546875, "learning_rate": 1.3852292629399362e-05, "loss": 0.24756011366844177, "step": 1213 }, { "epoch": 0.7872892347600519, "grad_norm": 0.2265625, "learning_rate": 1.384259766981083e-05, "loss": 0.23961769044399261, "step": 1214 }, { "epoch": 0.7879377431906615, "grad_norm": 0.2119140625, "learning_rate": 1.3832898470945298e-05, "loss": 0.23670747876167297, "step": 1215 }, { "epoch": 0.788586251621271, "grad_norm": 0.2001953125, "learning_rate": 1.3823195043503237e-05, "loss": 0.22920732200145721, "step": 1216 }, { "epoch": 0.7892347600518806, "grad_norm": 0.2138671875, "learning_rate": 1.3813487398189784e-05, "loss": 0.23541462421417236, "step": 1217 }, { "epoch": 0.7898832684824902, "grad_norm": 0.2060546875, "learning_rate": 1.3803775545714717e-05, "loss": 0.25698041915893555, "step": 1218 }, { "epoch": 0.7905317769130998, "grad_norm": 0.201171875, "learning_rate": 1.3794059496792469e-05, "loss": 0.24195370078086853, "step": 1219 }, { "epoch": 0.7911802853437094, "grad_norm": 0.2197265625, "learning_rate": 1.3784339262142092e-05, "loss": 0.23997701704502106, "step": 1220 }, { "epoch": 0.791828793774319, "grad_norm": 0.205078125, "learning_rate": 1.3774614852487262e-05, "loss": 0.2332383543252945, "step": 1221 }, { "epoch": 0.7924773022049286, "grad_norm": 0.2041015625, "learning_rate": 1.3764886278556264e-05, "loss": 0.22908632457256317, "step": 1222 }, { "epoch": 0.7931258106355382, "grad_norm": 0.2001953125, "learning_rate": 1.3755153551081968e-05, "loss": 0.2304653823375702, "step": 1223 }, { "epoch": 0.7937743190661478, "grad_norm": 0.2080078125, "learning_rate": 1.3745416680801835e-05, "loss": 0.24463587999343872, "step": 1224 }, { "epoch": 0.7944228274967574, "grad_norm": 0.1923828125, "learning_rate": 1.3735675678457886e-05, "loss": 0.22454363107681274, "step": 1225 }, { "epoch": 0.795071335927367, "grad_norm": 0.2177734375, "learning_rate": 1.3725930554796713e-05, "loss": 0.24397879838943481, "step": 1226 }, { "epoch": 0.7957198443579766, "grad_norm": 0.2265625, "learning_rate": 1.3716181320569448e-05, "loss": 0.23877134919166565, "step": 1227 }, { "epoch": 0.7963683527885862, "grad_norm": 0.2158203125, "learning_rate": 1.3706427986531759e-05, "loss": 0.2599659264087677, "step": 1228 }, { "epoch": 0.7970168612191959, "grad_norm": 0.2001953125, "learning_rate": 1.3696670563443833e-05, "loss": 0.23403674364089966, "step": 1229 }, { "epoch": 0.7976653696498055, "grad_norm": 0.1982421875, "learning_rate": 1.3686909062070377e-05, "loss": 0.22922232747077942, "step": 1230 }, { "epoch": 0.7983138780804151, "grad_norm": 0.1982421875, "learning_rate": 1.3677143493180589e-05, "loss": 0.24412491917610168, "step": 1231 }, { "epoch": 0.7989623865110247, "grad_norm": 0.203125, "learning_rate": 1.3667373867548162e-05, "loss": 0.23881417512893677, "step": 1232 }, { "epoch": 0.7996108949416343, "grad_norm": 0.2080078125, "learning_rate": 1.3657600195951256e-05, "loss": 0.22995254397392273, "step": 1233 }, { "epoch": 0.8002594033722439, "grad_norm": 0.1982421875, "learning_rate": 1.3647822489172505e-05, "loss": 0.2539726495742798, "step": 1234 }, { "epoch": 0.8009079118028535, "grad_norm": 0.208984375, "learning_rate": 1.363804075799898e-05, "loss": 0.23886165022850037, "step": 1235 }, { "epoch": 0.8015564202334631, "grad_norm": 0.2060546875, "learning_rate": 1.3628255013222206e-05, "loss": 0.24868306517601013, "step": 1236 }, { "epoch": 0.8022049286640727, "grad_norm": 0.193359375, "learning_rate": 1.361846526563813e-05, "loss": 0.23268838226795197, "step": 1237 }, { "epoch": 0.8028534370946823, "grad_norm": 0.212890625, "learning_rate": 1.3608671526047115e-05, "loss": 0.2679118514060974, "step": 1238 }, { "epoch": 0.8035019455252919, "grad_norm": 0.2109375, "learning_rate": 1.3598873805253927e-05, "loss": 0.2387547791004181, "step": 1239 }, { "epoch": 0.8041504539559015, "grad_norm": 0.1962890625, "learning_rate": 1.3589072114067732e-05, "loss": 0.23748889565467834, "step": 1240 }, { "epoch": 0.804798962386511, "grad_norm": 0.2041015625, "learning_rate": 1.3579266463302063e-05, "loss": 0.24385850131511688, "step": 1241 }, { "epoch": 0.8054474708171206, "grad_norm": 0.2021484375, "learning_rate": 1.356945686377483e-05, "loss": 0.23088158667087555, "step": 1242 }, { "epoch": 0.8060959792477302, "grad_norm": 0.2119140625, "learning_rate": 1.35596433263083e-05, "loss": 0.22159135341644287, "step": 1243 }, { "epoch": 0.8067444876783398, "grad_norm": 0.21484375, "learning_rate": 1.3549825861729083e-05, "loss": 0.22597172856330872, "step": 1244 }, { "epoch": 0.8073929961089494, "grad_norm": 0.2060546875, "learning_rate": 1.3540004480868119e-05, "loss": 0.24597719311714172, "step": 1245 }, { "epoch": 0.808041504539559, "grad_norm": 0.2021484375, "learning_rate": 1.3530179194560668e-05, "loss": 0.23260916769504547, "step": 1246 }, { "epoch": 0.8086900129701686, "grad_norm": 0.1904296875, "learning_rate": 1.3520350013646304e-05, "loss": 0.22312740981578827, "step": 1247 }, { "epoch": 0.8093385214007782, "grad_norm": 0.1982421875, "learning_rate": 1.3510516948968893e-05, "loss": 0.24379070103168488, "step": 1248 }, { "epoch": 0.8099870298313878, "grad_norm": 0.1875, "learning_rate": 1.350068001137659e-05, "loss": 0.22774359583854675, "step": 1249 }, { "epoch": 0.8106355382619974, "grad_norm": 0.2041015625, "learning_rate": 1.349083921172182e-05, "loss": 0.24756315350532532, "step": 1250 }, { "epoch": 0.811284046692607, "grad_norm": 0.1953125, "learning_rate": 1.3480994560861267e-05, "loss": 0.24051818251609802, "step": 1251 }, { "epoch": 0.8119325551232166, "grad_norm": 0.205078125, "learning_rate": 1.3471146069655862e-05, "loss": 0.22485780715942383, "step": 1252 }, { "epoch": 0.8125810635538262, "grad_norm": 0.2138671875, "learning_rate": 1.3461293748970783e-05, "loss": 0.2418041229248047, "step": 1253 }, { "epoch": 0.8132295719844358, "grad_norm": 0.205078125, "learning_rate": 