TinyLlama-v1.1-Tiny-Agent-Test / trainer_state.json
Josephgflowers's picture
End of training
3fea9c6 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9987515605493134,
"eval_steps": 500,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0024968789013732834,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5487,
"step": 1
},
{
"epoch": 0.004993757802746567,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5726,
"step": 2
},
{
"epoch": 0.00749063670411985,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.4761,
"step": 3
},
{
"epoch": 0.009987515605493134,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5582,
"step": 4
},
{
"epoch": 0.012484394506866416,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5577,
"step": 5
},
{
"epoch": 0.0149812734082397,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5281,
"step": 6
},
{
"epoch": 0.017478152309612985,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5385,
"step": 7
},
{
"epoch": 0.019975031210986267,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.4239,
"step": 8
},
{
"epoch": 0.02247191011235955,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.558,
"step": 9
},
{
"epoch": 0.024968789013732832,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.4404,
"step": 10
},
{
"epoch": 0.02746566791510612,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5149,
"step": 11
},
{
"epoch": 0.0299625468164794,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5407,
"step": 12
},
{
"epoch": 0.03245942571785269,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5754,
"step": 13
},
{
"epoch": 0.03495630461922597,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5222,
"step": 14
},
{
"epoch": 0.03745318352059925,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5261,
"step": 15
},
{
"epoch": 0.039950062421972535,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5199,
"step": 16
},
{
"epoch": 0.04244694132334582,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5327,
"step": 17
},
{
"epoch": 0.0449438202247191,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.4925,
"step": 18
},
{
"epoch": 0.04744069912609238,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5452,
"step": 19
},
{
"epoch": 0.049937578027465665,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.4986,
"step": 20
},
{
"epoch": 0.052434456928838954,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.5148,
"step": 21
},
{
"epoch": 0.05493133583021224,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.6131,
"step": 22
},
{
"epoch": 0.05742821473158552,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 2.534,
"step": 23
},
{
"epoch": 0.0599250936329588,
"grad_norm": 3.498404026031494,
"learning_rate": 4.9875000000000006e-05,
"loss": 2.5259,
"step": 24
},
{
"epoch": 0.062421972534332085,
"grad_norm": 3.7281525135040283,
"learning_rate": 4.975e-05,
"loss": 2.5641,
"step": 25
},
{
"epoch": 0.06491885143570537,
"grad_norm": 3.4878628253936768,
"learning_rate": 4.962500000000001e-05,
"loss": 2.5001,
"step": 26
},
{
"epoch": 0.06741573033707865,
"grad_norm": 3.498518228530884,
"learning_rate": 4.9500000000000004e-05,
"loss": 2.4923,
"step": 27
},
{
"epoch": 0.06991260923845194,
"grad_norm": 3.5697684288024902,
"learning_rate": 4.937500000000001e-05,
"loss": 2.4743,
"step": 28
},
{
"epoch": 0.07240948813982521,
"grad_norm": 3.58793044090271,
"learning_rate": 4.9250000000000004e-05,
"loss": 2.4403,
"step": 29
},
{
"epoch": 0.0749063670411985,
"grad_norm": 3.395378828048706,
"learning_rate": 4.9125e-05,
"loss": 2.4839,
"step": 30
},
{
"epoch": 0.07740324594257178,
"grad_norm": 3.4821157455444336,
"learning_rate": 4.9e-05,
"loss": 2.4865,
"step": 31
},
{
"epoch": 0.07990012484394507,
"grad_norm": 3.5381717681884766,
"learning_rate": 4.8875e-05,
"loss": 2.3919,
"step": 32
},
{
"epoch": 0.08239700374531835,
"grad_norm": 3.7879738807678223,
"learning_rate": 4.875e-05,
"loss": 2.5253,
"step": 33
},
{
"epoch": 0.08489388264669163,
"grad_norm": 3.9536428451538086,
"learning_rate": 4.8625e-05,
"loss": 2.557,
"step": 34
},
{
"epoch": 0.08739076154806492,
"grad_norm": 3.5281002521514893,
"learning_rate": 4.85e-05,
"loss": 2.419,
"step": 35
},
{
"epoch": 0.0898876404494382,
"grad_norm": 3.8065526485443115,
"learning_rate": 4.8375000000000004e-05,
"loss": 2.4839,
"step": 36
},
{
"epoch": 0.09238451935081149,
"grad_norm": 3.48492431640625,
"learning_rate": 4.825e-05,
"loss": 2.3443,
"step": 37
},
{
"epoch": 0.09488139825218476,
"grad_norm": 3.5769503116607666,
"learning_rate": 4.8125000000000004e-05,
"loss": 2.5158,
"step": 38
},
{
"epoch": 0.09737827715355805,
"grad_norm": 3.5777034759521484,
"learning_rate": 4.8e-05,
"loss": 2.403,
"step": 39
},
{
"epoch": 0.09987515605493133,
"grad_norm": 3.471339225769043,
"learning_rate": 4.7875000000000005e-05,
"loss": 2.3998,
"step": 40
},
{
"epoch": 0.10237203495630462,
"grad_norm": 3.6594278812408447,
"learning_rate": 4.775e-05,
"loss": 2.4084,
"step": 41
},
{
"epoch": 0.10486891385767791,
"grad_norm": 3.5339417457580566,
"learning_rate": 4.7625000000000006e-05,
"loss": 2.4,
"step": 42
},
{
"epoch": 0.10736579275905118,
"grad_norm": 3.4090983867645264,
"learning_rate": 4.75e-05,
"loss": 2.367,
"step": 43
},
{
"epoch": 0.10986267166042447,
"grad_norm": 3.769968032836914,
"learning_rate": 4.7375e-05,
"loss": 2.3624,
"step": 44
},
{
"epoch": 0.11235955056179775,
"grad_norm": 3.788815975189209,
"learning_rate": 4.7249999999999997e-05,
"loss": 2.4006,
"step": 45
},
{
"epoch": 0.11485642946317104,
"grad_norm": 3.7179384231567383,
"learning_rate": 4.7125e-05,
"loss": 2.376,
"step": 46
},
{
"epoch": 0.11735330836454431,
"grad_norm": 3.4289679527282715,
"learning_rate": 4.7e-05,
"loss": 2.3354,
"step": 47
},
{
"epoch": 0.1198501872659176,
"grad_norm": 3.5412650108337402,
"learning_rate": 4.6875e-05,
"loss": 2.3317,
"step": 48
},
{
"epoch": 0.12234706616729088,
"grad_norm": 3.5559499263763428,
"learning_rate": 4.6750000000000005e-05,
"loss": 2.3663,
"step": 49
},
{
"epoch": 0.12484394506866417,
"grad_norm": 3.6865787506103516,
"learning_rate": 4.6625e-05,
"loss": 2.4062,
"step": 50
},
{
"epoch": 0.12734082397003746,
"grad_norm": 3.417897939682007,
"learning_rate": 4.6500000000000005e-05,
"loss": 2.3314,
"step": 51
},
{
"epoch": 0.12983770287141075,
"grad_norm": 3.5215134620666504,
"learning_rate": 4.6375e-05,
"loss": 2.367,
"step": 52
},
{
"epoch": 0.132334581772784,
