axolotl-ex / checkpoint-671 /trainer_state.json
Deadwalker0's picture
Upload folder using huggingface_hub
76503fe verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 168,
"global_step": 671,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 1.3745,
"step": 1
},
{
"epoch": 0.0,
"eval_loss": 1.6296857595443726,
"eval_runtime": 2.6662,
"eval_samples_per_second": 409.572,
"eval_steps_per_second": 25.88,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 2e-05,
"loss": 1.42,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 3e-05,
"loss": 1.3057,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 4e-05,
"loss": 1.2307,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 5e-05,
"loss": 1.289,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 6e-05,
"loss": 1.4111,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 7e-05,
"loss": 1.3089,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 8e-05,
"loss": 1.3204,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 9e-05,
"loss": 1.3575,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 1.3279,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 0.00011000000000000002,
"loss": 1.3149,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 0.00012,
"loss": 1.2578,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 0.00013000000000000002,
"loss": 1.2849,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 0.00014,
"loss": 1.2971,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 0.00015000000000000001,
"loss": 1.1473,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 0.00016,
"loss": 1.1943,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 0.00017,
"loss": 1.1877,
"step": 17
},
{
"epoch": 0.03,
"learning_rate": 0.00018,
"loss": 1.1984,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 0.00019,
"loss": 1.2647,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.217,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 0.00019999993046535236,
"loss": 1.0274,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 0.00019999972186150606,
"loss": 1.2122,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 0.00019999937418875124,
"loss": 1.1868,
"step": 23
},
{
"epoch": 0.04,
"learning_rate": 0.00019999888744757143,
"loss": 1.2345,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 0.00019999826163864348,
"loss": 1.2127,
"step": 25
},
{
"epoch": 0.04,
"learning_rate": 0.00019999749676283775,
"loss": 1.2114,
"step": 26
},
{
"epoch": 0.04,
"learning_rate": 0.00019999659282121792,
"loss": 1.2224,
"step": 27
},
{
"epoch": 0.04,
"learning_rate": 0.0001999955498150411,
"loss": 1.1517,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 0.0001999943677457578,
"loss": 1.1631,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 0.0001999930466150119,
"loss": 1.0465,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 0.0001999915864246407,
"loss": 1.1847,
"step": 31
},
{
"epoch": 0.05,
"learning_rate": 0.0001999899871766749,
