EC2 Default User
add ckpt for epoch 1
8494dcb
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 13434,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.5227460711331677e-08,
"loss": 3.3575,
"step": 64
},
{
"epoch": 0.01,
"learning_rate": 5.128205128205128e-08,
"loss": 3.3023,
"step": 128
},
{
"epoch": 0.01,
"learning_rate": 7.775020678246484e-08,
"loss": 2.9134,
"step": 192
},
{
"epoch": 0.02,
"learning_rate": 1.0421836228287841e-07,
"loss": 2.7766,
"step": 256
},
{
"epoch": 0.02,
"learning_rate": 1.3068651778329198e-07,
"loss": 2.6203,
"step": 320
},
{
"epoch": 0.03,
"learning_rate": 1.5715467328370554e-07,
"loss": 2.221,
"step": 384
},
{
"epoch": 0.03,
"learning_rate": 1.836228287841191e-07,
"loss": 1.6761,
"step": 448
},
{
"epoch": 0.04,
"learning_rate": 2.1009098428453268e-07,
"loss": 1.3371,
"step": 512
},
{
"epoch": 0.04,
"learning_rate": 2.3655913978494625e-07,
"loss": 1.102,
"step": 576
},
{
"epoch": 0.05,
"learning_rate": 2.6302729528535976e-07,
"loss": 0.9863,
"step": 640
},
{
"epoch": 0.05,
"learning_rate": 2.8949545078577336e-07,
"loss": 0.8123,
"step": 704
},
{
"epoch": 0.06,
"learning_rate": 3.159636062861869e-07,
"loss": 0.6005,
"step": 768
},
{
"epoch": 0.06,
"learning_rate": 3.424317617866005e-07,
"loss": 0.4275,
"step": 832
},
{
"epoch": 0.07,
"learning_rate": 3.6889991728701403e-07,
"loss": 0.4868,
"step": 896
},
{
"epoch": 0.07,
"learning_rate": 3.9536807278742763e-07,
"loss": 0.4454,
"step": 960
},
{
"epoch": 0.08,
"learning_rate": 4.2183622828784117e-07,
"loss": 0.3431,
"step": 1024
},
{
"epoch": 0.08,
"learning_rate": 4.4830438378825477e-07,
"loss": 0.3373,
"step": 1088
},
{
"epoch": 0.09,
"learning_rate": 4.743589743589743e-07,
"loss": 0.351,
"step": 1152
},
{
"epoch": 0.09,
"learning_rate": 5.00827129859388e-07,
"loss": 0.3565,
"step": 1216
},
{
"epoch": 0.1,
"learning_rate": 5.272952853598015e-07,
"loss": 0.2179,
"step": 1280
},
{
"epoch": 0.1,
"learning_rate": 5.537634408602149e-07,
"loss": 0.3892,
"step": 1344
},
{
"epoch": 0.1,
"learning_rate": 5.802315963606285e-07,
"loss": 0.3388,
"step": 1408
},
{
"epoch": 0.11,
"learning_rate": 6.066997518610421e-07,
"loss": 0.4345,
"step": 1472
},
{
"epoch": 0.11,
"learning_rate": 6.331679073614557e-07,
"loss": 0.1948,
"step": 1536
},
{
"epoch": 0.12,
"learning_rate": 6.596360628618692e-07,
"loss": 0.2907,
"step": 1600
},
{
"epoch": 0.12,
"learning_rate": 6.861042183622828e-07,
"loss": 0.3393,
"step": 1664
},
{
"epoch": 0.13,
"learning_rate": 7.125723738626964e-07,
"loss": 0.2568,
"step": 1728
},
{
"epoch": 0.13,
"learning_rate": 7.3904052936311e-07,
"loss": 0.3041,
"step": 1792
},
{
"epoch": 0.14,
"learning_rate": 7.655086848635235e-07,
"loss": 0.3316,
"step": 1856
},
{