"grad_norm": 3.478131055831909,
"learning_rate": 4.6250000000000006e-05,
"loss": 2.285,
"step": 53
},
{
"epoch": 0.1348314606741573,
"grad_norm": 3.8263564109802246,
"learning_rate": 4.6125e-05,
"loss": 2.402,
"step": 54
},
{
"epoch": 0.1373283395755306,
"grad_norm": 3.4977402687072754,
"learning_rate": 4.600000000000001e-05,
"loss": 2.317,
"step": 55
},
{
"epoch": 0.13982521847690388,
"grad_norm": 3.5797126293182373,
"learning_rate": 4.5875000000000004e-05,
"loss": 2.3097,
"step": 56
},
{
"epoch": 0.14232209737827714,
"grad_norm": 3.6681716442108154,
"learning_rate": 4.575e-05,
"loss": 2.3766,
"step": 57
},
{
"epoch": 0.14481897627965043,
"grad_norm": 3.6064581871032715,
"learning_rate": 4.5625e-05,
"loss": 2.2548,
"step": 58
},
{
"epoch": 0.14731585518102372,
"grad_norm": 3.680893659591675,
"learning_rate": 4.55e-05,
"loss": 2.4249,
"step": 59
},
{
"epoch": 0.149812734082397,
"grad_norm": 3.5588841438293457,
"learning_rate": 4.5375e-05,
"loss": 2.3109,
"step": 60
},
{
"epoch": 0.1523096129837703,
"grad_norm": 3.4901130199432373,
"learning_rate": 4.525e-05,
"loss": 2.2421,
"step": 61
},
{
"epoch": 0.15480649188514356,
"grad_norm": 3.5400235652923584,
"learning_rate": 4.5125e-05,
"loss": 2.3226,
"step": 62
},
{
"epoch": 0.15730337078651685,
"grad_norm": 3.578420877456665,
"learning_rate": 4.5e-05,
"loss": 2.2904,
"step": 63
},
{
"epoch": 0.15980024968789014,
"grad_norm": 3.583136558532715,
"learning_rate": 4.4875e-05,
"loss": 2.3255,
"step": 64
},
{
"epoch": 0.16229712858926343,
"grad_norm": 3.35066819190979,
"learning_rate": 4.4750000000000004e-05,
"loss": 2.2183,
"step": 65
},
{
"epoch": 0.1647940074906367,
"grad_norm": 3.4735934734344482,
"learning_rate": 4.4625e-05,
"loss": 2.2754,
"step": 66
},
{
"epoch": 0.16729088639200998,
"grad_norm": 3.3307180404663086,
"learning_rate": 4.4500000000000004e-05,
"loss": 2.2964,
"step": 67
},
{
"epoch": 0.16978776529338327,
"grad_norm": 3.516148567199707,
"learning_rate": 4.4375e-05,
"loss": 2.3107,
"step": 68
},
{
"epoch": 0.17228464419475656,
"grad_norm": 3.4239909648895264,
"learning_rate": 4.4250000000000005e-05,
"loss": 2.2945,
"step": 69
},
{
"epoch": 0.17478152309612985,
"grad_norm": 3.507624626159668,
"learning_rate": 4.4125e-05,
"loss": 2.2859,
"step": 70
},
{
"epoch": 0.1772784019975031,
"grad_norm": 3.6821298599243164,
"learning_rate": 4.4000000000000006e-05,
"loss": 2.3248,
"step": 71
},
{
"epoch": 0.1797752808988764,
"grad_norm": 3.3753108978271484,
"learning_rate": 4.3875e-05,
"loss": 2.2001,
"step": 72
},
{
"epoch": 0.1822721598002497,
"grad_norm": 3.4027931690216064,
"learning_rate": 4.375e-05,
"loss": 2.2668,
"step": 73
},
{
"epoch": 0.18476903870162298,
"grad_norm": 3.524763584136963,
"learning_rate": 4.3625e-05,
"loss": 2.2686,
"step": 74
},
{
"epoch": 0.18726591760299627,
"grad_norm": 3.5769248008728027,
"learning_rate": 4.35e-05,
"loss": 2.2757,
"step": 75
},
{
"epoch": 0.18976279650436953,
"grad_norm": 3.5016684532165527,
"learning_rate": 4.3375000000000004e-05,
"loss": 2.2218,
"step": 76
},
{
"epoch": 0.19225967540574282,
"grad_norm": 3.45440411567688,
"learning_rate": 4.325e-05,
"loss": 2.2405,
"step": 77
},
{
"epoch": 0.1947565543071161,
"grad_norm": 3.5838842391967773,
"learning_rate": 4.3125000000000005e-05,
"loss": 2.2426,
"step": 78
},
{
"epoch": 0.1972534332084894,
"grad_norm": 3.716230869293213,
"learning_rate": 4.3e-05,
"loss": 2.2819,
"step": 79
},
{
"epoch": 0.19975031210986266,
"grad_norm": 3.258978843688965,
"learning_rate": 4.2875000000000005e-05,
"loss": 2.2049,
"step": 80
},
{
"epoch": 0.20224719101123595,
"grad_norm": 3.575076103210449,
"learning_rate": 4.275e-05,
"loss": 2.2412,
"step": 81
},
{
"epoch": 0.20474406991260924,
"grad_norm": 3.5371599197387695,
"learning_rate": 4.2625000000000006e-05,
"loss": 2.2206,
"step": 82
},
{
"epoch": 0.20724094881398253,
"grad_norm": 3.6981263160705566,
"learning_rate": 4.25e-05,
"loss": 2.266,
"step": 83
},
{
"epoch": 0.20973782771535582,
"grad_norm": 3.451237678527832,
"learning_rate": 4.237500000000001e-05,
"loss": 2.2564,
"step": 84
},
{
"epoch": 0.21223470661672908,
"grad_norm": 3.4362707138061523,
"learning_rate": 4.2250000000000004e-05,
"loss": 2.1987,
"step": 85
},
{
"epoch": 0.21473158551810237,
"grad_norm": 3.45649790763855,
"learning_rate": 4.2125e-05,
"loss": 2.2001,
"step": 86
},
{
"epoch": 0.21722846441947566,
"grad_norm": 3.476231575012207,
"learning_rate": 4.2e-05,
"loss": 2.1378,
"step": 87
},
{
"epoch": 0.21972534332084895,
"grad_norm": 3.5050230026245117,
"learning_rate": 4.1875e-05,
"loss": 2.1478,
"step": 88
},
{
"epoch": 0.2222222222222222,
"grad_norm": 3.455080509185791,
"learning_rate": 4.175e-05,
"loss": 2.2395,
"step": 89
},
{
"epoch": 0.2247191011235955,
"grad_norm": 3.500718832015991,
"learning_rate": 4.1625e-05,
"loss": 2.1794,
"step": 90
},
{
"epoch": 0.2272159800249688,
"grad_norm": 3.53946852684021,
"learning_rate": 4.15e-05,
"loss": 2.2581,
"step": 91
},
{
"epoch": 0.22971285892634208,
"grad_norm": 3.506479024887085,
"learning_rate": 4.1375e-05,
"loss": 2.2028,
"step": 92
},
{
"epoch": 0.23220973782771537,
"grad_norm": 3.4707953929901123,
"learning_rate": 4.125e-05,
"loss": 2.1435,
"step": 93
},
{
"epoch": 0.23470661672908863,
"grad_norm": 3.4014856815338135,
"learning_rate": 4.1125000000000004e-05,
"loss": 2.2146,
"step": 94
},
{
"epoch": 0.23720349563046192,
"grad_norm": 3.42364764213562,
"learning_rate": 4.1e-05,
"loss": 2.1824,
"step": 95
},
{
"epoch": 0.2397003745318352,
"grad_norm": 3.480703115463257,
"learning_rate": 4.0875000000000004e-05,
"loss": 2.2208,
"step": 96
},
{
"epoch": 0.2421972534332085,
"grad_norm": 3.6021103858947754,
"learning_rate": 4.075e-05,
"loss": 2.1939,
"step": 97
},
{
"epoch": 0.24469413233458176,
"grad_norm": 3.673717498779297,
"learning_rate": 4.0625000000000005e-05,
"loss": 2.234,
"step": 98
},
{
"epoch": 0.24719101123595505,
"grad_norm": 3.511613368988037,
"learning_rate": 4.05e-05,
"loss": 2.2176,
"step": 99
},
{
"epoch": 0.24968789013732834,
"grad_norm": 3.5998849868774414,
"learning_rate": 4.0375e-05,
"loss": 2.2259,
"step": 100
},
{
"epoch": 0.25218476903870163,
"grad_norm": 3.4577770233154297,
"learning_rate": 4.025e-05,
"loss": 2.2238,
"step": 101
},
{
"epoch": 0.2546816479400749,
"grad_norm": 3.612593173980713,
"learning_rate": 4.0125e-05,
"loss": 2.161,
"step": 102
},
{
"epoch": 0.2571785268414482,
"grad_norm": 3.477313280105591,
"learning_rate": 4e-05,