"loss": 1.1238,
"step": 32
},
{
"epoch": 0.05,
"learning_rate": 0.0001999882488733385,
"loss": 1.1491,
"step": 33
},
{
"epoch": 0.05,
"learning_rate": 0.000199986371517049,
"loss": 1.276,
"step": 34
},
{
"epoch": 0.05,
"learning_rate": 0.0001999843551104172,
"loss": 1.0911,
"step": 35
},
{
"epoch": 0.05,
"learning_rate": 0.00019998219965624734,
"loss": 1.1276,
"step": 36
},
{
"epoch": 0.06,
"learning_rate": 0.00019997990515753693,
"loss": 1.0981,
"step": 37
},
{
"epoch": 0.06,
"learning_rate": 0.00019997747161747695,
"loss": 1.0901,
"step": 38
},
{
"epoch": 0.06,
"learning_rate": 0.0001999748990394517,
"loss": 1.096,
"step": 39
},
{
"epoch": 0.06,
"learning_rate": 0.00019997218742703887,
"loss": 1.122,
"step": 40
},
{
"epoch": 0.06,
"learning_rate": 0.00019996933678400946,
"loss": 1.1132,
"step": 41
},
{
"epoch": 0.06,
"learning_rate": 0.00019996634711432786,
"loss": 1.1498,
"step": 42
},
{
"epoch": 0.06,
"learning_rate": 0.00019996321842215173,
"loss": 1.0708,
"step": 43
},
{
"epoch": 0.07,
"learning_rate": 0.0001999599507118322,
"loss": 1.1154,
"step": 44
},
{
"epoch": 0.07,
"learning_rate": 0.00019995654398791355,
"loss": 1.2118,
"step": 45
},
{
"epoch": 0.07,
"learning_rate": 0.00019995299825513357,
"loss": 1.0919,
"step": 46
},
{
"epoch": 0.07,
"learning_rate": 0.00019994931351842327,
"loss": 1.1364,
"step": 47
},
{
"epoch": 0.07,
"learning_rate": 0.00019994548978290695,
"loss": 1.1442,
"step": 48
},
{
"epoch": 0.07,
"learning_rate": 0.0001999415270539023,
"loss": 1.1248,
"step": 49
},
{
"epoch": 0.07,
"learning_rate": 0.00019993742533692022,
"loss": 1.1366,
"step": 50
},
{
"epoch": 0.08,
"learning_rate": 0.00019993318463766495,
"loss": 1.1437,
"step": 51
},
{
"epoch": 0.08,
"learning_rate": 0.000199928804962034,
"loss": 1.1191,
"step": 52
},
{
"epoch": 0.08,
"learning_rate": 0.0001999242863161182,
"loss": 1.0786,
"step": 53
},
{
"epoch": 0.08,
"learning_rate": 0.00019991962870620153,
"loss": 1.1951,
"step": 54
},
{
"epoch": 0.08,
"learning_rate": 0.00019991483213876134,
"loss": 1.1321,
"step": 55
},
{
"epoch": 0.08,
"learning_rate": 0.00019990989662046818,
"loss": 1.0876,
"step": 56
},
{
"epoch": 0.08,
"learning_rate": 0.0001999048221581858,
"loss": 1.1794,
"step": 57
},
{
"epoch": 0.09,
"learning_rate": 0.00019989960875897126,
"loss": 1.1796,
"step": 58
},
{
"epoch": 0.09,
"learning_rate": 0.00019989425643007476,
"loss": 1.1165,
"step": 59
},
{
"epoch": 0.09,
"learning_rate": 0.0001998887651789398,
"loss": 1.1978,
"step": 60
},
{
"epoch": 0.09,
"learning_rate": 0.00019988313501320297,
"loss": 1.1693,
"step": 61
},
{
"epoch": 0.09,
"learning_rate": 0.00019987736594069414,
"loss": 1.1553,
"step": 62
},
{
"epoch": 0.09,
"learning_rate": 0.0001998714579694363,
"loss": 1.1959,
"step": 63
},
{
"epoch": 0.1,
"learning_rate": 0.00019986541110764565,
"loss": 1.1945,
"step": 64
},
{
"epoch": 0.1,
"learning_rate": 0.00019985922536373146,
"loss": 1.121,
"step": 65
},
{
"epoch": 0.1,