"epoch": 0.14,
"learning_rate": 7.919768403639371e-07,
"loss": 0.3193,
"step": 1920
},
{
"epoch": 0.15,
"learning_rate": 8.184449958643507e-07,
"loss": 0.3393,
"step": 1984
},
{
"epoch": 0.15,
"learning_rate": 8.449131513647643e-07,
"loss": 0.2933,
"step": 2048
},
{
"epoch": 0.16,
"learning_rate": 8.713813068651778e-07,
"loss": 0.236,
"step": 2112
},
{
"epoch": 0.16,
"learning_rate": 8.978494623655913e-07,
"loss": 0.305,
"step": 2176
},
{
"epoch": 0.17,
"learning_rate": 9.243176178660049e-07,
"loss": 0.2158,
"step": 2240
},
{
"epoch": 0.17,
"learning_rate": 9.507857733664185e-07,
"loss": 0.3261,
"step": 2304
},
{
"epoch": 0.18,
"learning_rate": 9.77253928866832e-07,
"loss": 0.2282,
"step": 2368
},
{
"epoch": 0.18,
"learning_rate": 9.997624326892619e-07,
"loss": 0.3758,
"step": 2432
},
{
"epoch": 0.19,
"learning_rate": 9.980730651462358e-07,
"loss": 0.2466,
"step": 2496
},
{
"epoch": 0.19,
"learning_rate": 9.963836976032098e-07,
"loss": 0.2283,
"step": 2560
},
{
"epoch": 0.2,
"learning_rate": 9.946943300601838e-07,
"loss": 0.2605,
"step": 2624
},
{
"epoch": 0.2,
"learning_rate": 9.930049625171575e-07,
"loss": 0.2818,
"step": 2688
},
{
"epoch": 0.2,
"learning_rate": 9.913155949741315e-07,
"loss": 0.3004,
"step": 2752
},
{
"epoch": 0.21,
"learning_rate": 9.896262274311054e-07,
"loss": 0.2703,
"step": 2816
},
{
"epoch": 0.21,
"learning_rate": 9.879368598880794e-07,
"loss": 0.2924,
"step": 2880
},
{
"epoch": 0.22,
"learning_rate": 9.862474923450532e-07,
"loss": 0.3661,
"step": 2944
},
{
"epoch": 0.22,
"learning_rate": 9.845581248020271e-07,
"loss": 0.3517,
"step": 3008
},
{
"epoch": 0.23,
"learning_rate": 9.82868757259001e-07,
"loss": 0.2773,
"step": 3072
},
{
"epoch": 0.23,
"learning_rate": 9.81179389715975e-07,
"loss": 0.3023,
"step": 3136
},
{
"epoch": 0.24,
"learning_rate": 9.79490022172949e-07,
"loss": 0.2831,
"step": 3200
},
{
"epoch": 0.24,
"learning_rate": 9.77800654629923e-07,
"loss": 0.2693,
"step": 3264
},
{
"epoch": 0.25,
"learning_rate": 9.76111287086897e-07,
"loss": 0.2534,
"step": 3328
},
{
"epoch": 0.25,
"learning_rate": 9.744219195438707e-07,
"loss": 0.183,
"step": 3392
},
{
"epoch": 0.26,
"learning_rate": 9.727325520008446e-07,
"loss": 0.1786,
"step": 3456
},
{
"epoch": 0.26,
"learning_rate": 9.710431844578186e-07,
"loss": 0.3985,
"step": 3520
},
{
"epoch": 0.27,
"learning_rate": 9.693538169147924e-07,
"loss": 0.2585,
"step": 3584
},
{
"epoch": 0.27,
"learning_rate": 9.676644493717663e-07,
"loss": 0.2088,
"step": 3648
},
{
"epoch": 0.28,
"learning_rate": 9.659750818287403e-07,
"loss": 0.1913,
"step": 3712
},
{
"epoch": 0.28,
"learning_rate": 9.642857142857142e-07,
"loss": 0.2747,
"step": 3776
},
{
"epoch": 0.29,
"learning_rate": 9.625963467426882e-07,