"loss": 2.1839,
"step": 103
},
{
"epoch": 0.2596754057428215,
"grad_norm": 3.553819417953491,
"learning_rate": 3.9875e-05,
"loss": 2.2249,
"step": 104
},
{
"epoch": 0.26217228464419473,
"grad_norm": 3.412799596786499,
"learning_rate": 3.9750000000000004e-05,
"loss": 2.1834,
"step": 105
},
{
"epoch": 0.264669163545568,
"grad_norm": 3.4956414699554443,
"learning_rate": 3.9625e-05,
"loss": 2.1456,
"step": 106
},
{
"epoch": 0.2671660424469413,
"grad_norm": 3.6447088718414307,
"learning_rate": 3.9500000000000005e-05,
"loss": 2.166,
"step": 107
},
{
"epoch": 0.2696629213483146,
"grad_norm": 3.6700491905212402,
"learning_rate": 3.9375e-05,
"loss": 2.2626,
"step": 108
},
{
"epoch": 0.2721598002496879,
"grad_norm": 3.570895195007324,
"learning_rate": 3.9250000000000005e-05,
"loss": 2.1324,
"step": 109
},
{
"epoch": 0.2746566791510612,
"grad_norm": 3.456331968307495,
"learning_rate": 3.9125e-05,
"loss": 2.1244,
"step": 110
},
{
"epoch": 0.27715355805243447,
"grad_norm": 3.4046988487243652,
"learning_rate": 3.9000000000000006e-05,
"loss": 2.1525,
"step": 111
},
{
"epoch": 0.27965043695380776,
"grad_norm": 3.423374652862549,
"learning_rate": 3.8875e-05,
"loss": 2.1114,
"step": 112
},
{
"epoch": 0.28214731585518105,
"grad_norm": 3.3426084518432617,
"learning_rate": 3.875e-05,
"loss": 2.1863,
"step": 113
},
{
"epoch": 0.2846441947565543,
"grad_norm": 3.2898874282836914,
"learning_rate": 3.8625e-05,
"loss": 2.2121,
"step": 114
},
{
"epoch": 0.28714107365792757,
"grad_norm": 3.395939826965332,
"learning_rate": 3.85e-05,
"loss": 2.1401,
"step": 115
},
{
"epoch": 0.28963795255930086,
"grad_norm": 3.3747150897979736,
"learning_rate": 3.8375e-05,
"loss": 2.0959,
"step": 116
},
{
"epoch": 0.29213483146067415,
"grad_norm": 3.5609467029571533,
"learning_rate": 3.825e-05,
"loss": 2.1268,
"step": 117
},
{
"epoch": 0.29463171036204744,
"grad_norm": 3.6404829025268555,
"learning_rate": 3.8125e-05,
"loss": 2.184,
"step": 118
},
{
"epoch": 0.29712858926342073,
"grad_norm": 3.50461745262146,
"learning_rate": 3.8e-05,
"loss": 2.168,
"step": 119
},
{
"epoch": 0.299625468164794,
"grad_norm": 3.4648733139038086,
"learning_rate": 3.7875e-05,
"loss": 2.1526,
"step": 120
},
{
"epoch": 0.3021223470661673,
"grad_norm": 3.696610450744629,
"learning_rate": 3.775e-05,
"loss": 2.204,
"step": 121
},
{
"epoch": 0.3046192259675406,
"grad_norm": 3.4781978130340576,
"learning_rate": 3.7625e-05,
"loss": 2.1915,
"step": 122
},
{
"epoch": 0.30711610486891383,
"grad_norm": 3.490053176879883,
"learning_rate": 3.7500000000000003e-05,
"loss": 2.1437,
"step": 123
},
{
"epoch": 0.3096129837702871,
"grad_norm": 3.452174186706543,
"learning_rate": 3.737500000000001e-05,
"loss": 2.1535,
"step": 124
},
{
"epoch": 0.3121098626716604,
"grad_norm": 3.5188889503479004,
"learning_rate": 3.7250000000000004e-05,
"loss": 2.1696,
"step": 125
},
{
"epoch": 0.3146067415730337,
"grad_norm": 3.452965021133423,
"learning_rate": 3.7125e-05,
"loss": 2.1077,
"step": 126
},
{
"epoch": 0.317103620474407,
"grad_norm": 3.4781739711761475,
"learning_rate": 3.7e-05,
"loss": 2.1442,
"step": 127
},
{
"epoch": 0.3196004993757803,
"grad_norm": 3.455982208251953,
"learning_rate": 3.6875e-05,
"loss": 2.2422,
"step": 128
},
{
"epoch": 0.32209737827715357,
"grad_norm": 3.735812187194824,
"learning_rate": 3.675e-05,
"loss": 2.211,
"step": 129
},
{
"epoch": 0.32459425717852686,
"grad_norm": 3.7122321128845215,
"learning_rate": 3.6625e-05,
"loss": 2.1534,
"step": 130
},
{
"epoch": 0.32709113607990015,
"grad_norm": 3.407907724380493,
"learning_rate": 3.65e-05,
"loss": 2.135,
"step": 131
},
{
"epoch": 0.3295880149812734,
"grad_norm": 3.610645055770874,
"learning_rate": 3.6375e-05,
"loss": 2.1437,
"step": 132
},
{
"epoch": 0.33208489388264667,
"grad_norm": 3.316847085952759,
"learning_rate": 3.625e-05,
"loss": 2.1594,
"step": 133
},
{
"epoch": 0.33458177278401996,
"grad_norm": 3.504835367202759,
"learning_rate": 3.6125000000000004e-05,
"loss": 2.1369,
"step": 134
},
{
"epoch": 0.33707865168539325,
"grad_norm": 3.4886667728424072,
"learning_rate": 3.6e-05,
"loss": 2.1854,
"step": 135
},
{
"epoch": 0.33957553058676654,
"grad_norm": 3.4116599559783936,
"learning_rate": 3.5875000000000005e-05,
"loss": 2.0741,
"step": 136
},
{
"epoch": 0.34207240948813983,
"grad_norm": 3.4653735160827637,
"learning_rate": 3.575e-05,
"loss": 2.1779,
"step": 137
},
{
"epoch": 0.3445692883895131,
"grad_norm": 3.496469497680664,
"learning_rate": 3.5625000000000005e-05,
"loss": 2.1337,
"step": 138
},
{
"epoch": 0.3470661672908864,
"grad_norm": 3.4037115573883057,
"learning_rate": 3.55e-05,
"loss": 2.1346,
"step": 139
},
{
"epoch": 0.3495630461922597,
"grad_norm": 3.6134746074676514,
"learning_rate": 3.5375e-05,
"loss": 2.212,
"step": 140
},
{
"epoch": 0.352059925093633,
"grad_norm": 3.444700002670288,
"learning_rate": 3.525e-05,
"loss": 2.1676,
"step": 141
},
{
"epoch": 0.3545568039950062,
"grad_norm": 3.404010534286499,
"learning_rate": 3.5125e-05,
"loss": 2.0873,
"step": 142
},
{
"epoch": 0.3570536828963795,
"grad_norm": 3.3055148124694824,
"learning_rate": 3.5e-05,
"loss": 2.1762,
"step": 143
},
{
"epoch": 0.3595505617977528,
"grad_norm": 3.5183520317077637,
"learning_rate": 3.4875e-05,
"loss": 2.0908,
"step": 144
},
{
"epoch": 0.3620474406991261,
"grad_norm": 3.661907911300659,
"learning_rate": 3.475e-05,
"loss": 2.0899,
"step": 145
},
{
"epoch": 0.3645443196004994,
"grad_norm": 3.574948787689209,
"learning_rate": 3.4625e-05,
"loss": 2.1531,
"step": 146
},
{
"epoch": 0.36704119850187267,
"grad_norm": 3.4745309352874756,
"learning_rate": 3.45e-05,
"loss": 2.1238,
"step": 147
},
{
"epoch": 0.36953807740324596,
"grad_norm": 3.6377320289611816,
"learning_rate": 3.4375e-05,
"loss": 2.0556,
"step": 148
},
{
"epoch": 0.37203495630461925,
"grad_norm": 3.3080575466156006,
"learning_rate": 3.4250000000000006e-05,
"loss": 2.1218,
"step": 149
},
{
"epoch": 0.37453183520599254,
"grad_norm": 3.2884228229522705,
"learning_rate": 3.4125e-05,
"loss": 2.0843,
"step": 150
},
{
"epoch": 0.37702871410736577,
"grad_norm": 3.4235734939575195,
"learning_rate": 3.4000000000000007e-05,
"loss": 2.1042,
"step": 151
},
{
"epoch": 0.37952559300873906,
"grad_norm": 3.284189462661743,
"learning_rate": 3.3875000000000003e-05,
"loss": 2.0937,
"step": 152
},
{
"epoch": 0.38202247191011235,
"grad_norm": 3.311265468597412,
"learning_rate": 3.375000000000001e-05,
"loss": 2.0621,
"step": 153
},
{