"learning_rate": 0.00019985290074629627,
"loss": 1.122,
"step": 66
},
{
"epoch": 0.1,
"learning_rate": 0.00019984643726413565,
"loss": 1.1435,
"step": 67
},
{
"epoch": 0.1,
"learning_rate": 0.00019983983492623833,
"loss": 1.0413,
"step": 68
},
{
"epoch": 0.1,
"learning_rate": 0.0001998330937417861,
"loss": 1.078,
"step": 69
},
{
"epoch": 0.1,
"learning_rate": 0.0001998262137201539,
"loss": 1.0811,
"step": 70
},
{
"epoch": 0.11,
"learning_rate": 0.00019981919487090972,
"loss": 1.1639,
"step": 71
},
{
"epoch": 0.11,
"learning_rate": 0.00019981203720381463,
"loss": 1.164,
"step": 72
},
{
"epoch": 0.11,
"learning_rate": 0.00019980474072882277,
"loss": 1.1006,
"step": 73
},
{
"epoch": 0.11,
"learning_rate": 0.00019979730545608126,
"loss": 1.1926,
"step": 74
},
{
"epoch": 0.11,
"learning_rate": 0.0001997897313959303,
"loss": 1.1129,
"step": 75
},
{
"epoch": 0.11,
"learning_rate": 0.00019978201855890308,
"loss": 1.1367,
"step": 76
},
{
"epoch": 0.11,
"learning_rate": 0.00019977416695572578,
"loss": 1.1495,
"step": 77
},
{
"epoch": 0.12,
"learning_rate": 0.0001997661765973176,
"loss": 1.1567,
"step": 78
},
{
"epoch": 0.12,
"learning_rate": 0.00019975804749479062,
"loss": 1.2102,
"step": 79
},
{
"epoch": 0.12,
"learning_rate": 0.00019974977965945,
"loss": 1.1175,
"step": 80
},
{
"epoch": 0.12,
"learning_rate": 0.0001997413731027937,
"loss": 1.1243,
"step": 81
},
{
"epoch": 0.12,
"learning_rate": 0.00019973282783651263,
"loss": 1.1406,
"step": 82
},
{
"epoch": 0.12,
"learning_rate": 0.00019972414387249072,
"loss": 1.09,
"step": 83
},
{
"epoch": 0.13,
"learning_rate": 0.00019971532122280464,
"loss": 1.0115,
"step": 84
},
{
"epoch": 0.13,
"learning_rate": 0.00019970635989972402,
"loss": 1.0328,
"step": 85
},
{
"epoch": 0.13,
"learning_rate": 0.00019969725991571128,
"loss": 1.1226,
"step": 86
},
{
"epoch": 0.13,
"learning_rate": 0.00019968802128342172,
"loss": 1.0747,
"step": 87
},
{
"epoch": 0.13,
"learning_rate": 0.00019967864401570343,
"loss": 1.119,
"step": 88
},
{
"epoch": 0.13,
"learning_rate": 0.00019966912812559732,
"loss": 1.1125,
"step": 89
},
{
"epoch": 0.13,
"learning_rate": 0.00019965947362633708,
"loss": 1.0734,
"step": 90
},
{
"epoch": 0.14,
"learning_rate": 0.0001996496805313491,
"loss": 1.1798,
"step": 91
},
{
"epoch": 0.14,
"learning_rate": 0.00019963974885425266,
"loss": 1.1461,
"step": 92
},
{
"epoch": 0.14,
"learning_rate": 0.0001996296786088596,
"loss": 1.0397,
"step": 93
},
{
"epoch": 0.14,
"learning_rate": 0.00019961946980917456,
"loss": 1.17,
"step": 94
},
{
"epoch": 0.14,
"learning_rate": 0.00019960912246939485,
"loss": 1.0679,
"step": 95
},
{
"epoch": 0.14,
"learning_rate": 0.00019959863660391045,
"loss": 1.0839,
"step": 96
},
{
"epoch": 0.14,
"learning_rate": 0.00019958801222730394,
"loss": 1.0937,
"step": 97
},
{
"epoch": 0.15,
"learning_rate": 0.00019957724935435063,
"loss": 1.1668,
"step": 98
},
{
"epoch": 0.15,
"learning_rate": 0.00019956634800001832,
"loss": 1.0858,