1.3451437609675424e-05, "loss": 0.23893660306930542, "step": 1254 }, { "epoch": 0.8138780804150454, "grad_norm": 0.240234375, "learning_rate": 1.3441577662643393e-05, "loss": 0.2563047409057617, "step": 1255 }, { "epoch": 0.814526588845655, "grad_norm": 0.189453125, "learning_rate": 1.3431713918752499e-05, "loss": 0.21974045038223267, "step": 1256 }, { "epoch": 0.8151750972762646, "grad_norm": 0.263671875, "learning_rate": 1.3421846388884742e-05, "loss": 0.25775837898254395, "step": 1257 }, { "epoch": 0.8158236057068742, "grad_norm": 0.208984375, "learning_rate": 1.3411975083926296e-05, "loss": 0.23737657070159912, "step": 1258 }, { "epoch": 0.8164721141374838, "grad_norm": 0.189453125, "learning_rate": 1.3402100014767508e-05, "loss": 0.2242875099182129, "step": 1259 }, { "epoch": 0.8171206225680934, "grad_norm": 0.21875, "learning_rate": 1.3392221192302862e-05, "loss": 0.2366115152835846, "step": 1260 }, { "epoch": 0.817769130998703, "grad_norm": 0.216796875, "learning_rate": 1.3382338627430995e-05, "loss": 0.25378477573394775, "step": 1261 }, { "epoch": 0.8184176394293126, "grad_norm": 0.2001953125, "learning_rate": 1.337245233105467e-05, "loss": 0.2256709635257721, "step": 1262 }, { "epoch": 0.8190661478599222, "grad_norm": 0.208984375, "learning_rate": 1.3362562314080765e-05, "loss": 0.22477035224437714, "step": 1263 }, { "epoch": 0.8197146562905318, "grad_norm": 0.2001953125, "learning_rate": 1.3352668587420267e-05, "loss": 0.2229248285293579, "step": 1264 }, { "epoch": 0.8203631647211413, "grad_norm": 0.21484375, "learning_rate": 1.3342771161988249e-05, "loss": 0.24404467642307281, "step": 1265 }, { "epoch": 0.8210116731517509, "grad_norm": 0.2109375, "learning_rate": 1.3332870048703871e-05, "loss": 0.23871521651744843, "step": 1266 }, { "epoch": 0.8216601815823605, "grad_norm": 0.2197265625, "learning_rate": 1.332296525849036e-05, "loss": 0.2578944265842438, "step": 1267 }, { "epoch": 0.8223086900129701, "grad_norm": 0.2294921875, "learning_rate": 1.3313056802274989e-05, "loss": 0.2643631100654602, "step": 1268 }, { "epoch": 0.8229571984435797, "grad_norm": 0.2421875, "learning_rate": 1.3303144690989095e-05, "loss": 0.2430381178855896, "step": 1269 }, { "epoch": 0.8236057068741893, "grad_norm": 0.2041015625, "learning_rate": 1.3293228935568036e-05, "loss": 0.25373387336730957, "step": 1270 }, { "epoch": 0.8242542153047989, "grad_norm": 0.22265625, "learning_rate": 1.3283309546951188e-05, "loss": 0.2503284811973572, "step": 1271 }, { "epoch": 0.8249027237354085, "grad_norm": 0.2109375, "learning_rate": 1.327338653608194e-05, "loss": 0.23565617203712463, "step": 1272 }, { "epoch": 0.8255512321660181, "grad_norm": 0.2021484375, "learning_rate": 1.3263459913907673e-05, "loss": 0.23223067820072174, "step": 1273 }, { "epoch": 0.8261997405966277, "grad_norm": 0.21875, "learning_rate": 1.325352969137976e-05, "loss": 0.25427502393722534, "step": 1274 }, { "epoch": 0.8268482490272373, "grad_norm": 0.2158203125, "learning_rate": 1.3243595879453538e-05, "loss": 0.25811564922332764, "step": 1275 }, { "epoch": 0.8274967574578469, "grad_norm": 0.2158203125, "learning_rate": 1.3233658489088306e-05, "loss": 0.23822084069252014, "step": 1276 }, { "epoch": 0.8281452658884566, "grad_norm": 0.208984375, "learning_rate": 1.3223717531247316e-05, "loss": 0.25072136521339417, "step": 1277 }, { "epoch": 0.8287937743190662, "grad_norm": 0.23046875, "learning_rate": 1.3213773016897746e-05, "loss": 0.2317470908164978, "step": 1278 }, { "epoch": 0.8294422827496758, "grad_norm": 0.2001953125, "learning_rate": 1.3203824957010707e-05, "loss": 0.23256275057792664, "step": 1279 }, { "epoch": 0.8300907911802854, "grad_norm": 0.2109375, "learning_rate": 1.3193873362561217e-05, "loss": 0.2399323284626007, "step": 1280 }, { "epoch": 0.830739299610895, "grad_norm": 0.232421875, "learning_rate": 1.3183918244528193e-05, "loss": 0.23039120435714722, "step": 1281 }, { "epoch": 0.8313878080415046, "grad_norm": 0.1865234375, "learning_rate": 1.3173959613894443e-05, "loss": 0.2171938568353653, "step": 1282 }, { "epoch": 0.8320363164721142, "grad_norm": 0.1904296875, "learning_rate": 1.3163997481646644e-05, "loss": 0.23407676815986633, "step": 1283 }, { "epoch": 0.8326848249027238, "grad_norm": 0.22265625, "learning_rate": 1.3154031858775343e-05, "loss": 0.24379855394363403, "step": 1284 }, { "epoch": 0.8333333333333334, "grad_norm": 0.2041015625, "learning_rate": 1.3144062756274933e-05, "loss": 0.25516295433044434, "step": 1285 }, { "epoch": 0.833981841763943, "grad_norm": 0.1865234375, "learning_rate": 1.3134090185143648e-05, "loss": 0.22867891192436218, "step": 1286 }, { "epoch": 0.8346303501945526, "grad_norm": 0.2158203125, "learning_rate": 1.3124114156383551e-05, "loss": 0.26472315192222595, "step": 1287 }, { "epoch": 0.8352788586251622, "grad_norm": 0.2138671875, "learning_rate": 1.3114134681000514e-05, "loss": 0.23682279884815216, "step": 1288 }, { "epoch": 0.8359273670557718, "grad_norm": 0.21484375, "learning_rate": 1.3104151770004215e-05, "loss": 0.23471590876579285, "step": 1289 }, { "epoch": 0.8365758754863813, "grad_norm": 0.1982421875, "learning_rate": 1.309416543440812e-05, "loss": 0.24177376925945282, "step": 1290 }, { "epoch": 0.8372243839169909, "grad_norm": 0.20703125, "learning_rate": 1.3084175685229477e-05, "loss": 0.23791003227233887, "step": 1291 }, { "epoch": 0.8378728923476005, "grad_norm": 0.1923828125, "learning_rate": 1.3074182533489297e-05, "loss": 0.23256519436836243, "step": 1292 }, { "epoch": 0.8385214007782101, "grad_norm": 0.234375, "learning_rate": 1.3064185990212344e-05, "loss": 0.21784313023090363, "step": 1293 }, { "epoch": 0.8391699092088197, "grad_norm": 0.2392578125, "learning_rate": 1.305418606642713e-05, "loss": 0.22992035746574402, "step": 1294 }, { "epoch": 0.8398184176394293, "grad_norm": 0.2080078125, "learning_rate": 1.3044182773165883e-05, "loss": 0.23249870538711548, "step": 1295 }, { "epoch": 0.8404669260700389, "grad_norm": 0.1865234375, "learning_rate": 1.3034176121464568e-05, "loss": 0.2036076784133911, "step": 1296 }, { "epoch": 0.8411154345006485, "grad_norm": 0.208984375, "learning_rate": 1.3024166122362835e-05, "loss": 0.226297527551651, "step": 1297 }, { "epoch": 0.8417639429312581, "grad_norm": 0.2001953125, "learning_rate": 1.3014152786904042e-05, "loss": 0.23699961602687836, "step": 1298 }, { "epoch": 0.8424124513618677, "grad_norm": 0.2255859375, "learning_rate": 1.3004136126135213e-05, "loss": 0.23737524449825287, "step": 1299 }, { "epoch": 0.8430609597924773, "grad_norm": 0.21875, "learning_rate": 1.2994116151107061e-05, "loss": 0.25633901357650757, "step": 1300 }, { "epoch": 0.8437094682230869, "grad_norm": 0.2138671875, "learning_rate": 1.2984092872873937e-05, "loss": 0.23433026671409607, "step": 1301 }, { "epoch": 0.8443579766536965, "grad_norm": 0.2158203125, "learning_rate": 1.2974066302493846e-05, "loss": 0.23932671546936035, "step": 1302 }, { "epoch": 0.8450064850843061, "grad_norm": 0.228515625, "learning_rate": 1.296403645102842e-05, "loss": 0.24286824464797974, "step": 1303 }, { "epoch": 0.8456549935149157, "grad_norm": 0.1953125, "learning_rate": 1.2954003329542915e-05, "loss": 0.25161102414131165, "step": 1304 }, { "epoch": 0.8463035019455253, "grad_norm": 0.2177734375, "learning_rate": 1.2943966949106188e-05, "loss": 0.2369084656238556, "step": 1305 }, { "epoch": 0.8469520103761349, "grad_norm": 0.2216796875, "learning_rate": 1.2933927320790698e-05, "loss": 0.25047510862350464, "step": 1306 }, { "epoch": 0.8476005188067445, "grad_norm": 0.2138671875, "learning_rate": 1.2923884455672488e-05, "loss": 0.24543093144893646, "step": 1307 }, { "epoch": 0.8482490272373541, "grad_norm": 0.2138671875, "learning_rate": 1.2913838364831169e-05, "loss": 0.23756304383277893, "step": 1308 }, { "epoch": 0.8488975356679637, "grad_norm": 0.201171875, "learning_rate": 1.2903789059349903e-05, "loss": 0.23038998246192932, "step": 1309 }, { "epoch": 0.8495460440985733, "grad_norm": 0.193359375, "learning_rate": 1.2893736550315412e-05, "loss": 0.24138934910297394, "step": 1310 }, { "epoch": 0.8501945525291829, "grad_norm": 0.2099609375, "learning_rate": 1.2883680848817946e-05, "loss": 0.2259259968996048, "step": 1311 }, { "epoch": 0.8508430609597925, "grad_norm": 0.2265625, "learning_rate": 1.2873621965951278e-05, "loss": 0.23850002884864807, "step": 1312 }, { "epoch": 0.851491569390402, "grad_norm": 0.2041015625, "learning_rate": 1.286355991281269e-05, "loss": 0.24339675903320312, "step": 1313 }, { "epoch": 0.8521400778210116, "grad_norm": 0.23828125, "learning_rate": 1.2853494700502963e-05, "loss": 0.26608288288116455, "step": 1314 }, { "epoch": 0.8527885862516212, "grad_norm": 0.193359375, "learning_rate": 1.2843426340126355e-05, "loss": 0.2333861142396927, "step": 1315 }, { "epoch": 0.8534370946822308, "grad_norm": 0.240234375, "learning_rate": 1.283335484279061e-05, "loss": 0.2577156722545624, "step": 1316 }, { "epoch": 0.8540856031128404, "grad_norm": 0.1826171875, "learning_rate": 1.2823280219606929e-05, "loss": 0.22620806097984314, "step": 1317 }, { "epoch": 0.85473411154345, "grad_norm": 0.2041015625, "learning_rate": 1.2813202481689954e-05, "loss": 0.2249845564365387, "step": 1318 }, { "epoch": 0.8553826199740596, "grad_norm": 0.224609375, "learning_rate": 1.2803121640157773e-05, "loss": 0.25719451904296875, "step": 1319 }, { "epoch": 0.8560311284046692, "grad_norm": 0.1806640625, "learning_rate": 1.279303770613189e-05, "loss": 0.23608353734016418, "step": 1320 }, { "epoch": 0.8566796368352788, "grad_norm": 0.2109375, "learning_rate": 1.2782950690737228e-05, "loss": 0.22046442329883575, "step": 1321 }, { "epoch": 0.8573281452658884, "grad_norm": 0.1884765625, "learning_rate": 1.2772860605102104e-05, "loss": 0.2161683440208435, "step": 1322 }, { "epoch": 0.857976653696498, "grad_norm": 0.2001953125, "learning_rate": 1.2762767460358223e-05, "loss": 0.2216189205646515, "step": 1323 }, { "epoch": 0.8586251621271076, "grad_norm": 0.240234375, "learning_rate": 1.2752671267640671e-05, "loss": 0.2725641131401062, "step": 1324 }, { "epoch": 0.8592736705577172, "grad_norm": 0.2109375, "learning_rate": 1.2742572038087886e-05, "loss": 0.23875154554843903, "step": 1325 }, { "epoch": 0.8599221789883269, "grad_norm": 0.1904296875, "learning_rate": 1.273246978284166e-05, "loss": 0.22586576640605927, "step": 1326 }, { "epoch": 0.8605706874189365, "grad_norm": 0.2197265625, "learning_rate": 1.2722364513047135e-05, "loss": 0.23107826709747314, "step": 1327 }, { "epoch": 0.8612191958495461, "grad_norm": 0.201171875, "learning_rate": 1.2712256239852758e-05, "loss": 0.2371031641960144, "step": 1328 }, { "epoch": 0.8618677042801557, "grad_norm": 0.201171875, "learning_rate": 1.270214497441031e-05, "loss": 0.23200753331184387, "step": 1329 }, { "epoch": 0.8625162127107653, "grad_norm": 0.212890625, "learning_rate": 1.2692030727874853e-05, "loss": 0.244542196393013, "step": 1330 }, { "epoch": 0.8631647211413749, "grad_norm": 0.205078125, "learning_rate": 1.2681913511404758e-05, "loss": 0.23019364476203918, "step": 1331 }, { "epoch": 0.8638132295719845, "grad_norm": 0.2236328125, "learning_rate": 1.2671793336161653e-05, "loss": 0.2207522988319397, "step": 1332 }, { "epoch": 0.8644617380025941, "grad_norm": 0.228515625, "learning_rate": 1.2661670213310449e-05, "loss": 0.23804020881652832, "step": 1333 }, { "epoch": 0.8651102464332037, "grad_norm": 0.1884765625, "learning_rate": 1.2651544154019295e-05, "loss": 0.2265183925628662, "step": 1334 }, { "epoch": 0.8657587548638133, "grad_norm": 0.19140625, "learning_rate": 1.2641415169459585e-05, "loss": 0.22712449729442596, "step": 1335 }, { "epoch": 0.8664072632944229, "grad_norm": 0.2021484375, "learning_rate": 1.263128327080594e-05, "loss": 0.22147253155708313, "step": 1336 }, { "epoch": 0.8670557717250325, "grad_norm": 