"loss": 0.2283,
"step": 3840
},
{
"epoch": 0.29,
"learning_rate": 9.609069791996622e-07,
"loss": 0.305,
"step": 3904
},
{
"epoch": 0.3,
"learning_rate": 9.59217611656636e-07,
"loss": 0.2648,
"step": 3968
},
{
"epoch": 0.3,
"learning_rate": 9.575282441136099e-07,
"loss": 0.2277,
"step": 4032
},
{
"epoch": 0.3,
"learning_rate": 9.558388765705839e-07,
"loss": 0.2445,
"step": 4096
},
{
"epoch": 0.31,
"learning_rate": 9.541495090275578e-07,
"loss": 0.3094,
"step": 4160
},
{
"epoch": 0.31,
"learning_rate": 9.524601414845317e-07,
"loss": 0.2558,
"step": 4224
},
{
"epoch": 0.32,
"learning_rate": 9.507707739415056e-07,
"loss": 0.2467,
"step": 4288
},
{
"epoch": 0.32,
"learning_rate": 9.490814063984796e-07,
"loss": 0.2412,
"step": 4352
},
{
"epoch": 0.33,
"learning_rate": 9.473920388554535e-07,
"loss": 0.2564,
"step": 4416
},
{
"epoch": 0.33,
"learning_rate": 9.457026713124273e-07,
"loss": 0.2373,
"step": 4480
},
{
"epoch": 0.34,
"learning_rate": 9.440133037694013e-07,
"loss": 0.34,
"step": 4544
},
{
"epoch": 0.34,
"learning_rate": 9.423239362263751e-07,
"loss": 0.2398,
"step": 4608
},
{
"epoch": 0.35,
"learning_rate": 9.406345686833491e-07,
"loss": 0.2493,
"step": 4672
},
{
"epoch": 0.35,
"learning_rate": 9.389452011403231e-07,
"loss": 0.2398,
"step": 4736
},
{
"epoch": 0.36,
"learning_rate": 9.37255833597297e-07,
"loss": 0.2536,
"step": 4800
},
{
"epoch": 0.36,
"learning_rate": 9.355664660542709e-07,
"loss": 0.3538,
"step": 4864
},
{
"epoch": 0.37,
"learning_rate": 9.338770985112448e-07,
"loss": 0.2481,
"step": 4928
},
{
"epoch": 0.37,
"learning_rate": 9.321877309682187e-07,
"loss": 0.2152,
"step": 4992
},
{
"epoch": 0.38,
"learning_rate": 9.304983634251927e-07,
"loss": 0.3056,
"step": 5056
},
{
"epoch": 0.38,
"learning_rate": 9.288089958821665e-07,
"loss": 0.2473,
"step": 5120
},
{
"epoch": 0.39,
"learning_rate": 9.271196283391405e-07,
"loss": 0.234,
"step": 5184
},
{
"epoch": 0.39,
"learning_rate": 9.254302607961144e-07,
"loss": 0.1578,
"step": 5248
},
{
"epoch": 0.4,
"learning_rate": 9.237672896209481e-07,
"loss": 0.2566,
"step": 5312
},
{
"epoch": 0.4,
"learning_rate": 9.22077922077922e-07,
"loss": 0.3794,
"step": 5376
},
{
"epoch": 0.4,
"learning_rate": 9.203885545348959e-07,
"loss": 0.2453,
"step": 5440
},
{
"epoch": 0.41,
"learning_rate": 9.186991869918699e-07,
"loss": 0.2361,
"step": 5504
},
{
"epoch": 0.41,
"learning_rate": 9.170098194488438e-07,
"loss": 0.1734,
"step": 5568
},
{
"epoch": 0.42,
"learning_rate": 9.153204519058178e-07,
"loss": 0.1762,
"step": 5632
},
{
"epoch": 0.42,
"learning_rate": 9.136310843627916e-07,
"loss": 0.2933,
"step": 5696
},
{
"epoch": 0.43,
"learning_rate": 9.119417168197655e-07,
"loss": 0.3152,
"step": 5760