"step": 99
},
{
"epoch": 0.15,
"learning_rate": 0.00019955530817946748,
"loss": 1.0935,
"step": 100
},
{
"epoch": 0.15,
"learning_rate": 0.00019954412990805107,
"loss": 1.1046,
"step": 101
},
{
"epoch": 0.15,
"learning_rate": 0.00019953281320131468,
"loss": 1.1319,
"step": 102
},
{
"epoch": 0.15,
"learning_rate": 0.00019952135807499633,
"loss": 1.1108,
"step": 103
},
{
"epoch": 0.15,
"learning_rate": 0.0001995097645450266,
"loss": 1.0485,
"step": 104
},
{
"epoch": 0.16,
"learning_rate": 0.00019949803262752855,
"loss": 1.0862,
"step": 105
},
{
"epoch": 0.16,
"learning_rate": 0.00019948616233881768,
"loss": 1.268,
"step": 106
},
{
"epoch": 0.16,
"learning_rate": 0.00019947415369540189,
"loss": 1.0926,
"step": 107
},
{
"epoch": 0.16,
"learning_rate": 0.0001994620067139815,
"loss": 1.1427,
"step": 108
},
{
"epoch": 0.16,
"learning_rate": 0.00019944972141144928,
"loss": 1.0754,
"step": 109
},
{
"epoch": 0.16,
"learning_rate": 0.00019943729780489027,
"loss": 1.0044,
"step": 110
},
{
"epoch": 0.17,
"learning_rate": 0.0001994247359115819,
"loss": 1.1304,
"step": 111
},
{
"epoch": 0.17,
"learning_rate": 0.00019941203574899393,
"loss": 1.1683,
"step": 112
},
{
"epoch": 0.17,
"learning_rate": 0.00019939919733478838,
"loss": 1.1559,
"step": 113
},
{
"epoch": 0.17,
"learning_rate": 0.00019938622068681953,
"loss": 1.1879,
"step": 114
},
{
"epoch": 0.17,
"learning_rate": 0.00019937310582313392,
"loss": 1.0613,
"step": 115
},
{
"epoch": 0.17,
"learning_rate": 0.0001993598527619703,
"loss": 1.1196,
"step": 116
},
{
"epoch": 0.17,
"learning_rate": 0.0001993464615217596,
"loss": 1.0762,
"step": 117
},
{
"epoch": 0.18,
"learning_rate": 0.00019933293212112495,
"loss": 1.1059,
"step": 118
},
{
"epoch": 0.18,
"learning_rate": 0.00019931926457888156,
"loss": 1.0831,
"step": 119
},
{
"epoch": 0.18,
"learning_rate": 0.00019930545891403678,
"loss": 1.0552,
"step": 120
},
{
"epoch": 0.18,
"learning_rate": 0.00019929151514579008,
"loss": 1.15,
"step": 121
},
{
"epoch": 0.18,
"learning_rate": 0.00019927743329353295,
"loss": 1.1038,
"step": 122
},
{
"epoch": 0.18,
"learning_rate": 0.0001992632133768489,
"loss": 1.067,
"step": 123
},
{
"epoch": 0.18,
"learning_rate": 0.0001992488554155135,
"loss": 1.1311,
"step": 124
},
{
"epoch": 0.19,
"learning_rate": 0.00019923435942949426,
"loss": 1.1402,
"step": 125
},
{
"epoch": 0.19,
"learning_rate": 0.00019921972543895066,
"loss": 1.0453,
"step": 126
},
{
"epoch": 0.19,
"learning_rate": 0.00019920495346423402,
"loss": 1.1567,
"step": 127
},
{
"epoch": 0.19,
"learning_rate": 0.00019919004352588767,
"loss": 1.137,
"step": 128
},
{
"epoch": 0.19,
"learning_rate": 0.0001991749956446468,
"loss": 0.9986,
"step": 129
},
{
"epoch": 0.19,
"learning_rate": 0.00019915980984143832,
"loss": 1.083,
"step": 130
},
{
"epoch": 0.2,
"learning_rate": 0.00019914448613738106,
"loss": 1.0619,
"step": 131
},
{
"epoch": 0.2,
"learning_rate": 0.00019912902455378556,
"loss": 1.1294,
"step": 132
},
{