0.1806640625, "learning_rate": 1.2621148469236193e-05, "loss": 0.22175011038780212, "step": 1337 }, { "epoch": 0.867704280155642, "grad_norm": 0.1953125, "learning_rate": 1.2611010775931388e-05, "loss": 0.25160425901412964, "step": 1338 }, { "epoch": 0.8683527885862516, "grad_norm": 0.2060546875, "learning_rate": 1.260087020207575e-05, "loss": 0.23066404461860657, "step": 1339 }, { "epoch": 0.8690012970168612, "grad_norm": 0.2021484375, "learning_rate": 1.2590726758856686e-05, "loss": 0.23756031692028046, "step": 1340 }, { "epoch": 0.8696498054474708, "grad_norm": 0.201171875, "learning_rate": 1.2580580457464766e-05, "loss": 0.25139930844306946, "step": 1341 }, { "epoch": 0.8702983138780804, "grad_norm": 0.2021484375, "learning_rate": 1.2570431309093714e-05, "loss": 0.23599126935005188, "step": 1342 }, { "epoch": 0.87094682230869, "grad_norm": 0.224609375, "learning_rate": 1.2560279324940404e-05, "loss": 0.2510282099246979, "step": 1343 }, { "epoch": 0.8715953307392996, "grad_norm": 0.205078125, "learning_rate": 1.255012451620482e-05, "loss": 0.24565234780311584, "step": 1344 }, { "epoch": 0.8722438391699092, "grad_norm": 0.2001953125, "learning_rate": 1.2539966894090082e-05, "loss": 0.22181406617164612, "step": 1345 }, { "epoch": 0.8728923476005188, "grad_norm": 0.19140625, "learning_rate": 1.2529806469802392e-05, "loss": 0.21633070707321167, "step": 1346 }, { "epoch": 0.8735408560311284, "grad_norm": 0.2080078125, "learning_rate": 1.251964325455107e-05, "loss": 0.2420673966407776, "step": 1347 }, { "epoch": 0.874189364461738, "grad_norm": 0.2109375, "learning_rate": 1.2509477259548495e-05, "loss": 0.24417465925216675, "step": 1348 }, { "epoch": 0.8748378728923476, "grad_norm": 0.1953125, "learning_rate": 1.2499308496010118e-05, "loss": 0.2156796157360077, "step": 1349 }, { "epoch": 0.8754863813229572, "grad_norm": 0.201171875, "learning_rate": 1.2489136975154448e-05, "loss": 0.2314346730709076, "step": 1350 }, { "epoch": 0.8761348897535668, "grad_norm": 0.2001953125, "learning_rate": 1.247896270820303e-05, "loss": 0.2476593554019928, "step": 1351 }, { "epoch": 0.8767833981841764, "grad_norm": 0.1953125, "learning_rate": 1.246878570638044e-05, "loss": 0.2310778796672821, "step": 1352 }, { "epoch": 0.877431906614786, "grad_norm": 0.2138671875, "learning_rate": 1.2458605980914279e-05, "loss": 0.2367561310529709, "step": 1353 }, { "epoch": 0.8780804150453956, "grad_norm": 0.2578125, "learning_rate": 1.2448423543035142e-05, "loss": 0.22862094640731812, "step": 1354 }, { "epoch": 0.8787289234760052, "grad_norm": 0.2001953125, "learning_rate": 1.2438238403976619e-05, "loss": 0.22705036401748657, "step": 1355 }, { "epoch": 0.8793774319066148, "grad_norm": 0.20703125, "learning_rate": 1.242805057497529e-05, "loss": 0.2524130344390869, "step": 1356 }, { "epoch": 0.8800259403372244, "grad_norm": 0.1962890625, "learning_rate": 1.2417860067270688e-05, "loss": 0.23237645626068115, "step": 1357 }, { "epoch": 0.880674448767834, "grad_norm": 0.201171875, "learning_rate": 1.2407666892105309e-05, "loss": 0.24902065098285675, "step": 1358 }, { "epoch": 0.8813229571984436, "grad_norm": 0.2041015625, "learning_rate": 1.2397471060724593e-05, "loss": 0.24200649559497833, "step": 1359 }, { "epoch": 0.8819714656290532, "grad_norm": 0.212890625, "learning_rate": 1.2387272584376906e-05, "loss": 0.2391549050807953, "step": 1360 }, { "epoch": 0.8826199740596627, "grad_norm": 0.212890625, "learning_rate": 1.2377071474313535e-05, "loss": 0.2636871933937073, "step": 1361 }, { "epoch": 0.8832684824902723, "grad_norm": 0.1953125, "learning_rate": 1.2366867741788675e-05, "loss": 0.2404363453388214, "step": 1362 }, { "epoch": 0.8839169909208819, "grad_norm": 0.19140625, "learning_rate": 1.2356661398059405e-05, "loss": 0.22772425413131714, "step": 1363 }, { "epoch": 0.8845654993514915, "grad_norm": 0.2177734375, "learning_rate": 1.2346452454385691e-05, "loss": 0.23359455168247223, "step": 1364 }, { "epoch": 0.8852140077821011, "grad_norm": 0.1982421875, "learning_rate": 1.2336240922030374e-05, "loss": 0.2356293946504593, "step": 1365 }, { "epoch": 0.8858625162127107, "grad_norm": 0.271484375, "learning_rate": 1.2326026812259138e-05, "loss": 0.24324257671833038, "step": 1366 }, { "epoch": 0.8865110246433203, "grad_norm": 0.197265625, "learning_rate": 1.2315810136340521e-05, "loss": 0.24868172407150269, "step": 1367 }, { "epoch": 0.8871595330739299, "grad_norm": 0.201171875, "learning_rate": 1.2305590905545879e-05, "loss": 0.23945100605487823, "step": 1368 }, { "epoch": 0.8878080415045395, "grad_norm": 0.185546875, "learning_rate": 1.2295369131149406e-05, "loss": 0.22962693870067596, "step": 1369 }, { "epoch": 0.8884565499351491, "grad_norm": 0.2138671875, "learning_rate": 1.2285144824428087e-05, "loss": 0.25395667552948, "step": 1370 }, { "epoch": 0.8891050583657587, "grad_norm": 0.208984375, "learning_rate": 1.2274917996661702e-05, "loss": 0.24459466338157654, "step": 1371 }, { "epoch": 0.8897535667963683, "grad_norm": 0.205078125, "learning_rate": 1.2264688659132817e-05, "loss": 0.23565781116485596, "step": 1372 }, { "epoch": 0.8904020752269779, "grad_norm": 0.2138671875, "learning_rate": 1.2254456823126768e-05, "loss": 0.22592270374298096, "step": 1373 }, { "epoch": 0.8910505836575876, "grad_norm": 0.2099609375, "learning_rate": 1.224422249993164e-05, "loss": 0.23274323344230652, "step": 1374 }, { "epoch": 0.8916990920881972, "grad_norm": 0.201171875, "learning_rate": 1.2233985700838273e-05, "loss": 0.21891938149929047, "step": 1375 }, { "epoch": 0.8923476005188068, "grad_norm": 0.2255859375, "learning_rate": 1.2223746437140226e-05, "loss": 0.23923352360725403, "step": 1376 }, { "epoch": 0.8929961089494164, "grad_norm": 0.193359375, "learning_rate": 1.2213504720133788e-05, "loss": 0.2324732542037964, "step": 1377 }, { "epoch": 0.893644617380026, "grad_norm": 0.2001953125, "learning_rate": 1.220326056111795e-05, "loss": 