},
{
"epoch": 0.43,
"learning_rate": 9.102523492767395e-07,
"loss": 0.1966,
"step": 5824
},
{
"epoch": 0.44,
"learning_rate": 9.085629817337133e-07,
"loss": 0.298,
"step": 5888
},
{
"epoch": 0.44,
"learning_rate": 9.068736141906873e-07,
"loss": 0.2437,
"step": 5952
},
{
"epoch": 0.45,
"learning_rate": 9.051842466476613e-07,
"loss": 0.305,
"step": 6016
},
{
"epoch": 0.45,
"learning_rate": 9.034948791046352e-07,
"loss": 0.1959,
"step": 6080
},
{
"epoch": 0.46,
"learning_rate": 9.018055115616091e-07,
"loss": 0.2465,
"step": 6144
},
{
"epoch": 0.46,
"learning_rate": 9.00116144018583e-07,
"loss": 0.2624,
"step": 6208
},
{
"epoch": 0.47,
"learning_rate": 8.984267764755569e-07,
"loss": 0.2772,
"step": 6272
},
{
"epoch": 0.47,
"learning_rate": 8.967374089325309e-07,
"loss": 0.2208,
"step": 6336
},
{
"epoch": 0.48,
"learning_rate": 8.950480413895047e-07,
"loss": 0.2695,
"step": 6400
},
{
"epoch": 0.48,
"learning_rate": 8.933586738464787e-07,
"loss": 0.3235,
"step": 6464
},
{
"epoch": 0.49,
"learning_rate": 8.916693063034526e-07,
"loss": 0.2802,
"step": 6528
},
{
"epoch": 0.49,
"learning_rate": 8.899799387604265e-07,
"loss": 0.2383,
"step": 6592
},
{
"epoch": 0.5,
"learning_rate": 8.882905712174005e-07,
"loss": 0.2238,
"step": 6656
},
{
"epoch": 0.5,
"learning_rate": 8.866012036743744e-07,
"loss": 0.2847,
"step": 6720
},
{
"epoch": 0.5,
"learning_rate": 8.849118361313483e-07,
"loss": 0.2713,
"step": 6784
},
{
"epoch": 0.51,
"learning_rate": 8.832224685883221e-07,
"loss": 0.2156,
"step": 6848
},
{
"epoch": 0.51,
"learning_rate": 8.815331010452961e-07,
"loss": 0.2832,
"step": 6912
},
{
"epoch": 0.52,
"learning_rate": 8.798437335022701e-07,
"loss": 0.2675,
"step": 6976
},
{
"epoch": 0.52,
"learning_rate": 8.781543659592439e-07,
"loss": 0.2506,
"step": 7040
},
{
"epoch": 0.53,
"learning_rate": 8.764649984162179e-07,
"loss": 0.2807,
"step": 7104
},
{
"epoch": 0.53,
"learning_rate": 8.747756308731918e-07,
"loss": 0.2802,
"step": 7168
},
{
"epoch": 0.54,
"learning_rate": 8.730862633301658e-07,
"loss": 0.2125,
"step": 7232
},
{
"epoch": 0.54,
"learning_rate": 8.713968957871396e-07,
"loss": 0.2739,
"step": 7296
},
{
"epoch": 0.55,
"learning_rate": 8.697075282441135e-07,
"loss": 0.2341,
"step": 7360
},
{
"epoch": 0.55,
"learning_rate": 8.680181607010875e-07,
"loss": 0.2267,
"step": 7424
},
{
"epoch": 0.56,
"learning_rate": 8.663287931580614e-07,
"loss": 0.3504,
"step": 7488
},
{
"epoch": 0.56,
"learning_rate": 8.646394256150353e-07,
"loss": 0.2675,
"step": 7552
},
{
"epoch": 0.57,
"learning_rate": 8.629500580720093e-07,
"loss": 0.1694,
"step": 7616
},
{
"epoch": 0.57,
"learning_rate": 8.612606905289832e-07,
"loss": 0.2865,
"step": 7680
},
{
"epoch": 0.58,