"epoch": 0.38451935081148564,
"grad_norm": 3.5135247707366943,
"learning_rate": 3.3625000000000004e-05,
"loss": 2.1317,
"step": 154
},
{
"epoch": 0.38701622971285893,
"grad_norm": 3.428800582885742,
"learning_rate": 3.35e-05,
"loss": 2.1447,
"step": 155
},
{
"epoch": 0.3895131086142322,
"grad_norm": 3.4077048301696777,
"learning_rate": 3.3375e-05,
"loss": 2.1757,
"step": 156
},
{
"epoch": 0.3920099875156055,
"grad_norm": 3.572735071182251,
"learning_rate": 3.325e-05,
"loss": 2.0373,
"step": 157
},
{
"epoch": 0.3945068664169788,
"grad_norm": 3.465317487716675,
"learning_rate": 3.3125e-05,
"loss": 2.0783,
"step": 158
},
{
"epoch": 0.3970037453183521,
"grad_norm": 3.5976178646087646,
"learning_rate": 3.3e-05,
"loss": 2.2142,
"step": 159
},
{
"epoch": 0.3995006242197253,
"grad_norm": 3.576270341873169,
"learning_rate": 3.2875e-05,
"loss": 2.134,
"step": 160
},
{
"epoch": 0.4019975031210986,
"grad_norm": 3.536389112472534,
"learning_rate": 3.275e-05,
"loss": 2.1068,
"step": 161
},
{
"epoch": 0.4044943820224719,
"grad_norm": 3.45173716545105,
"learning_rate": 3.2625e-05,
"loss": 2.0449,
"step": 162
},
{
"epoch": 0.4069912609238452,
"grad_norm": 3.498258352279663,
"learning_rate": 3.2500000000000004e-05,
"loss": 2.1712,
"step": 163
},
{
"epoch": 0.4094881398252185,
"grad_norm": 3.2850704193115234,
"learning_rate": 3.2375e-05,
"loss": 2.0633,
"step": 164
},
{
"epoch": 0.41198501872659177,
"grad_norm": 3.3497467041015625,
"learning_rate": 3.2250000000000005e-05,
"loss": 2.1995,
"step": 165
},
{
"epoch": 0.41448189762796506,
"grad_norm": 3.4341518878936768,
"learning_rate": 3.2125e-05,
"loss": 2.1297,
"step": 166
},
{
"epoch": 0.41697877652933835,
"grad_norm": 3.3831026554107666,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.198,
"step": 167
},
{
"epoch": 0.41947565543071164,
"grad_norm": 3.450352191925049,
"learning_rate": 3.1875e-05,
"loss": 2.092,
"step": 168
},
{
"epoch": 0.42197253433208487,
"grad_norm": 3.3830325603485107,
"learning_rate": 3.175e-05,
"loss": 2.1015,
"step": 169
},
{
"epoch": 0.42446941323345816,
"grad_norm": 3.548405885696411,
"learning_rate": 3.1624999999999996e-05,
"loss": 2.0894,
"step": 170
},
{
"epoch": 0.42696629213483145,
"grad_norm": 3.675614595413208,
"learning_rate": 3.15e-05,
"loss": 2.1759,
"step": 171
},
{
"epoch": 0.42946317103620474,
"grad_norm": 3.520315408706665,
"learning_rate": 3.1375e-05,
"loss": 2.1231,
"step": 172
},
{
"epoch": 0.43196004993757803,
"grad_norm": 3.604353666305542,
"learning_rate": 3.125e-05,
"loss": 2.048,
"step": 173
},
{
"epoch": 0.4344569288389513,
"grad_norm": 3.609004259109497,
"learning_rate": 3.1125000000000004e-05,
"loss": 2.1223,
"step": 174
},
{
"epoch": 0.4369538077403246,
"grad_norm": 3.4398860931396484,
"learning_rate": 3.1e-05,
"loss": 2.0657,
"step": 175
},
{
"epoch": 0.4394506866416979,
"grad_norm": 3.4411044120788574,
"learning_rate": 3.0875000000000005e-05,
"loss": 2.0593,
"step": 176
},
{
"epoch": 0.4419475655430712,
"grad_norm": 3.5043869018554688,
"learning_rate": 3.075e-05,
"loss": 2.157,
"step": 177
},
{
"epoch": 0.4444444444444444,
"grad_norm": 3.3451061248779297,
"learning_rate": 3.0625000000000006e-05,
"loss": 1.996,
"step": 178
},
{
"epoch": 0.4469413233458177,
"grad_norm": 3.6858675479888916,
"learning_rate": 3.05e-05,
"loss": 2.1263,
"step": 179
},
{
"epoch": 0.449438202247191,
"grad_norm": 3.5967984199523926,
"learning_rate": 3.0375000000000003e-05,
"loss": 2.0165,
"step": 180
},
{
"epoch": 0.4519350811485643,
"grad_norm": 3.5284011363983154,
"learning_rate": 3.025e-05,
"loss": 2.1286,
"step": 181
},
{
"epoch": 0.4544319600499376,
"grad_norm": 3.548715353012085,
"learning_rate": 3.0125000000000004e-05,
"loss": 2.0539,
"step": 182
},
{
"epoch": 0.45692883895131087,
"grad_norm": 3.52622127532959,
"learning_rate": 3e-05,
"loss": 2.1254,
"step": 183
},
{
"epoch": 0.45942571785268416,
"grad_norm": 3.3532912731170654,
"learning_rate": 2.9875000000000004e-05,
"loss": 2.1257,
"step": 184
},
{
"epoch": 0.46192259675405745,
"grad_norm": 3.4587035179138184,
"learning_rate": 2.975e-05,
"loss": 2.1171,
"step": 185
},
{
"epoch": 0.46441947565543074,
"grad_norm": 3.5046117305755615,
"learning_rate": 2.9625000000000002e-05,
"loss": 2.1057,
"step": 186
},
{
"epoch": 0.46691635455680397,
"grad_norm": 3.33771014213562,
"learning_rate": 2.95e-05,
"loss": 2.0668,
"step": 187
},
{
"epoch": 0.46941323345817726,
"grad_norm": 3.402855157852173,
"learning_rate": 2.9375000000000003e-05,
"loss": 2.087,
"step": 188
},
{
"epoch": 0.47191011235955055,
"grad_norm": 3.417536735534668,
"learning_rate": 2.925e-05,
"loss": 1.9994,
"step": 189
},
{
"epoch": 0.47440699126092384,
"grad_norm": 3.627957582473755,
"learning_rate": 2.9125000000000003e-05,
"loss": 2.1349,
"step": 190
},
{
"epoch": 0.4769038701622971,
"grad_norm": 3.5531859397888184,
"learning_rate": 2.9e-05,
"loss": 2.1836,
"step": 191
},
{
"epoch": 0.4794007490636704,
"grad_norm": 3.5431745052337646,
"learning_rate": 2.8875e-05,
"loss": 2.0185,
"step": 192
},
{
"epoch": 0.4818976279650437,
"grad_norm": 3.592146158218384,
"learning_rate": 2.8749999999999997e-05,
"loss": 2.0973,
"step": 193
},
{
"epoch": 0.484394506866417,
"grad_norm": 3.4691829681396484,
"learning_rate": 2.8625e-05,
"loss": 2.1199,
"step": 194
},
{
"epoch": 0.4868913857677903,
"grad_norm": 3.599349021911621,
"learning_rate": 2.8499999999999998e-05,
"loss": 2.0849,
"step": 195
},
{
"epoch": 0.4893882646691635,
"grad_norm": 3.5513803958892822,
"learning_rate": 2.8375000000000002e-05,
"loss": 2.0859,
"step": 196
},
{
"epoch": 0.4918851435705368,
"grad_norm": 3.4182136058807373,
"learning_rate": 2.825e-05,
"loss": 2.0096,
"step": 197
},
{
"epoch": 0.4943820224719101,
"grad_norm": 3.347532272338867,
"learning_rate": 2.8125000000000003e-05,
"loss": 2.1039,
"step": 198
},
{
"epoch": 0.4968789013732834,
"grad_norm": 3.5202083587646484,
"learning_rate": 2.8000000000000003e-05,
"loss": 2.0436,
"step": 199
},
{
"epoch": 0.4993757802746567,
"grad_norm": 3.5688531398773193,
"learning_rate": 2.7875e-05,
"loss": 2.0736,
"step": 200
},
{
"epoch": 0.50187265917603,
"grad_norm": 3.531306743621826,
"learning_rate": 2.7750000000000004e-05,
"loss": 2.0244,
"step": 201
},
{
"epoch": 0.5043695380774033,
"grad_norm": 3.595841884613037,
"learning_rate": 2.7625e-05,
"loss": 2.0808,
"step": 202
},
{
"epoch": 0.5068664169787765,
"grad_norm": 3.610381603240967,
"learning_rate": 2.7500000000000004e-05,