"epoch": 0.2,
"learning_rate": 0.00019911342511215414,
"loss": 1.0965,
"step": 133
},
{
"epoch": 0.2,
"learning_rate": 0.00019909768783418086,
"loss": 1.0216,
"step": 134
},
{
"epoch": 0.2,
"learning_rate": 0.00019908181274175138,
"loss": 1.0081,
"step": 135
},
{
"epoch": 0.2,
"learning_rate": 0.0001990657998569432,
"loss": 1.0246,
"step": 136
},
{
"epoch": 0.2,
"learning_rate": 0.0001990496492020252,
"loss": 1.1249,
"step": 137
},
{
"epoch": 0.21,
"learning_rate": 0.00019903336079945804,
"loss": 1.0518,
"step": 138
},
{
"epoch": 0.21,
"learning_rate": 0.00019901693467189386,
"loss": 1.189,
"step": 139
},
{
"epoch": 0.21,
"learning_rate": 0.00019900037084217637,
"loss": 1.1475,
"step": 140
},
{
"epoch": 0.21,
"learning_rate": 0.0001989836693333408,
"loss": 1.2259,
"step": 141
},
{
"epoch": 0.21,
"learning_rate": 0.0001989668301686138,
"loss": 1.0399,
"step": 142
},
{
"epoch": 0.21,
"learning_rate": 0.0001989498533714135,
"loss": 1.128,
"step": 143
},
{
"epoch": 0.21,
"learning_rate": 0.00019893273896534936,
"loss": 1.014,
"step": 144
},
{
"epoch": 0.22,
"learning_rate": 0.0001989154869742223,
"loss": 1.1552,
"step": 145
},
{
"epoch": 0.22,
"learning_rate": 0.00019889809742202455,
"loss": 1.1159,
"step": 146
},
{
"epoch": 0.22,
"learning_rate": 0.0001988805703329396,
"loss": 1.0218,
"step": 147
},
{
"epoch": 0.22,
"learning_rate": 0.00019886290573134228,
"loss": 1.1723,
"step": 148
},
{
"epoch": 0.22,
"learning_rate": 0.0001988451036417986,
"loss": 1.2132,
"step": 149
},
{
"epoch": 0.22,
"learning_rate": 0.00019882716408906585,
"loss": 1.112,
"step": 150
},
{
"epoch": 0.23,
"learning_rate": 0.0001988090870980924,
"loss": 1.0856,
"step": 151
},
{
"epoch": 0.23,
"learning_rate": 0.0001987908726940178,
"loss": 1.0951,
"step": 152
},
{
"epoch": 0.23,
"learning_rate": 0.00019877252090217271,
"loss": 1.0218,
"step": 153
},
{
"epoch": 0.23,
"learning_rate": 0.00019875403174807882,
"loss": 1.0552,
"step": 154
},
{
"epoch": 0.23,
"learning_rate": 0.00019873540525744887,
"loss": 1.1481,
"step": 155
},
{
"epoch": 0.23,
"learning_rate": 0.00019871664145618657,
"loss": 1.169,
"step": 156
},
{
"epoch": 0.23,
"learning_rate": 0.00019869774037038665,
"loss": 1.0802,
"step": 157
},
{
"epoch": 0.24,
"learning_rate": 0.0001986787020263347,
"loss": 1.0871,
"step": 158
},
{
"epoch": 0.24,
"learning_rate": 0.0001986595264505072,
"loss": 1.1022,
"step": 159
},
{
"epoch": 0.24,
"learning_rate": 0.00019864021366957147,
"loss": 1.0257,
"step": 160
},
{
"epoch": 0.24,
"learning_rate": 0.0001986207637103857,
"loss": 1.0986,
"step": 161
},
{
"epoch": 0.24,
"learning_rate": 0.00019860117659999878,
"loss": 1.0837,
"step": 162
},
{
"epoch": 0.24,
"learning_rate": 0.00019858145236565037,
"loss": 1.1895,
"step": 163
},
{
"epoch": 0.24,
"learning_rate": 0.00019856159103477086,
"loss": 1.052,
"step": 164
},
{
"epoch": 0.25,
"learning_rate": 0.00019854159263498123,
"loss": 1.1184,
"step": 165
},
{
"epoch": 0.25,