0.23389506340026855, "step": 1378 }, { "epoch": 0.8942931258106356, "grad_norm": 0.1982421875, "learning_rate": 1.2193013971394384e-05, "loss": 0.23047643899917603, "step": 1379 }, { "epoch": 0.8949416342412452, "grad_norm": 0.1953125, "learning_rate": 1.2182764962267475e-05, "loss": 0.24457857012748718, "step": 1380 }, { "epoch": 0.8955901426718548, "grad_norm": 0.1865234375, "learning_rate": 1.217251354504425e-05, "loss": 0.22666120529174805, "step": 1381 }, { "epoch": 0.8962386511024644, "grad_norm": 0.228515625, "learning_rate": 1.2162259731034399e-05, "loss": 0.24617710709571838, "step": 1382 }, { "epoch": 0.896887159533074, "grad_norm": 0.2041015625, "learning_rate": 1.215200353155026e-05, "loss": 0.2523443102836609, "step": 1383 }, { "epoch": 0.8975356679636836, "grad_norm": 0.193359375, "learning_rate": 1.2141744957906805e-05, "loss": 0.2332681119441986, "step": 1384 }, { "epoch": 0.8981841763942932, "grad_norm": 0.20703125, "learning_rate": 1.2131484021421614e-05, "loss": 0.2340814769268036, "step": 1385 }, { "epoch": 0.8988326848249028, "grad_norm": 0.2080078125, "learning_rate": 1.2121220733414888e-05, "loss": 0.23707327246665955, "step": 1386 }, { "epoch": 0.8994811932555123, "grad_norm": 0.1953125, "learning_rate": 1.2110955105209417e-05, "loss": 0.22306910157203674, "step": 1387 }, { "epoch": 0.9001297016861219, "grad_norm": 0.1982421875, "learning_rate": 1.2100687148130565e-05, "loss": 0.24799120426177979, "step": 1388 }, { "epoch": 0.9007782101167315, "grad_norm": 0.203125, "learning_rate": 1.2090416873506272e-05, "loss": 0.22798410058021545, "step": 1389 }, { "epoch": 0.9014267185473411, "grad_norm": 0.224609375, "learning_rate": 1.208014429266704e-05, "loss": 0.26158931851387024, "step": 1390 }, { "epoch": 0.9020752269779507, "grad_norm": 0.193359375, "learning_rate": 1.2069869416945903e-05, "loss": 0.21968789398670197, "step": 1391 }, { "epoch": 0.9027237354085603, "grad_norm": 0.1962890625, "learning_rate": 1.2059592257678441e-05, "loss": 0.23090475797653198, "step": 1392 }, { "epoch": 0.9033722438391699, "grad_norm": 0.2001953125, "learning_rate": 1.204931282620274e-05, "loss": 0.23645909130573273, "step": 1393 }, { "epoch": 0.9040207522697795, "grad_norm": 0.201171875, "learning_rate": 1.2039031133859398e-05, "loss": 0.24444949626922607, "step": 1394 }, { "epoch": 0.9046692607003891, "grad_norm": 0.193359375, "learning_rate": 1.2028747191991509e-05, "loss": 0.23327398300170898, "step": 1395 }, { "epoch": 0.9053177691309987, "grad_norm": 0.2197265625, "learning_rate": 1.201846101194465e-05, "loss": 0.2534821629524231, "step": 1396 }, { "epoch": 0.9059662775616083, "grad_norm": 0.220703125, "learning_rate": 1.2008172605066866e-05, "loss": 0.23881199955940247, "step": 1397 }, { "epoch": 0.9066147859922179, "grad_norm": 0.20703125, "learning_rate": 1.199788198270865e-05, "loss": 0.23026658594608307, "step": 1398 }, { "epoch": 0.9072632944228275, "grad_norm": 0.20703125, "learning_rate": 1.1987589156222954e-05, "loss": 0.23241057991981506, "step": 1399 }, { "epoch": 0.9079118028534371, "grad_norm": 0.2041015625, "learning_rate": 1.1977294136965148e-05, "loss": 0.2409856915473938, "step": 1400 }, { "epoch": 0.9085603112840467, "grad_norm": 0.189453125, "learning_rate": 1.1966996936293032e-05, "loss": 0.23062291741371155, "step": 1401 }, { "epoch": 0.9092088197146563, "grad_norm": 0.2001953125, "learning_rate": 1.1956697565566808e-05, "loss": 0.2468806803226471, "step": 1402 }, { "epoch": 0.9098573281452659, "grad_norm": 0.1865234375, "learning_rate": 1.1946396036149071e-05, "loss": 0.22484895586967468, "step": 1403 }, { "epoch": 0.9105058365758755, "grad_norm": 0.205078125, "learning_rate": 1.1936092359404798e-05, "loss": 0.2505338191986084, "step": 1404 }, { "epoch": 0.9111543450064851, "grad_norm": 0.21875, "learning_rate": 1.1925786546701336e-05, "loss": 0.237228661775589, "step": 1405 }, { "epoch": 0.9118028534370947, "grad_norm": 0.2021484375, "learning_rate": 1.191547860940839e-05, "loss": 0.25502923130989075, "step": 1406 }, { "epoch": 0.9124513618677043, "grad_norm": 0.1982421875, "learning_rate": 1.1905168558898005e-05, "loss": 0.23565666377544403, "step": 1407 }, { "epoch": 0.9130998702983139, "grad_norm": 0.197265625, "learning_rate": 1.1894856406544559e-05, "loss": 0.228379487991333, "step": 1408 }, { "epoch": 0.9137483787289234, "grad_norm": 0.1875, "learning_rate": 1.1884542163724751e-05, "loss": 0.23862844705581665, "step": 1409 }, { "epoch": 0.914396887159533, "grad_norm": 0.1962890625, "learning_rate": 1.1874225841817583e-05, "loss": 0.24616622924804688, "step": 1410 }, { "epoch": 0.9150453955901426, "grad_norm": 0.19921875, "learning_rate": 1.186390745220435e-05, "loss": 0.23051349818706512, "step": 1411 }, { "epoch": 0.9156939040207522, "grad_norm": 0.20703125, "learning_rate": 1.1853587006268639e-05, "loss": 0.24823406338691711, "step": 1412 }, { "epoch": 0.9163424124513618, "grad_norm": 0.20703125, "learning_rate": 1.184326451539629e-05, "loss": 0.21841636300086975, "step": 1413 }, { "epoch": 0.9169909208819714, "grad_norm": 0.1982421875, "learning_rate": 1.1832939990975404e-05, "loss": 0.24496108293533325, "step": 1414 }, { "epoch": 0.917639429312581, "grad_norm": 0.1982421875, "learning_rate": 1.1822613444396334e-05, "loss": 0.238599956035614, "step": 1415 }, { "epoch": 0.9182879377431906, "grad_norm": 0.1884765625, "learning_rate": 1.1812284887051649e-05, "loss": 0.2328108251094818, "step": 1416 }, { "epoch": 0.9189364461738002, "grad_norm": 0.2080078125, "learning_rate": 1.1801954330336153e-05, "loss": 0.24084848165512085, "step": 1417 }, { "epoch": 0.9195849546044098, "grad_norm": 0.1962890625, "learning_rate": 1.1791621785646843e-05, "loss": 0.23755431175231934, "step": 1418 }, { "epoch": 0.9202334630350194, "grad_norm": 0.1875, "learning_rate": 1.178128726438292e-05, "loss": 0.24077200889587402, "step": 1419 }, { "epoch": 