"loss": 2.0863,
"step": 203
},
{
"epoch": 0.5093632958801498,
"grad_norm": 3.2456705570220947,
"learning_rate": 2.7375e-05,
"loss": 2.1102,
"step": 204
},
{
"epoch": 0.5118601747815231,
"grad_norm": 3.5384883880615234,
"learning_rate": 2.725e-05,
"loss": 2.0491,
"step": 205
},
{
"epoch": 0.5143570536828964,
"grad_norm": 3.4325191974639893,
"learning_rate": 2.7125000000000002e-05,
"loss": 2.0562,
"step": 206
},
{
"epoch": 0.5168539325842697,
"grad_norm": 3.428877115249634,
"learning_rate": 2.7000000000000002e-05,
"loss": 2.0329,
"step": 207
},
{
"epoch": 0.519350811485643,
"grad_norm": 3.451172351837158,
"learning_rate": 2.6875e-05,
"loss": 2.1357,
"step": 208
},
{
"epoch": 0.5218476903870163,
"grad_norm": 3.5145444869995117,
"learning_rate": 2.6750000000000003e-05,
"loss": 2.133,
"step": 209
},
{
"epoch": 0.5243445692883895,
"grad_norm": 3.452249050140381,
"learning_rate": 2.6625e-05,
"loss": 2.033,
"step": 210
},
{
"epoch": 0.5268414481897628,
"grad_norm": 3.493157148361206,
"learning_rate": 2.6500000000000004e-05,
"loss": 2.0387,
"step": 211
},
{
"epoch": 0.529338327091136,
"grad_norm": 3.4883360862731934,
"learning_rate": 2.6375e-05,
"loss": 2.0182,
"step": 212
},
{
"epoch": 0.5318352059925093,
"grad_norm": 3.377523183822632,
"learning_rate": 2.625e-05,
"loss": 2.0963,
"step": 213
},
{
"epoch": 0.5343320848938826,
"grad_norm": 3.4430289268493652,
"learning_rate": 2.6124999999999998e-05,
"loss": 2.0959,
"step": 214
},
{
"epoch": 0.5368289637952559,
"grad_norm": 3.380902051925659,
"learning_rate": 2.6000000000000002e-05,
"loss": 2.0883,
"step": 215
},
{
"epoch": 0.5393258426966292,
"grad_norm": 3.437469005584717,
"learning_rate": 2.5875e-05,
"loss": 2.0548,
"step": 216
},
{
"epoch": 0.5418227215980025,
"grad_norm": 3.628032684326172,
"learning_rate": 2.5750000000000002e-05,
"loss": 2.0784,
"step": 217
},
{
"epoch": 0.5443196004993758,
"grad_norm": 3.2870864868164062,
"learning_rate": 2.5625e-05,
"loss": 2.0463,
"step": 218
},
{
"epoch": 0.5468164794007491,
"grad_norm": 3.5962319374084473,
"learning_rate": 2.5500000000000003e-05,
"loss": 2.0625,
"step": 219
},
{
"epoch": 0.5493133583021224,
"grad_norm": 3.3193917274475098,
"learning_rate": 2.5375e-05,
"loss": 2.0249,
"step": 220
},
{
"epoch": 0.5518102372034956,
"grad_norm": 3.4375598430633545,
"learning_rate": 2.525e-05,
"loss": 2.0802,
"step": 221
},
{
"epoch": 0.5543071161048689,
"grad_norm": 3.500824451446533,
"learning_rate": 2.5124999999999997e-05,
"loss": 2.0309,
"step": 222
},
{
"epoch": 0.5568039950062422,
"grad_norm": 3.5241281986236572,
"learning_rate": 2.5e-05,
"loss": 2.1013,
"step": 223
},
{
"epoch": 0.5593008739076155,
"grad_norm": 3.4705541133880615,
"learning_rate": 2.4875e-05,
"loss": 2.0883,
"step": 224
},
{
"epoch": 0.5617977528089888,
"grad_norm": 3.4071896076202393,
"learning_rate": 2.4750000000000002e-05,
"loss": 2.0965,
"step": 225
},
{
"epoch": 0.5642946317103621,
"grad_norm": 3.315619707107544,
"learning_rate": 2.4625000000000002e-05,
"loss": 2.0697,
"step": 226
},
{
"epoch": 0.5667915106117354,
"grad_norm": 3.280471086502075,
"learning_rate": 2.45e-05,
"loss": 2.1179,
"step": 227
},
{
"epoch": 0.5692883895131086,
"grad_norm": 3.7654521465301514,
"learning_rate": 2.4375e-05,
"loss": 2.0855,
"step": 228
},
{
"epoch": 0.5717852684144819,
"grad_norm": 3.7220211029052734,
"learning_rate": 2.425e-05,
"loss": 2.0319,
"step": 229
},
{
"epoch": 0.5742821473158551,
"grad_norm": 3.419952154159546,
"learning_rate": 2.4125e-05,
"loss": 2.0362,
"step": 230
},
{
"epoch": 0.5767790262172284,
"grad_norm": 3.46474552154541,
"learning_rate": 2.4e-05,
"loss": 2.0325,
"step": 231
},
{
"epoch": 0.5792759051186017,
"grad_norm": 3.272773027420044,
"learning_rate": 2.3875e-05,
"loss": 2.0735,
"step": 232
},
{
"epoch": 0.581772784019975,
"grad_norm": 3.659705877304077,
"learning_rate": 2.375e-05,
"loss": 2.1283,
"step": 233
},
{
"epoch": 0.5842696629213483,
"grad_norm": 3.303420305252075,
"learning_rate": 2.3624999999999998e-05,
"loss": 2.1808,
"step": 234
},
{
"epoch": 0.5867665418227216,
"grad_norm": 3.622915744781494,
"learning_rate": 2.35e-05,
"loss": 2.0583,
"step": 235
},
{
"epoch": 0.5892634207240949,
"grad_norm": 3.3635072708129883,
"learning_rate": 2.3375000000000002e-05,
"loss": 2.0519,
"step": 236
},
{
"epoch": 0.5917602996254682,
"grad_norm": 3.5549280643463135,
"learning_rate": 2.3250000000000003e-05,
"loss": 2.0682,
"step": 237
},
{
"epoch": 0.5942571785268415,
"grad_norm": 3.578655958175659,
"learning_rate": 2.3125000000000003e-05,
"loss": 2.077,
"step": 238
},
{
"epoch": 0.5967540574282147,
"grad_norm": 3.611335277557373,
"learning_rate": 2.3000000000000003e-05,
"loss": 1.9911,
"step": 239
},
{
"epoch": 0.599250936329588,
"grad_norm": 3.3821637630462646,
"learning_rate": 2.2875e-05,
"loss": 2.0082,
"step": 240
},
{
"epoch": 0.6017478152309613,
"grad_norm": 3.4852335453033447,
"learning_rate": 2.275e-05,
"loss": 2.0278,
"step": 241
},
{
"epoch": 0.6042446941323346,
"grad_norm": 3.525944948196411,
"learning_rate": 2.2625e-05,
"loss": 2.0914,
"step": 242
},
{
"epoch": 0.6067415730337079,
"grad_norm": 3.3227696418762207,
"learning_rate": 2.25e-05,
"loss": 2.107,
"step": 243
},
{
"epoch": 0.6092384519350812,
"grad_norm": 3.669677257537842,
"learning_rate": 2.2375000000000002e-05,
"loss": 1.9829,
"step": 244
},
{
"epoch": 0.6117353308364545,
"grad_norm": 3.625420570373535,
"learning_rate": 2.2250000000000002e-05,
"loss": 2.0123,
"step": 245
},
{
"epoch": 0.6142322097378277,
"grad_norm": 3.4239187240600586,
"learning_rate": 2.2125000000000002e-05,
"loss": 2.0562,
"step": 246
},
{
"epoch": 0.616729088639201,
"grad_norm": 3.5444185733795166,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.0755,
"step": 247
},
{
"epoch": 0.6192259675405742,
"grad_norm": 3.500282049179077,
"learning_rate": 2.1875e-05,
"loss": 2.0275,
"step": 248
},
{
"epoch": 0.6217228464419475,
"grad_norm": 3.4052162170410156,
"learning_rate": 2.175e-05,
"loss": 2.0654,
"step": 249
},
{
"epoch": 0.6242197253433208,
"grad_norm": 3.5831384658813477,
"learning_rate": 2.1625e-05,
"loss": 1.994,
"step": 250
},
{
"epoch": 0.6267166042446941,
"grad_norm": 3.322357654571533,
"learning_rate": 2.15e-05,
"loss": 2.0476,
"step": 251
},
{
"epoch": 0.6292134831460674,
"grad_norm": 3.543062448501587,
"learning_rate": 2.1375e-05,
"loss": 2.0585,
"step": 252
},
{
"epoch": 0.6317103620474407,
"grad_norm": 3.521042823791504,
"learning_rate": 2.125e-05,