"learning_rate": 0.0001985214571940931,
"loss": 1.0895,
"step": 166
},
{
"epoch": 0.25,
"learning_rate": 0.00019850118474010872,
"loss": 1.0764,
"step": 167
},
{
"epoch": 0.25,
"learning_rate": 0.00019848077530122083,
"loss": 1.1387,
"step": 168
},
{
"epoch": 0.25,
"eval_loss": 1.084919810295105,
"eval_runtime": 2.6029,
"eval_samples_per_second": 419.538,
"eval_steps_per_second": 26.509,
"step": 168
},
{
"epoch": 0.25,
"learning_rate": 0.00019846022890581267,
"loss": 1.0826,
"step": 169
},
{
"epoch": 0.25,
"learning_rate": 0.000198439545582458,
"loss": 1.1366,
"step": 170
},
{
"epoch": 0.25,
"learning_rate": 0.000198418725359921,
"loss": 1.1349,
"step": 171
},
{
"epoch": 0.26,
"learning_rate": 0.00019839776826715614,
"loss": 1.0636,
"step": 172
},
{
"epoch": 0.26,
"learning_rate": 0.00019837667433330838,
"loss": 1.1216,
"step": 173
},
{
"epoch": 0.26,
"learning_rate": 0.0001983554435877128,
"loss": 1.1051,
"step": 174
},
{
"epoch": 0.26,
"learning_rate": 0.00019833407605989494,
"loss": 1.1558,
"step": 175
},
{
"epoch": 0.26,
"learning_rate": 0.00019831257177957044,
"loss": 1.0364,
"step": 176
},
{
"epoch": 0.26,
"learning_rate": 0.00019829093077664513,
"loss": 1.0665,
"step": 177
},
{
"epoch": 0.27,
"learning_rate": 0.00019826915308121504,
"loss": 1.1994,
"step": 178
},
{
"epoch": 0.27,
"learning_rate": 0.0001982472387235662,
"loss": 1.1434,
"step": 179
},
{
"epoch": 0.27,
"learning_rate": 0.0001982251877341748,
"loss": 1.081,
"step": 180
},
{
"epoch": 0.27,
"learning_rate": 0.000198203000143707,
"loss": 1.0653,
"step": 181
},
{
"epoch": 0.27,
"learning_rate": 0.0001981806759830189,
"loss": 1.0269,
"step": 182
},
{
"epoch": 0.27,
"learning_rate": 0.0001981582152831566,
"loss": 1.1167,
"step": 183
},
{
"epoch": 0.27,
"learning_rate": 0.00019813561807535598,
"loss": 1.0608,
"step": 184
},
{
"epoch": 0.28,
"learning_rate": 0.0001981128843910428,
"loss": 1.0989,
"step": 185
},
{
"epoch": 0.28,
"learning_rate": 0.0001980900142618327,
"loss": 1.1405,
"step": 186
},
{
"epoch": 0.28,
"learning_rate": 0.00019806700771953097,
"loss": 1.0359,
"step": 187
},
{
"epoch": 0.28,
"learning_rate": 0.0001980438647961327,
"loss": 1.1073,
"step": 188
},
{
"epoch": 0.28,
"learning_rate": 0.0001980205855238225,
"loss": 1.0338,
"step": 189
},
{
"epoch": 0.28,
"learning_rate": 0.00019799716993497475,
"loss": 1.1285,
"step": 190
},
{
"epoch": 0.28,
"learning_rate": 0.00019797361806215332,
"loss": 1.1277,
"step": 191
},
{
"epoch": 0.29,
"learning_rate": 0.00019794992993811165,
"loss": 1.119,
"step": 192
},
{
"epoch": 0.29,
"learning_rate": 0.00019792610559579265,
"loss": 1.1224,
"step": 193
},
{
"epoch": 0.29,
"learning_rate": 0.00019790214506832868,
"loss": 1.1438,
"step": 194
},
{
"epoch": 0.29,
"learning_rate": 0.0001978780483890414,
"loss": 1.1462,
"step": 195
},
{
"epoch": 0.29,
"learning_rate": 0.00019785381559144196,
"loss": 1.042,
"step": 196
},
{
"epoch": 0.29,
"learning_rate": 0.00019782944670923076,
"loss": 1.1022,