0.920881971465629, "grad_norm": 0.2021484375, "learning_rate": 1.1770950777945748e-05, "loss": 0.250032514333725, "step": 1420 }, { "epoch": 0.9215304798962386, "grad_norm": 0.205078125, "learning_rate": 1.1760612337738879e-05, "loss": 0.2389945685863495, "step": 1421 }, { "epoch": 0.9221789883268483, "grad_norm": 0.201171875, "learning_rate": 1.1750271955168012e-05, "loss": 0.24411006271839142, "step": 1422 }, { "epoch": 0.9228274967574579, "grad_norm": 0.1943359375, "learning_rate": 1.1739929641640983e-05, "loss": 0.24554386734962463, "step": 1423 }, { "epoch": 0.9234760051880675, "grad_norm": 0.1953125, "learning_rate": 1.172958540856777e-05, "loss": 0.23318272829055786, "step": 1424 }, { "epoch": 0.9241245136186771, "grad_norm": 0.201171875, "learning_rate": 1.1719239267360459e-05, "loss": 0.23093880712985992, "step": 1425 }, { "epoch": 0.9247730220492867, "grad_norm": 0.2060546875, "learning_rate": 1.1708891229433244e-05, "loss": 0.2282642126083374, "step": 1426 }, { "epoch": 0.9254215304798963, "grad_norm": 0.2001953125, "learning_rate": 1.1698541306202413e-05, "loss": 0.25469306111335754, "step": 1427 }, { "epoch": 0.9260700389105059, "grad_norm": 0.2197265625, "learning_rate": 1.1688189509086337e-05, "loss": 0.25210070610046387, "step": 1428 }, { "epoch": 0.9267185473411155, "grad_norm": 0.205078125, "learning_rate": 1.1677835849505448e-05, "loss": 0.2269148975610733, "step": 1429 }, { "epoch": 0.9273670557717251, "grad_norm": 0.2109375, "learning_rate": 1.1667480338882236e-05, "loss": 0.2441801130771637, "step": 1430 }, { "epoch": 0.9280155642023347, "grad_norm": 0.1875, "learning_rate": 1.1657122988641232e-05, "loss": 0.21714577078819275, "step": 1431 }, { "epoch": 0.9286640726329443, "grad_norm": 0.2001953125, "learning_rate": 1.1646763810208993e-05, "loss": 0.24192890524864197, "step": 1432 }, { "epoch": 0.9293125810635539, "grad_norm": 0.2060546875, "learning_rate": 1.1636402815014102e-05, "loss": 0.235250324010849, "step": 1433 }, { "epoch": 0.9299610894941635, "grad_norm": 0.1845703125, "learning_rate": 1.1626040014487143e-05, "loss": 0.22462356090545654, "step": 1434 }, { "epoch": 0.930609597924773, "grad_norm": 0.1923828125, "learning_rate": 1.1615675420060685e-05, "loss": 0.2430328130722046, "step": 1435 }, { "epoch": 0.9312581063553826, "grad_norm": 0.2001953125, "learning_rate": 1.1605309043169282e-05, "loss": 0.23461303114891052, "step": 1436 }, { "epoch": 0.9319066147859922, "grad_norm": 0.1884765625, "learning_rate": 1.1594940895249453e-05, "loss": 0.22825080156326294, "step": 1437 }, { "epoch": 0.9325551232166018, "grad_norm": 0.2099609375, "learning_rate": 1.1584570987739676e-05, "loss": 0.25511634349823, "step": 1438 }, { "epoch": 0.9332036316472114, "grad_norm": 0.2119140625, "learning_rate": 1.157419933208036e-05, "loss": 0.26079002022743225, "step": 1439 }, { "epoch": 0.933852140077821, "grad_norm": 0.1962890625, "learning_rate": 1.1563825939713853e-05, "loss": 0.2306469976902008, "step": 1440 }, { "epoch": 0.9345006485084306, "grad_norm": 0.2001953125, "learning_rate": 1.1553450822084409e-05, "loss": 0.2310113161802292, "step": 1441 }, { "epoch": 0.9351491569390402, "grad_norm": 0.185546875, "learning_rate": 1.1543073990638192e-05, "loss": 0.2204381227493286, "step": 1442 }, { "epoch": 0.9357976653696498, "grad_norm": 0.205078125, "learning_rate": 1.153269545682326e-05, "loss": 0.23832815885543823, "step": 1443 }, { "epoch": 0.9364461738002594, "grad_norm": 0.2001953125, "learning_rate": 1.1522315232089539e-05, "loss": 0.23516924679279327, "step": 1444 }, { "epoch": 0.937094682230869, "grad_norm": 0.2265625, "learning_rate": 1.1511933327888825e-05, "loss": 0.2393331527709961, "step": 1445 }, { "epoch": 0.9377431906614786, "grad_norm": 0.1982421875, "learning_rate": 1.1501549755674773e-05, "loss": 0.23700720071792603, "step": 1446 }, { "epoch": 0.9383916990920882, "grad_norm": 0.240234375, "learning_rate": 1.149116452690287e-05, "loss": 0.2423371821641922, "step": 1447 }, { "epoch": 0.9390402075226978, "grad_norm": 0.205078125, "learning_rate": 1.1480777653030431e-05, "loss": 0.22588187456130981, "step": 1448 }, { "epoch": 0.9396887159533074, "grad_norm": 0.2060546875, "learning_rate": 1.1470389145516594e-05, "loss": 0.22687339782714844, "step": 1449 }, { "epoch": 0.940337224383917, "grad_norm": 0.2138671875, "learning_rate": 1.1459999015822292e-05, "loss": 0.2189233899116516, "step": 1450 }, { "epoch": 0.9409857328145266, "grad_norm": 0.1953125, "learning_rate": 1.1449607275410246e-05, "loss": 0.23664388060569763, "step": 1451 }, { "epoch": 0.9416342412451362, "grad_norm": 0.1953125, "learning_rate": 1.1439213935744959e-05, "loss": 0.24012941122055054, "step": 1452 }, { "epoch": 0.9422827496757458, "grad_norm": 0.1943359375, "learning_rate": 1.1428819008292698e-05, "loss": 0.23705783486366272, "step": 1453 }, { "epoch": 0.9429312581063554, "grad_norm": 0.1953125, "learning_rate": 1.1418422504521476e-05, "loss": 0.24141715466976166, "step": 1454 }, { "epoch": 0.943579766536965, "grad_norm": 0.2060546875, "learning_rate": 1.1408024435901058e-05, "loss": 0.24927747249603271, "step": 1455 }, { "epoch": 0.9442282749675746, "grad_norm": 0.1943359375, "learning_rate": 1.1397624813902919e-05, "loss": 0.23238620162010193, "step": 1456 }, { "epoch": 0.9448767833981842, "grad_norm": 0.205078125, "learning_rate": 1.1387223650000261e-05, "loss": 0.26300644874572754, "step": 1457 }, { "epoch": 0.9455252918287937, "grad_norm": 0.1923828125, "learning_rate": 1.1376820955667973e-05, "loss": 0.22634723782539368, "step": 1458 }, { "epoch": 0.9461738002594033, "grad_norm": 0.203125, "learning_rate": 1.1366416742382654e-05, "loss": 0.23229219019412994, "step": 1459 }, { "epoch": 0.9468223086900129, "grad_norm": 0.2080078125, "learning_rate": 1.1356011021622555e-05, "loss": 0.22405287623405457, "step": 1460 }, { "epoch": 0.9474708171206225, "grad_norm": 0.2021484375, "learning_rate": 