"learning_rate": 8.595713229859571e-07,
"loss": 0.2737,
"step": 7744
},
{
"epoch": 0.58,
"learning_rate": 8.578819554429309e-07,
"loss": 0.2201,
"step": 7808
},
{
"epoch": 0.59,
"learning_rate": 8.561925878999049e-07,
"loss": 0.1701,
"step": 7872
},
{
"epoch": 0.59,
"learning_rate": 8.545032203568789e-07,
"loss": 0.2566,
"step": 7936
},
{
"epoch": 0.6,
"learning_rate": 8.528138528138527e-07,
"loss": 0.274,
"step": 8000
},
{
"epoch": 0.6,
"learning_rate": 8.511244852708267e-07,
"loss": 0.3413,
"step": 8064
},
{
"epoch": 0.61,
"learning_rate": 8.494351177278007e-07,
"loss": 0.2035,
"step": 8128
},
{
"epoch": 0.61,
"learning_rate": 8.477721465526343e-07,
"loss": 0.2612,
"step": 8192
},
{
"epoch": 0.61,
"learning_rate": 8.460827790096083e-07,
"loss": 0.2322,
"step": 8256
},
{
"epoch": 0.62,
"learning_rate": 8.443934114665822e-07,
"loss": 0.1929,
"step": 8320
},
{
"epoch": 0.62,
"learning_rate": 8.427040439235561e-07,
"loss": 0.2212,
"step": 8384
},
{
"epoch": 0.63,
"learning_rate": 8.4101467638053e-07,
"loss": 0.1912,
"step": 8448
},
{
"epoch": 0.63,
"learning_rate": 8.39325308837504e-07,
"loss": 0.3325,
"step": 8512
},
{
"epoch": 0.64,
"learning_rate": 8.376359412944777e-07,
"loss": 0.2341,
"step": 8576
},
{
"epoch": 0.64,
"learning_rate": 8.359465737514517e-07,
"loss": 0.248,
"step": 8640
},
{
"epoch": 0.65,
"learning_rate": 8.342572062084257e-07,
"loss": 0.268,
"step": 8704
},
{
"epoch": 0.65,
"learning_rate": 8.325678386653996e-07,
"loss": 0.3279,
"step": 8768
},
{
"epoch": 0.66,
"learning_rate": 8.308784711223735e-07,
"loss": 0.2175,
"step": 8832
},
{
"epoch": 0.66,
"learning_rate": 8.291891035793475e-07,
"loss": 0.2641,
"step": 8896
},
{
"epoch": 0.67,
"learning_rate": 8.274997360363214e-07,
"loss": 0.2435,
"step": 8960
},
{
"epoch": 0.67,
"learning_rate": 8.258103684932953e-07,
"loss": 0.208,
"step": 9024
},
{
"epoch": 0.68,
"learning_rate": 8.241210009502691e-07,
"loss": 0.2631,
"step": 9088
},
{
"epoch": 0.68,
"learning_rate": 8.224316334072431e-07,
"loss": 0.2774,
"step": 9152
},
{
"epoch": 0.69,
"learning_rate": 8.207422658642171e-07,
"loss": 0.2279,
"step": 9216
},
{
"epoch": 0.69,
"learning_rate": 8.190528983211909e-07,
"loss": 0.1885,
"step": 9280
},
{
"epoch": 0.7,
"learning_rate": 8.173635307781649e-07,
"loss": 0.2396,
"step": 9344
},
{
"epoch": 0.7,
"learning_rate": 8.156741632351388e-07,
"loss": 0.269,
"step": 9408
},
{
"epoch": 0.71,
"learning_rate": 8.139847956921128e-07,
"loss": 0.315,
"step": 9472
},
{
"epoch": 0.71,
"learning_rate": 8.122954281490867e-07,
"loss": 0.2165,
"step": 9536
},
{
"epoch": 0.71,
"learning_rate": 8.106060606060605e-07,
"loss": 0.2035,
"step": 9600
},
{
"epoch": 0.72,
"learning_rate": 8.089166930630345e-07,
"loss": 0.2472,