"step": 197
},
{
"epoch": 0.3,
"learning_rate": 0.00019780494177629735,
"loss": 1.0564,
"step": 198
},
{
"epoch": 0.3,
"learning_rate": 0.00019778030082672068,
"loss": 1.0471,
"step": 199
},
{
"epoch": 0.3,
"learning_rate": 0.00019775552389476864,
"loss": 1.0636,
"step": 200
},
{
"epoch": 0.3,
"learning_rate": 0.0001977306110148984,
"loss": 1.0917,
"step": 201
},
{
"epoch": 0.3,
"learning_rate": 0.00019770556222175608,
"loss": 1.1965,
"step": 202
},
{
"epoch": 0.3,
"learning_rate": 0.00019768037755017685,
"loss": 1.073,
"step": 203
},
{
"epoch": 0.3,
"learning_rate": 0.00019765505703518496,
"loss": 1.0636,
"step": 204
},
{
"epoch": 0.31,
"learning_rate": 0.00019762960071199333,
"loss": 1.087,
"step": 205
},
{
"epoch": 0.31,
"learning_rate": 0.000197604008616004,
"loss": 1.0569,
"step": 206
},
{
"epoch": 0.31,
"learning_rate": 0.00019757828078280766,
"loss": 1.08,
"step": 207
},
{
"epoch": 0.31,
"learning_rate": 0.00019755241724818387,
"loss": 1.1536,
"step": 208
},
{
"epoch": 0.31,
"learning_rate": 0.00019752641804810084,
"loss": 1.1514,
"step": 209
},
{
"epoch": 0.31,
"learning_rate": 0.00019750028321871546,
"loss": 1.0691,
"step": 210
},
{
"epoch": 0.31,
"learning_rate": 0.00019747401279637325,
"loss": 1.1289,
"step": 211
},
{
"epoch": 0.32,
"learning_rate": 0.00019744760681760832,
"loss": 1.0834,
"step": 212
},
{
"epoch": 0.32,
"learning_rate": 0.00019742106531914328,
"loss": 1.0762,
"step": 213
},
{
"epoch": 0.32,
"learning_rate": 0.0001973943883378892,
"loss": 1.0913,
"step": 214
},
{
"epoch": 0.32,
"learning_rate": 0.00019736757591094558,
"loss": 1.132,
"step": 215
},
{
"epoch": 0.32,
"learning_rate": 0.00019734062807560027,
"loss": 1.0894,
"step": 216
},
{
"epoch": 0.32,
"learning_rate": 0.00019731354486932944,
"loss": 1.0327,
"step": 217
},
{
"epoch": 0.32,
"learning_rate": 0.00019728632632979746,
"loss": 1.112,
"step": 218
},
{
"epoch": 0.33,
"learning_rate": 0.00019725897249485704,
"loss": 1.0718,
"step": 219
},
{
"epoch": 0.33,
"learning_rate": 0.00019723148340254892,
"loss": 1.077,
"step": 220
},
{
"epoch": 0.33,
"learning_rate": 0.00019720385909110198,
"loss": 1.0335,
"step": 221
},
{
"epoch": 0.33,
"learning_rate": 0.00019717609959893318,
"loss": 1.0483,
"step": 222
},
{
"epoch": 0.33,
"learning_rate": 0.00019714820496464746,
"loss": 1.0901,
"step": 223
},
{
"epoch": 0.33,
"learning_rate": 0.00019712017522703764,
"loss": 0.9921,
"step": 224
},
{
"epoch": 0.34,
"learning_rate": 0.00019709201042508455,
"loss": 1.0829,
"step": 225
},
{
"epoch": 0.34,
"learning_rate": 0.0001970637105979567,
"loss": 1.0705,
"step": 226
},
{
"epoch": 0.34,
"learning_rate": 0.0001970352757850105,
"loss": 1.0481,
"step": 227
},
{
"epoch": 0.34,
"learning_rate": 0.00019700670602579008,
"loss": 0.9846,
"step": 228
},
{
"epoch": 0.34,
"learning_rate": 0.0001969780013600272,
"loss": 1.1492,
"step": 229
},
{
"epoch": 0.34,
"learning_rate": 0.00019694916182764113,
"loss": 1.1745,
"step": 230
},
{