"loss": 2.0239,
"step": 253
},
{
"epoch": 0.634207240948814,
"grad_norm": 3.395559549331665,
"learning_rate": 2.1125000000000002e-05,
"loss": 2.0957,
"step": 254
},
{
"epoch": 0.6367041198501873,
"grad_norm": 3.567340135574341,
"learning_rate": 2.1e-05,
"loss": 2.0649,
"step": 255
},
{
"epoch": 0.6392009987515606,
"grad_norm": 3.397399663925171,
"learning_rate": 2.0875e-05,
"loss": 2.1739,
"step": 256
},
{
"epoch": 0.6416978776529338,
"grad_norm": 3.4432034492492676,
"learning_rate": 2.075e-05,
"loss": 2.0686,
"step": 257
},
{
"epoch": 0.6441947565543071,
"grad_norm": 3.4990758895874023,
"learning_rate": 2.0625e-05,
"loss": 2.1194,
"step": 258
},
{
"epoch": 0.6466916354556804,
"grad_norm": 3.497478723526001,
"learning_rate": 2.05e-05,
"loss": 2.0429,
"step": 259
},
{
"epoch": 0.6491885143570537,
"grad_norm": 3.4457273483276367,
"learning_rate": 2.0375e-05,
"loss": 2.1038,
"step": 260
},
{
"epoch": 0.651685393258427,
"grad_norm": 3.3803672790527344,
"learning_rate": 2.025e-05,
"loss": 2.1119,
"step": 261
},
{
"epoch": 0.6541822721598003,
"grad_norm": 3.474200963973999,
"learning_rate": 2.0125e-05,
"loss": 2.0346,
"step": 262
},
{
"epoch": 0.6566791510611736,
"grad_norm": 3.4010913372039795,
"learning_rate": 2e-05,
"loss": 2.0361,
"step": 263
},
{
"epoch": 0.6591760299625468,
"grad_norm": 3.391678810119629,
"learning_rate": 1.9875000000000002e-05,
"loss": 2.0216,
"step": 264
},
{
"epoch": 0.66167290886392,
"grad_norm": 3.484393835067749,
"learning_rate": 1.9750000000000002e-05,
"loss": 2.1634,
"step": 265
},
{
"epoch": 0.6641697877652933,
"grad_norm": 3.491408586502075,
"learning_rate": 1.9625000000000003e-05,
"loss": 2.0471,
"step": 266
},
{
"epoch": 0.6666666666666666,
"grad_norm": 3.562328815460205,
"learning_rate": 1.9500000000000003e-05,
"loss": 2.0928,
"step": 267
},
{
"epoch": 0.6691635455680399,
"grad_norm": 3.6033616065979004,
"learning_rate": 1.9375e-05,
"loss": 2.0641,
"step": 268
},
{
"epoch": 0.6716604244694132,
"grad_norm": 3.441002130508423,
"learning_rate": 1.925e-05,
"loss": 2.0484,
"step": 269
},
{
"epoch": 0.6741573033707865,
"grad_norm": 3.4448623657226562,
"learning_rate": 1.9125e-05,
"loss": 2.0558,
"step": 270
},
{
"epoch": 0.6766541822721598,
"grad_norm": 3.481809377670288,
"learning_rate": 1.9e-05,
"loss": 2.0449,
"step": 271
},
{
"epoch": 0.6791510611735331,
"grad_norm": 3.2882351875305176,
"learning_rate": 1.8875e-05,
"loss": 1.9441,
"step": 272
},
{
"epoch": 0.6816479400749064,
"grad_norm": 3.5338022708892822,
"learning_rate": 1.8750000000000002e-05,
"loss": 2.1015,
"step": 273
},
{
"epoch": 0.6841448189762797,
"grad_norm": 3.349963665008545,
"learning_rate": 1.8625000000000002e-05,
"loss": 2.0868,
"step": 274
},
{
"epoch": 0.686641697877653,
"grad_norm": 3.562603712081909,
"learning_rate": 1.85e-05,
"loss": 2.0308,
"step": 275
},
{
"epoch": 0.6891385767790262,
"grad_norm": 3.484811782836914,
"learning_rate": 1.8375e-05,
"loss": 2.0972,
"step": 276
},
{
"epoch": 0.6916354556803995,
"grad_norm": 3.4616386890411377,
"learning_rate": 1.825e-05,
"loss": 2.0084,
"step": 277
},
{
"epoch": 0.6941323345817728,
"grad_norm": 3.5441646575927734,
"learning_rate": 1.8125e-05,
"loss": 2.0395,
"step": 278
},
{
"epoch": 0.6966292134831461,
"grad_norm": 3.5133986473083496,
"learning_rate": 1.8e-05,
"loss": 2.0973,
"step": 279
},
{
"epoch": 0.6991260923845194,
"grad_norm": 3.6960537433624268,
"learning_rate": 1.7875e-05,
"loss": 1.9632,
"step": 280
},
{
"epoch": 0.7016229712858927,
"grad_norm": 3.499337911605835,
"learning_rate": 1.775e-05,
"loss": 2.0925,
"step": 281
},
{
"epoch": 0.704119850187266,
"grad_norm": 3.451720952987671,
"learning_rate": 1.7625e-05,
"loss": 2.0816,
"step": 282
},
{
"epoch": 0.7066167290886392,
"grad_norm": 3.540565252304077,
"learning_rate": 1.75e-05,
"loss": 2.0853,
"step": 283
},
{
"epoch": 0.7091136079900124,
"grad_norm": 3.5862390995025635,
"learning_rate": 1.7375e-05,
"loss": 1.9933,
"step": 284
},
{
"epoch": 0.7116104868913857,
"grad_norm": 3.436612844467163,
"learning_rate": 1.725e-05,
"loss": 2.0519,
"step": 285
},
{
"epoch": 0.714107365792759,
"grad_norm": 3.5170860290527344,
"learning_rate": 1.7125000000000003e-05,
"loss": 2.0087,
"step": 286
},
{
"epoch": 0.7166042446941323,
"grad_norm": 3.613799571990967,
"learning_rate": 1.7000000000000003e-05,
"loss": 2.0785,
"step": 287
},
{
"epoch": 0.7191011235955056,
"grad_norm": 3.4286880493164062,
"learning_rate": 1.6875000000000004e-05,
"loss": 2.0805,
"step": 288
},
{
"epoch": 0.7215980024968789,
"grad_norm": 3.4460251331329346,
"learning_rate": 1.675e-05,
"loss": 2.0529,
"step": 289
},
{
"epoch": 0.7240948813982522,
"grad_norm": 3.5601372718811035,
"learning_rate": 1.6625e-05,
"loss": 2.0795,
"step": 290
},
{
"epoch": 0.7265917602996255,
"grad_norm": 3.3969712257385254,
"learning_rate": 1.65e-05,
"loss": 2.0261,
"step": 291
},
{
"epoch": 0.7290886392009988,
"grad_norm": 3.285691738128662,
"learning_rate": 1.6375e-05,
"loss": 2.0902,
"step": 292
},
{
"epoch": 0.731585518102372,
"grad_norm": 3.482919454574585,
"learning_rate": 1.6250000000000002e-05,
"loss": 2.0239,
"step": 293
},
{
"epoch": 0.7340823970037453,
"grad_norm": 3.489551544189453,
"learning_rate": 1.6125000000000002e-05,
"loss": 2.0235,
"step": 294
},
{
"epoch": 0.7365792759051186,
"grad_norm": 3.461838960647583,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.0562,
"step": 295
},
{
"epoch": 0.7390761548064919,
"grad_norm": 3.3764636516571045,
"learning_rate": 1.5875e-05,
"loss": 2.0649,
"step": 296
},
{
"epoch": 0.7415730337078652,
"grad_norm": 3.4460861682891846,
"learning_rate": 1.575e-05,
"loss": 2.0674,
"step": 297
},
{
"epoch": 0.7440699126092385,
"grad_norm": 3.5665292739868164,
"learning_rate": 1.5625e-05,
"loss": 2.0219,
"step": 298
},
{
"epoch": 0.7465667915106118,
"grad_norm": 3.505133867263794,
"learning_rate": 1.55e-05,
"loss": 2.0278,
"step": 299
},
{
"epoch": 0.7490636704119851,
"grad_norm": 3.615962266921997,
"learning_rate": 1.5375e-05,
"loss": 2.0006,
"step": 300
},
{
"epoch": 0.7515605493133583,
"grad_norm": 3.462989330291748,
"learning_rate": 1.525e-05,
"loss": 2.0423,
"step": 301
},
{
"epoch": 0.7540574282147315,
"grad_norm": 3.351733446121216,
"learning_rate": 1.5125e-05,
"loss": 2.0353,
"step": 302
},
{
"epoch": 0.7565543071161048,
"grad_norm": 3.3703553676605225,
"learning_rate": 1.5e-05,
"loss": 2.0352,
"step": 303
},
{
"epoch": 0.7590511860174781,