1.1345603804867605e-05, "loss": 0.23612435162067413, "step": 1461 }, { "epoch": 0.9481193255512321, "grad_norm": 0.2041015625, "learning_rate": 1.133519510359938e-05, "loss": 0.23100623488426208, "step": 1462 }, { "epoch": 0.9487678339818417, "grad_norm": 0.2021484375, "learning_rate": 1.1324784929301087e-05, "loss": 0.23278938233852386, "step": 1463 }, { "epoch": 0.9494163424124513, "grad_norm": 0.2099609375, "learning_rate": 1.1314373293457572e-05, "loss": 0.24411481618881226, "step": 1464 }, { "epoch": 0.9500648508430609, "grad_norm": 0.216796875, "learning_rate": 1.1303960207555284e-05, "loss": 0.23482725024223328, "step": 1465 }, { "epoch": 0.9507133592736705, "grad_norm": 0.208984375, "learning_rate": 1.1293545683082272e-05, "loss": 0.2568148970603943, "step": 1466 }, { "epoch": 0.9513618677042801, "grad_norm": 0.2138671875, "learning_rate": 1.1283129731528173e-05, "loss": 0.23011818528175354, "step": 1467 }, { "epoch": 0.9520103761348897, "grad_norm": 0.2197265625, "learning_rate": 1.1272712364384201e-05, "loss": 0.22526374459266663, "step": 1468 }, { "epoch": 0.9526588845654993, "grad_norm": 0.2138671875, "learning_rate": 1.1262293593143125e-05, "loss": 0.2605650722980499, "step": 1469 }, { "epoch": 0.953307392996109, "grad_norm": 0.1923828125, "learning_rate": 1.1251873429299272e-05, "loss": 0.22755911946296692, "step": 1470 }, { "epoch": 0.9539559014267186, "grad_norm": 0.1953125, "learning_rate": 1.12414518843485e-05, "loss": 0.22818998992443085, "step": 1471 }, { "epoch": 0.9546044098573282, "grad_norm": 0.19140625, "learning_rate": 1.1231028969788192e-05, "loss": 0.2394372820854187, "step": 1472 }, { "epoch": 0.9552529182879378, "grad_norm": 0.1943359375, "learning_rate": 1.122060469711724e-05, "loss": 0.22662466764450073, "step": 1473 }, { "epoch": 0.9559014267185474, "grad_norm": 0.1923828125, "learning_rate": 1.1210179077836032e-05, "loss": 0.21791677176952362, "step": 1474 }, { "epoch": 0.956549935149157, "grad_norm": 0.1875, "learning_rate": 1.1199752123446457e-05, "loss": 0.21297016739845276, "step": 1475 }, { "epoch": 0.9571984435797666, "grad_norm": 0.2021484375, "learning_rate": 1.1189323845451856e-05, "loss": 0.22680550813674927, "step": 1476 }, { "epoch": 0.9578469520103762, "grad_norm": 0.2119140625, "learning_rate": 1.1178894255357045e-05, "loss": 0.25160232186317444, "step": 1477 }, { "epoch": 0.9584954604409858, "grad_norm": 0.2158203125, "learning_rate": 1.1168463364668276e-05, "loss": 0.23472493886947632, "step": 1478 }, { "epoch": 0.9591439688715954, "grad_norm": 0.2236328125, "learning_rate": 1.1158031184893247e-05, "loss": 0.22998297214508057, "step": 1479 }, { "epoch": 0.959792477302205, "grad_norm": 0.203125, "learning_rate": 1.1147597727541076e-05, "loss": 0.2216833233833313, "step": 1480 }, { "epoch": 0.9604409857328146, "grad_norm": 0.2021484375, "learning_rate": 1.113716300412228e-05, "loss": 0.24973174929618835, "step": 1481 }, { "epoch": 0.9610894941634242, "grad_norm": 0.2197265625, "learning_rate": 1.1126727026148785e-05, "loss": 0.2468000054359436, "step": 1482 }, { "epoch": 0.9617380025940337, "grad_norm": 0.2060546875, "learning_rate": 1.1116289805133897e-05, "loss": 0.23721468448638916, "step": 1483 }, { "epoch": 0.9623865110246433, "grad_norm": 0.1953125, "learning_rate": 1.1105851352592297e-05, "loss": 0.23233485221862793, "step": 1484 }, { "epoch": 0.9630350194552529, "grad_norm": 0.2119140625, "learning_rate": 1.109541168004001e-05, "loss": 0.22265425324440002, "step": 1485 }, { "epoch": 0.9636835278858625, "grad_norm": 0.1953125, "learning_rate": 1.1084970798994425e-05, "loss": 0.22530248761177063, "step": 1486 }, { "epoch": 0.9643320363164721, "grad_norm": 0.2138671875, "learning_rate": 1.1074528720974255e-05, "loss": 0.23647159337997437, "step": 1487 }, { "epoch": 0.9649805447470817, "grad_norm": 0.2099609375, "learning_rate": 1.1064085457499537e-05, "loss": 0.2613672614097595, "step": 1488 }, { "epoch": 0.9656290531776913, "grad_norm": 0.2158203125, "learning_rate": 1.1053641020091614e-05, "loss": 0.2201242297887802, "step": 1489 }, { "epoch": 0.9662775616083009, "grad_norm": 0.208984375, "learning_rate": 1.1043195420273123e-05, "loss": 0.2398175299167633, "step": 1490 }, { "epoch": 0.9669260700389105, "grad_norm": 0.20703125, "learning_rate": 1.1032748669567983e-05, "loss": 0.24440929293632507, "step": 1491 }, { "epoch": 0.9675745784695201, "grad_norm": 0.2099609375, "learning_rate": 1.102230077950139e-05, "loss": 0.24006032943725586, "step": 1492 }, { "epoch": 0.9682230869001297, "grad_norm": 0.2080078125, "learning_rate": 1.1011851761599786e-05, "loss": 0.2322508692741394, "step": 1493 }, { "epoch": 0.9688715953307393, "grad_norm": 0.1962890625, "learning_rate": 1.1001401627390864e-05, "loss": 0.2318558692932129, "step": 1494 }, { "epoch": 0.9695201037613489, "grad_norm": 0.2001953125, "learning_rate": 1.0990950388403548e-05, "loss": 0.2385571300983429, "step": 1495 }, { "epoch": 0.9701686121919585, "grad_norm": 0.2080078125, "learning_rate": 1.098049805616798e-05, "loss": 0.22641921043395996, "step": 1496 }, { "epoch": 0.9708171206225681, "grad_norm": 0.1953125, "learning_rate": 1.0970044642215512e-05, "loss": 0.2150404006242752, "step": 1497 }, { "epoch": 0.9714656290531777, "grad_norm": 0.2001953125, "learning_rate": 1.095959015807868e-05, "loss": 0.23154330253601074, "step": 1498 }, { "epoch": 0.9721141374837873, "grad_norm": 0.2060546875, "learning_rate": 1.0949134615291205e-05, "loss": 0.23371177911758423, "step": 1499 }, { "epoch": 0.9727626459143969, "grad_norm": 0.212890625, "learning_rate": 1.093867802538798e-05, "loss": 0.23104898631572723, "step": 1500 }, { "epoch": 0.9734111543450065, "grad_norm": 0.1953125, "learning_rate": 1.0928220399905052e-05, "loss": 0.24231310188770294, "step": 1501 }, { "epoch": 0.9740596627756161, "grad_norm": 0.19140625, "learning_rate": 1.0917761750379607e-05, "loss": 