"step": 9664
},
{
"epoch": 0.72,
"learning_rate": 8.072273255200083e-07,
"loss": 0.2641,
"step": 9728
},
{
"epoch": 0.73,
"learning_rate": 8.055379579769823e-07,
"loss": 0.1937,
"step": 9792
},
{
"epoch": 0.73,
"learning_rate": 8.038485904339563e-07,
"loss": 0.2108,
"step": 9856
},
{
"epoch": 0.74,
"learning_rate": 8.021592228909302e-07,
"loss": 0.2866,
"step": 9920
},
{
"epoch": 0.74,
"learning_rate": 8.004698553479041e-07,
"loss": 0.2707,
"step": 9984
},
{
"epoch": 0.75,
"learning_rate": 7.98780487804878e-07,
"loss": 0.2249,
"step": 10048
},
{
"epoch": 0.75,
"learning_rate": 7.970911202618519e-07,
"loss": 0.2183,
"step": 10112
},
{
"epoch": 0.76,
"learning_rate": 7.954017527188258e-07,
"loss": 0.234,
"step": 10176
},
{
"epoch": 0.76,
"learning_rate": 7.937123851757997e-07,
"loss": 0.2504,
"step": 10240
},
{
"epoch": 0.77,
"learning_rate": 7.920230176327737e-07,
"loss": 0.1973,
"step": 10304
},
{
"epoch": 0.77,
"learning_rate": 7.903336500897477e-07,
"loss": 0.2003,
"step": 10368
},
{
"epoch": 0.78,
"learning_rate": 7.886442825467215e-07,
"loss": 0.2558,
"step": 10432
},
{
"epoch": 0.78,
"learning_rate": 7.869549150036955e-07,
"loss": 0.2694,
"step": 10496
},
{
"epoch": 0.79,
"learning_rate": 7.852655474606694e-07,
"loss": 0.2633,
"step": 10560
},
{
"epoch": 0.79,
"learning_rate": 7.835761799176432e-07,
"loss": 0.2649,
"step": 10624
},
{
"epoch": 0.8,
"learning_rate": 7.818868123746172e-07,
"loss": 0.2874,
"step": 10688
},
{
"epoch": 0.8,
"learning_rate": 7.801974448315911e-07,
"loss": 0.2393,
"step": 10752
},
{
"epoch": 0.81,
"learning_rate": 7.785080772885651e-07,
"loss": 0.2303,
"step": 10816
},
{
"epoch": 0.81,
"learning_rate": 7.768451061133987e-07,
"loss": 0.2417,
"step": 10880
},
{
"epoch": 0.81,
"learning_rate": 7.751557385703727e-07,
"loss": 0.272,
"step": 10944
},
{
"epoch": 0.82,
"learning_rate": 7.734663710273465e-07,
"loss": 0.2005,
"step": 11008
},
{
"epoch": 0.82,
"learning_rate": 7.717770034843205e-07,
"loss": 0.1505,
"step": 11072
},
{
"epoch": 0.83,
"learning_rate": 7.700876359412945e-07,
"loss": 0.2839,
"step": 11136
},
{
"epoch": 0.83,
"learning_rate": 7.683982683982684e-07,
"loss": 0.2805,
"step": 11200
},
{
"epoch": 0.84,
"learning_rate": 7.667089008552423e-07,
"loss": 0.2407,
"step": 11264
},
{
"epoch": 0.84,
"learning_rate": 7.650195333122162e-07,
"loss": 0.1769,
"step": 11328
},
{
"epoch": 0.85,
"learning_rate": 7.633301657691901e-07,
"loss": 0.2223,
"step": 11392
},
{
"epoch": 0.85,
"learning_rate": 7.61640798226164e-07,
"loss": 0.2609,
"step": 11456
},
{
"epoch": 0.86,
"learning_rate": 7.599514306831379e-07,
"loss": 0.3837,
"step": 11520
},
{
"epoch": 0.86,
"learning_rate": 7.582620631401119e-07,
"loss": 0.2162,