"grad_norm": 3.578253984451294,
"learning_rate": 1.4875e-05,
"loss": 2.027,
"step": 304
},
{
"epoch": 0.7615480649188514,
"grad_norm": 3.304739236831665,
"learning_rate": 1.475e-05,
"loss": 2.0538,
"step": 305
},
{
"epoch": 0.7640449438202247,
"grad_norm": 3.5209975242614746,
"learning_rate": 1.4625e-05,
"loss": 1.9996,
"step": 306
},
{
"epoch": 0.766541822721598,
"grad_norm": 3.5905096530914307,
"learning_rate": 1.45e-05,
"loss": 2.0141,
"step": 307
},
{
"epoch": 0.7690387016229713,
"grad_norm": 3.383382558822632,
"learning_rate": 1.4374999999999999e-05,
"loss": 1.9648,
"step": 308
},
{
"epoch": 0.7715355805243446,
"grad_norm": 3.4596011638641357,
"learning_rate": 1.4249999999999999e-05,
"loss": 2.0336,
"step": 309
},
{
"epoch": 0.7740324594257179,
"grad_norm": 3.4215636253356934,
"learning_rate": 1.4125e-05,
"loss": 2.0386,
"step": 310
},
{
"epoch": 0.7765293383270911,
"grad_norm": 3.341522693634033,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.1078,
"step": 311
},
{
"epoch": 0.7790262172284644,
"grad_norm": 3.366393566131592,
"learning_rate": 1.3875000000000002e-05,
"loss": 2.079,
"step": 312
},
{
"epoch": 0.7815230961298377,
"grad_norm": 3.497201919555664,
"learning_rate": 1.3750000000000002e-05,
"loss": 2.0535,
"step": 313
},
{
"epoch": 0.784019975031211,
"grad_norm": 3.563197135925293,
"learning_rate": 1.3625e-05,
"loss": 2.0283,
"step": 314
},
{
"epoch": 0.7865168539325843,
"grad_norm": 3.4403908252716064,
"learning_rate": 1.3500000000000001e-05,
"loss": 2.0832,
"step": 315
},
{
"epoch": 0.7890137328339576,
"grad_norm": 3.4520885944366455,
"learning_rate": 1.3375000000000002e-05,
"loss": 2.0146,
"step": 316
},
{
"epoch": 0.7915106117353309,
"grad_norm": 3.5180275440216064,
"learning_rate": 1.3250000000000002e-05,
"loss": 2.004,
"step": 317
},
{
"epoch": 0.7940074906367042,
"grad_norm": 3.153761863708496,
"learning_rate": 1.3125e-05,
"loss": 2.0935,
"step": 318
},
{
"epoch": 0.7965043695380774,
"grad_norm": 3.468968629837036,
"learning_rate": 1.3000000000000001e-05,
"loss": 2.066,
"step": 319
},
{
"epoch": 0.7990012484394506,
"grad_norm": 3.5003297328948975,
"learning_rate": 1.2875000000000001e-05,
"loss": 1.9856,
"step": 320
},
{
"epoch": 0.8014981273408239,
"grad_norm": 3.5374064445495605,
"learning_rate": 1.2750000000000002e-05,
"loss": 2.0671,
"step": 321
},
{
"epoch": 0.8039950062421972,
"grad_norm": 3.659308433532715,
"learning_rate": 1.2625e-05,
"loss": 1.9864,
"step": 322
},
{
"epoch": 0.8064918851435705,
"grad_norm": 3.5156655311584473,
"learning_rate": 1.25e-05,
"loss": 1.9394,
"step": 323
},
{
"epoch": 0.8089887640449438,
"grad_norm": 3.326158285140991,
"learning_rate": 1.2375000000000001e-05,
"loss": 1.961,
"step": 324
},
{
"epoch": 0.8114856429463171,
"grad_norm": 3.4294004440307617,
"learning_rate": 1.225e-05,
"loss": 2.0097,
"step": 325
},
{
"epoch": 0.8139825218476904,
"grad_norm": 3.4218974113464355,
"learning_rate": 1.2125e-05,
"loss": 2.0647,
"step": 326
},
{
"epoch": 0.8164794007490637,
"grad_norm": 3.438875198364258,
"learning_rate": 1.2e-05,
"loss": 2.0179,
"step": 327
},
{
"epoch": 0.818976279650437,
"grad_norm": 3.523358106613159,
"learning_rate": 1.1875e-05,
"loss": 2.0494,
"step": 328
},
{
"epoch": 0.8214731585518102,
"grad_norm": 3.506168842315674,
"learning_rate": 1.175e-05,
"loss": 2.1027,
"step": 329
},
{
"epoch": 0.8239700374531835,
"grad_norm": 3.548112154006958,
"learning_rate": 1.1625000000000001e-05,
"loss": 2.0389,
"step": 330
},
{
"epoch": 0.8264669163545568,
"grad_norm": 3.5158162117004395,
"learning_rate": 1.1500000000000002e-05,
"loss": 1.978,
"step": 331
},
{
"epoch": 0.8289637952559301,
"grad_norm": 3.4753963947296143,
"learning_rate": 1.1375e-05,
"loss": 2.0421,
"step": 332
},
{
"epoch": 0.8314606741573034,
"grad_norm": 3.5032706260681152,
"learning_rate": 1.125e-05,
"loss": 1.9888,
"step": 333
},
{
"epoch": 0.8339575530586767,
"grad_norm": 3.2991061210632324,
"learning_rate": 1.1125000000000001e-05,
"loss": 2.0151,
"step": 334
},
{
"epoch": 0.83645443196005,
"grad_norm": 3.425863027572632,
"learning_rate": 1.1000000000000001e-05,
"loss": 2.0503,
"step": 335
},
{
"epoch": 0.8389513108614233,
"grad_norm": 3.469403028488159,
"learning_rate": 1.0875e-05,
"loss": 1.9425,
"step": 336
},
{
"epoch": 0.8414481897627965,
"grad_norm": 3.3070104122161865,
"learning_rate": 1.075e-05,
"loss": 2.0603,
"step": 337
},
{
"epoch": 0.8439450686641697,
"grad_norm": 3.418203115463257,
"learning_rate": 1.0625e-05,
"loss": 2.0018,
"step": 338
},
{
"epoch": 0.846441947565543,
"grad_norm": 3.5066540241241455,
"learning_rate": 1.05e-05,
"loss": 2.0122,
"step": 339
},
{
"epoch": 0.8489388264669163,
"grad_norm": 3.4425551891326904,
"learning_rate": 1.0375e-05,
"loss": 2.0225,
"step": 340
},
{
"epoch": 0.8514357053682896,
"grad_norm": 3.343202829360962,
"learning_rate": 1.025e-05,
"loss": 2.0755,
"step": 341
},
{
"epoch": 0.8539325842696629,
"grad_norm": 3.28155255317688,
"learning_rate": 1.0125e-05,
"loss": 1.9847,
"step": 342
},
{
"epoch": 0.8564294631710362,
"grad_norm": 3.3546323776245117,
"learning_rate": 1e-05,
"loss": 1.991,
"step": 343
},
{
"epoch": 0.8589263420724095,
"grad_norm": 3.420783758163452,
"learning_rate": 9.875000000000001e-06,
"loss": 2.0471,
"step": 344
},
{
"epoch": 0.8614232209737828,
"grad_norm": 3.347703456878662,
"learning_rate": 9.750000000000002e-06,
"loss": 2.0444,
"step": 345
},
{
"epoch": 0.8639200998751561,
"grad_norm": 3.4276270866394043,
"learning_rate": 9.625e-06,
"loss": 2.0548,
"step": 346
},
{
"epoch": 0.8664169787765293,
"grad_norm": 3.3684396743774414,
"learning_rate": 9.5e-06,
"loss": 2.0664,
"step": 347
},
{
"epoch": 0.8689138576779026,
"grad_norm": 3.5308725833892822,
"learning_rate": 9.375000000000001e-06,
"loss": 2.0263,
"step": 348
},
{
"epoch": 0.8714107365792759,
"grad_norm": 3.5037009716033936,
"learning_rate": 9.25e-06,
"loss": 2.0629,
"step": 349
},
{
"epoch": 0.8739076154806492,
"grad_norm": 3.3732502460479736,
"learning_rate": 9.125e-06,
"loss": 2.0872,
"step": 350
},
{
"epoch": 0.8764044943820225,
"grad_norm": 3.379492998123169,
"learning_rate": 9e-06,
"loss": 2.0494,
"step": 351
},
{
"epoch": 0.8789013732833958,
"grad_norm": 3.356729030609131,
"learning_rate": 8.875e-06,
"loss": 2.0578,
"step": 352
},
{
"epoch": 0.8813982521847691,
"grad_norm": 3.505227565765381,
"learning_rate": 8.75e-06,
"loss": 2.0547,
"step": 353
},
{
"epoch": 0.8838951310861424,
"grad_norm": 3.325188159942627,