0.24701659381389618, "step": 1502 }, { "epoch": 0.9747081712062257, "grad_norm": 0.20703125, "learning_rate": 1.0907302088349965e-05, "loss": 0.2545427083969116, "step": 1503 }, { "epoch": 0.9753566796368353, "grad_norm": 0.19921875, "learning_rate": 1.0896841425355556e-05, "loss": 0.23171845078468323, "step": 1504 }, { "epoch": 0.9760051880674449, "grad_norm": 0.193359375, "learning_rate": 1.0886379772936921e-05, "loss": 0.23597726225852966, "step": 1505 }, { "epoch": 0.9766536964980544, "grad_norm": 0.2216796875, "learning_rate": 1.0875917142635693e-05, "loss": 0.2506871223449707, "step": 1506 }, { "epoch": 0.977302204928664, "grad_norm": 0.1923828125, "learning_rate": 1.086545354599458e-05, "loss": 0.21896615624427795, "step": 1507 }, { "epoch": 0.9779507133592736, "grad_norm": 0.203125, "learning_rate": 1.0854988994557356e-05, "loss": 0.21598447859287262, "step": 1508 }, { "epoch": 0.9785992217898832, "grad_norm": 0.232421875, "learning_rate": 1.0844523499868849e-05, "loss": 0.24243032932281494, "step": 1509 }, { "epoch": 0.9792477302204928, "grad_norm": 0.1943359375, "learning_rate": 1.083405707347493e-05, "loss": 0.22689422965049744, "step": 1510 }, { "epoch": 0.9798962386511024, "grad_norm": 0.19140625, "learning_rate": 1.0823589726922494e-05, "loss": 0.2344590127468109, "step": 1511 }, { "epoch": 0.980544747081712, "grad_norm": 0.212890625, "learning_rate": 1.081312147175946e-05, "loss": 0.2405458241701126, "step": 1512 }, { "epoch": 0.9811932555123216, "grad_norm": 0.19921875, "learning_rate": 1.0802652319534739e-05, "loss": 0.2449973076581955, "step": 1513 }, { "epoch": 0.9818417639429312, "grad_norm": 0.1962890625, "learning_rate": 1.0792182281798233e-05, "loss": 0.24066002666950226, "step": 1514 }, { "epoch": 0.9824902723735408, "grad_norm": 0.189453125, "learning_rate": 1.0781711370100827e-05, "loss": 0.23903927206993103, "step": 1515 }, { "epoch": 0.9831387808041504, "grad_norm": 0.19921875, "learning_rate": 1.077123959599436e-05, "loss": 0.25234168767929077, "step": 1516 }, { "epoch": 0.98378728923476, "grad_norm": 0.1962890625, "learning_rate": 1.076076697103164e-05, "loss": 0.23056384921073914, "step": 1517 }, { "epoch": 0.9844357976653697, "grad_norm": 0.1982421875, "learning_rate": 1.0750293506766392e-05, "loss": 0.22860902547836304, "step": 1518 }, { "epoch": 0.9850843060959793, "grad_norm": 0.2138671875, "learning_rate": 1.0739819214753286e-05, "loss": 0.2369219958782196, "step": 1519 }, { "epoch": 0.9857328145265889, "grad_norm": 0.2041015625, "learning_rate": 1.0729344106547893e-05, "loss": 0.24046747386455536, "step": 1520 }, { "epoch": 0.9863813229571985, "grad_norm": 0.197265625, "learning_rate": 1.0718868193706688e-05, "loss": 0.2222250998020172, "step": 1521 }, { "epoch": 0.9870298313878081, "grad_norm": 0.20703125, "learning_rate": 1.0708391487787036e-05, "loss": 0.22888711094856262, "step": 1522 }, { "epoch": 0.9876783398184177, "grad_norm": 0.2001953125, "learning_rate": 1.0697914000347173e-05, "loss": 0.23470643162727356, "step": 1523 }, { "epoch": 0.9883268482490273, "grad_norm": 0.2177734375, "learning_rate": 1.0687435742946203e-05, "loss": 0.23076725006103516, "step": 1524 }, { "epoch": 0.9889753566796369, "grad_norm": 0.1953125, "learning_rate": 1.0676956727144067e-05, "loss": 0.22949384152889252, "step": 1525 }, { "epoch": 0.9896238651102465, "grad_norm": 0.20703125, "learning_rate": 1.066647696450156e-05, "loss": 0.2309270203113556, "step": 1526 }, { "epoch": 0.9902723735408561, "grad_norm": 0.1845703125, "learning_rate": 1.0655996466580288e-05, "loss": 0.21738292276859283, "step": 1527 }, { "epoch": 0.9909208819714657, "grad_norm": 0.197265625, "learning_rate": 1.0645515244942676e-05, "loss": 0.23034021258354187, "step": 1528 }, { "epoch": 0.9915693904020753, "grad_norm": 0.1875, "learning_rate": 1.0635033311151942e-05, "loss": 0.2260051667690277, "step": 1529 }, { "epoch": 0.9922178988326849, "grad_norm": 0.2099609375, "learning_rate": 1.062455067677209e-05, "loss": 0.24502217769622803, "step": 1530 }, { "epoch": 0.9928664072632944, "grad_norm": 0.1953125, "learning_rate": 1.06140673533679e-05, "loss": 0.23468898236751556, "step": 1531 }, { "epoch": 0.993514915693904, "grad_norm": 0.2138671875, "learning_rate": 1.0603583352504909e-05, "loss": 0.22225283086299896, "step": 1532 }, { "epoch": 0.9941634241245136, "grad_norm": 0.1953125, "learning_rate": 1.0593098685749409e-05, "loss": 0.23471981287002563, "step": 1533 }, { "epoch": 0.9948119325551232, "grad_norm": 0.2109375, "learning_rate": 1.058261336466841e-05, "loss": 0.22314035892486572, "step": 1534 }, { "epoch": 0.9954604409857328, "grad_norm": 0.1953125, "learning_rate": 1.0572127400829664e-05, "loss": 0.23483601212501526, "step": 1535 }, { "epoch": 0.9961089494163424, "grad_norm": 0.2041015625, "learning_rate": 1.0561640805801616e-05, "loss": 0.2457972764968872, "step": 1536 }, { "epoch": 0.996757457846952, "grad_norm": 0.2041015625, "learning_rate": 1.055115359115342e-05, "loss": 0.22622992098331451, "step": 1537 }, { "epoch": 0.9974059662775616, "grad_norm": 0.2080078125, "learning_rate": 1.0540665768454903e-05, "loss": 0.23438572883605957, "step": 1538 }, { "epoch": 0.9980544747081712, "grad_norm": 0.2041015625, "learning_rate": 1.0530177349276572e-05, "loss": 0.2364831268787384, "step": 1539 }, { "epoch": 0.9987029831387808, "grad_norm": 0.19921875, "learning_rate": 1.0519688345189583e-05, "loss": 0.22529175877571106, "step": 1540 }, { "epoch": 0.9993514915693904, "grad_norm": 0.20703125, "learning_rate": 1.0509198767765743e-05, "loss": 0.2296258807182312, "step": 1541 }, { "epoch": 1.0, "grad_norm": 0.2041015625, "learning_rate": 1.0498708628577487e-05, "loss": 0.23429754376411438, "step": 1542 } ], "logging_steps": 1, "max_steps": 3084, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 7.784266421967939e+19, "train_batch_size": 16, "trial_name": null, "trial_params": null }