"step": 11584
},
{
"epoch": 0.87,
"learning_rate": 7.565726955970858e-07,
"loss": 0.2076,
"step": 11648
},
{
"epoch": 0.87,
"learning_rate": 7.548833280540597e-07,
"loss": 0.266,
"step": 11712
},
{
"epoch": 0.88,
"learning_rate": 7.531939605110337e-07,
"loss": 0.1652,
"step": 11776
},
{
"epoch": 0.88,
"learning_rate": 7.515045929680076e-07,
"loss": 0.2416,
"step": 11840
},
{
"epoch": 0.89,
"learning_rate": 7.498152254249815e-07,
"loss": 0.2471,
"step": 11904
},
{
"epoch": 0.89,
"learning_rate": 7.481258578819553e-07,
"loss": 0.2285,
"step": 11968
},
{
"epoch": 0.9,
"learning_rate": 7.464364903389293e-07,
"loss": 0.2368,
"step": 12032
},
{
"epoch": 0.9,
"learning_rate": 7.447471227959033e-07,
"loss": 0.1847,
"step": 12096
},
{
"epoch": 0.91,
"learning_rate": 7.430577552528771e-07,
"loss": 0.2826,
"step": 12160
},
{
"epoch": 0.91,
"learning_rate": 7.413683877098511e-07,
"loss": 0.2931,
"step": 12224
},
{
"epoch": 0.91,
"learning_rate": 7.396790201668251e-07,
"loss": 0.1722,
"step": 12288
},
{
"epoch": 0.92,
"learning_rate": 7.37989652623799e-07,
"loss": 0.2673,
"step": 12352
},
{
"epoch": 0.92,
"learning_rate": 7.363002850807728e-07,
"loss": 0.2244,
"step": 12416
},
{
"epoch": 0.93,
"learning_rate": 7.346109175377467e-07,
"loss": 0.1532,
"step": 12480
},
{
"epoch": 0.93,
"learning_rate": 7.329215499947207e-07,
"loss": 0.2207,
"step": 12544
},
{
"epoch": 0.94,
"learning_rate": 7.312321824516946e-07,
"loss": 0.2362,
"step": 12608
},
{
"epoch": 0.94,
"learning_rate": 7.295428149086685e-07,
"loss": 0.2222,
"step": 12672
},
{
"epoch": 0.95,
"learning_rate": 7.278534473656425e-07,
"loss": 0.2664,
"step": 12736
},
{
"epoch": 0.95,
"learning_rate": 7.261640798226164e-07,
"loss": 0.1632,
"step": 12800
},
{
"epoch": 0.96,
"learning_rate": 7.244747122795903e-07,
"loss": 0.2212,
"step": 12864
},
{
"epoch": 0.96,
"learning_rate": 7.227853447365642e-07,
"loss": 0.2026,
"step": 12928
},
{
"epoch": 0.97,
"learning_rate": 7.210959771935381e-07,
"loss": 0.2562,
"step": 12992
},
{
"epoch": 0.97,
"learning_rate": 7.194066096505121e-07,
"loss": 0.2038,
"step": 13056
},
{
"epoch": 0.98,
"learning_rate": 7.177436384753458e-07,
"loss": 0.1829,
"step": 13120
},
{
"epoch": 0.98,
"learning_rate": 7.160542709323197e-07,
"loss": 0.217,
"step": 13184
},
{
"epoch": 0.99,
"learning_rate": 7.143649033892935e-07,
"loss": 0.2303,
"step": 13248
},
{
"epoch": 0.99,
"learning_rate": 7.126755358462675e-07,
"loss": 0.1996,
"step": 13312
},
{
"epoch": 1.0,
"learning_rate": 7.109861683032415e-07,
"loss": 0.206,
"step": 13376
}
],
"logging_steps": 64,
"max_steps": 40302,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 4.564199225032704e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}