"learning_rate": 8.625e-06,
"loss": 2.0479,
"step": 354
},
{
"epoch": 0.8863920099875156,
"grad_norm": 3.220914363861084,
"learning_rate": 8.500000000000002e-06,
"loss": 2.1145,
"step": 355
},
{
"epoch": 0.8888888888888888,
"grad_norm": 3.2536563873291016,
"learning_rate": 8.375e-06,
"loss": 2.1226,
"step": 356
},
{
"epoch": 0.8913857677902621,
"grad_norm": 3.4424164295196533,
"learning_rate": 8.25e-06,
"loss": 1.9732,
"step": 357
},
{
"epoch": 0.8938826466916354,
"grad_norm": 3.210689067840576,
"learning_rate": 8.125000000000001e-06,
"loss": 2.0682,
"step": 358
},
{
"epoch": 0.8963795255930087,
"grad_norm": 3.6276254653930664,
"learning_rate": 8.000000000000001e-06,
"loss": 1.9996,
"step": 359
},
{
"epoch": 0.898876404494382,
"grad_norm": 3.284266471862793,
"learning_rate": 7.875e-06,
"loss": 1.9988,
"step": 360
},
{
"epoch": 0.9013732833957553,
"grad_norm": 3.3102824687957764,
"learning_rate": 7.75e-06,
"loss": 2.0986,
"step": 361
},
{
"epoch": 0.9038701622971286,
"grad_norm": 3.4718074798583984,
"learning_rate": 7.625e-06,
"loss": 2.0236,
"step": 362
},
{
"epoch": 0.9063670411985019,
"grad_norm": 3.356231689453125,
"learning_rate": 7.5e-06,
"loss": 1.9603,
"step": 363
},
{
"epoch": 0.9088639200998752,
"grad_norm": 3.488931655883789,
"learning_rate": 7.375e-06,
"loss": 2.0287,
"step": 364
},
{
"epoch": 0.9113607990012484,
"grad_norm": 3.370278835296631,
"learning_rate": 7.25e-06,
"loss": 2.055,
"step": 365
},
{
"epoch": 0.9138576779026217,
"grad_norm": 3.357985019683838,
"learning_rate": 7.1249999999999995e-06,
"loss": 2.0225,
"step": 366
},
{
"epoch": 0.916354556803995,
"grad_norm": 3.3029778003692627,
"learning_rate": 7.000000000000001e-06,
"loss": 1.9724,
"step": 367
},
{
"epoch": 0.9188514357053683,
"grad_norm": 3.6066527366638184,
"learning_rate": 6.875000000000001e-06,
"loss": 2.0172,
"step": 368
},
{
"epoch": 0.9213483146067416,
"grad_norm": 3.4643936157226562,
"learning_rate": 6.750000000000001e-06,
"loss": 2.0598,
"step": 369
},
{
"epoch": 0.9238451935081149,
"grad_norm": 3.2209830284118652,
"learning_rate": 6.625000000000001e-06,
"loss": 2.0395,
"step": 370
},
{
"epoch": 0.9263420724094882,
"grad_norm": 3.308652639389038,
"learning_rate": 6.5000000000000004e-06,
"loss": 2.0576,
"step": 371
},
{
"epoch": 0.9288389513108615,
"grad_norm": 3.378284215927124,
"learning_rate": 6.375000000000001e-06,
"loss": 2.1037,
"step": 372
},
{
"epoch": 0.9313358302122348,
"grad_norm": 3.408998489379883,
"learning_rate": 6.25e-06,
"loss": 2.0508,
"step": 373
},
{
"epoch": 0.9338327091136079,
"grad_norm": 3.4758336544036865,
"learning_rate": 6.125e-06,
"loss": 2.0642,
"step": 374
},
{
"epoch": 0.9363295880149812,
"grad_norm": 3.3644943237304688,
"learning_rate": 6e-06,
"loss": 2.104,
"step": 375
},
{
"epoch": 0.9388264669163545,
"grad_norm": 3.3621973991394043,
"learning_rate": 5.875e-06,
"loss": 2.05,
"step": 376
},
{
"epoch": 0.9413233458177278,
"grad_norm": 3.3936052322387695,
"learning_rate": 5.750000000000001e-06,
"loss": 1.9648,
"step": 377
},
{
"epoch": 0.9438202247191011,
"grad_norm": 3.28177809715271,
"learning_rate": 5.625e-06,
"loss": 2.0129,
"step": 378
},
{
"epoch": 0.9463171036204744,
"grad_norm": 3.1901121139526367,
"learning_rate": 5.500000000000001e-06,
"loss": 2.0564,
"step": 379
},
{
"epoch": 0.9488139825218477,
"grad_norm": 3.4150338172912598,
"learning_rate": 5.375e-06,
"loss": 2.0344,
"step": 380
},
{
"epoch": 0.951310861423221,
"grad_norm": 3.3532180786132812,
"learning_rate": 5.25e-06,
"loss": 2.012,
"step": 381
},
{
"epoch": 0.9538077403245943,
"grad_norm": 3.434931993484497,
"learning_rate": 5.125e-06,
"loss": 2.073,
"step": 382
},
{
"epoch": 0.9563046192259675,
"grad_norm": 3.34334135055542,
"learning_rate": 5e-06,
"loss": 2.0716,
"step": 383
},
{
"epoch": 0.9588014981273408,
"grad_norm": 3.3420920372009277,
"learning_rate": 4.875000000000001e-06,
"loss": 2.0691,
"step": 384
},
{
"epoch": 0.9612983770287141,
"grad_norm": 3.648798942565918,
"learning_rate": 4.75e-06,
"loss": 2.0198,
"step": 385
},
{
"epoch": 0.9637952559300874,
"grad_norm": 3.2924463748931885,
"learning_rate": 4.625e-06,
"loss": 2.015,
"step": 386
},
{
"epoch": 0.9662921348314607,
"grad_norm": 3.2124977111816406,
"learning_rate": 4.5e-06,
"loss": 2.1013,
"step": 387
},
{
"epoch": 0.968789013732834,
"grad_norm": 3.4171626567840576,
"learning_rate": 4.375e-06,
"loss": 2.0419,
"step": 388
},
{
"epoch": 0.9712858926342073,
"grad_norm": 3.4217112064361572,
"learning_rate": 4.250000000000001e-06,
"loss": 2.0808,
"step": 389
},
{
"epoch": 0.9737827715355806,
"grad_norm": 3.281397581100464,
"learning_rate": 4.125e-06,
"loss": 2.0552,
"step": 390
},
{
"epoch": 0.9762796504369539,
"grad_norm": 3.3025379180908203,
"learning_rate": 4.000000000000001e-06,
"loss": 2.0196,
"step": 391
},
{
"epoch": 0.978776529338327,
"grad_norm": 3.261284112930298,
"learning_rate": 3.875e-06,
"loss": 1.903,
"step": 392
},
{
"epoch": 0.9812734082397003,
"grad_norm": 3.3036253452301025,
"learning_rate": 3.75e-06,
"loss": 2.0455,
"step": 393
},
{
"epoch": 0.9837702871410736,
"grad_norm": 3.4235925674438477,
"learning_rate": 3.625e-06,
"loss": 2.0393,
"step": 394
},
{
"epoch": 0.9862671660424469,
"grad_norm": 3.347456455230713,
"learning_rate": 3.5000000000000004e-06,
"loss": 2.0227,
"step": 395
},
{
"epoch": 0.9887640449438202,
"grad_norm": 3.3116769790649414,
"learning_rate": 3.3750000000000003e-06,
"loss": 2.0891,
"step": 396
},
{
"epoch": 0.9912609238451935,
"grad_norm": 3.2966830730438232,
"learning_rate": 3.2500000000000002e-06,
"loss": 2.0784,
"step": 397
},
{
"epoch": 0.9937578027465668,
"grad_norm": 3.4097273349761963,
"learning_rate": 3.125e-06,
"loss": 2.0751,
"step": 398
},
{
"epoch": 0.9962546816479401,
"grad_norm": 3.3749406337738037,
"learning_rate": 3e-06,
"loss": 2.0916,
"step": 399
},
{
"epoch": 0.9987515605493134,
"grad_norm": 3.322603225708008,
"learning_rate": 2.8750000000000004e-06,
"loss": 2.0949,
"step": 400
},
{
"epoch": 0.9987515605493134,
"step": 400,
"total_flos": 2.847507751108608e+17,
"train_loss": 2.1486885741353037,
"train_runtime": 92894.5901,
"train_samples_per_second": 0.241,
"train_steps_per_second": 0.004
}
],
"logging_steps": 1.0,
"max_steps": 400,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 400,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.847507751108608e+17,
"train_batch_size": 14,
"trial_name": null,
"trial_params": null
}