"epoch": 0.34,
"learning_rate": 0.00019692018746873892,
"loss": 1.0451,
"step": 231
},
{
"epoch": 0.35,
"learning_rate": 0.00019689107832361496,
"loss": 1.1217,
"step": 232
},
{
"epoch": 0.35,
"learning_rate": 0.00019686183443275116,
"loss": 1.0788,
"step": 233
},
{
"epoch": 0.35,
"learning_rate": 0.00019683245583681675,
"loss": 1.0703,
"step": 234
},
{
"epoch": 0.35,
"learning_rate": 0.00019680294257666837,
"loss": 1.1521,
"step": 235
},
{
"epoch": 0.35,
"learning_rate": 0.0001967732946933499,
"loss": 1.0659,
"step": 236
},
{
"epoch": 0.35,
"learning_rate": 0.00019674351222809242,
"loss": 1.0321,
"step": 237
},
{
"epoch": 0.35,
"learning_rate": 0.0001967135952223142,
"loss": 1.0555,
"step": 238
},
{
"epoch": 0.36,
"learning_rate": 0.00019668354371762066,
"loss": 1.0648,
"step": 239
},
{
"epoch": 0.36,
"learning_rate": 0.00019665335775580415,
"loss": 1.0723,
"step": 240
},
{
"epoch": 0.36,
"learning_rate": 0.0001966230373788441,
"loss": 1.0264,
"step": 241
},
{
"epoch": 0.36,
"learning_rate": 0.00019659258262890683,
"loss": 1.0331,
"step": 242
},
{
"epoch": 0.36,
"learning_rate": 0.00019656199354834558,
"loss": 1.1514,
"step": 243
},
{
"epoch": 0.36,
"learning_rate": 0.00019653127017970034,
"loss": 1.069,
"step": 244
},
{
"epoch": 0.37,
"learning_rate": 0.00019650041256569792,
"loss": 0.9623,
"step": 245
},
{
"epoch": 0.37,
"learning_rate": 0.00019646942074925172,
"loss": 1.0021,
"step": 246
},
{
"epoch": 0.37,
"learning_rate": 0.00019643829477346188,
"loss": 1.1131,
"step": 247
},
{
"epoch": 0.37,
"learning_rate": 0.0001964070346816151,
"loss": 1.1426,
"step": 248
},
{
"epoch": 0.37,
"learning_rate": 0.0001963756405171845,
"loss": 1.0761,
"step": 249
},
{
"epoch": 0.37,
"learning_rate": 0.00019634411232382978,
"loss": 1.1112,
"step": 250
},
{
"epoch": 0.37,
"learning_rate": 0.00019631245014539698,
"loss": 1.081,
"step": 251
},
{
"epoch": 0.38,
"learning_rate": 0.00019628065402591845,
"loss": 1.1446,
"step": 252
},
{
"epoch": 0.38,
"learning_rate": 0.00019624872400961284,
"loss": 1.045,
"step": 253
},
{
"epoch": 0.38,
"learning_rate": 0.00019621666014088494,
"loss": 1.0337,
"step": 254
},
{
"epoch": 0.38,
"learning_rate": 0.00019618446246432583,
"loss": 1.1764,
"step": 255
},
{
"epoch": 0.38,
"learning_rate": 0.00019615213102471257,
"loss": 1.0323,
"step": 256
},
{
"epoch": 0.38,
"learning_rate": 0.00019611966586700823,
"loss": 1.0073,
"step": 257
},
{
"epoch": 0.38,
"learning_rate": 0.00019608706703636188,
"loss": 1.1615,
"step": 258
},
{
"epoch": 0.39,
"learning_rate": 0.00019605433457810855,
"loss": 1.1209,
"step": 259
},
{
"epoch": 0.39,
"learning_rate": 0.00019602146853776894,
"loss": 1.0721,
"step": 260
},
{
"epoch": 0.39,
"learning_rate": 0.0001959884689610497,
"loss": 1.0967,
"step": 261
},
{
"epoch": 0.39,
"learning_rate": 0.00019595533589384308,
"loss": 1.0284,
"step": 262
},
{
"epoch": 0.39,
"learning_rate": 0.00019592206938222703,
"loss": 1.0148,
"step": 263
},
{
"epoch": 0.39,
"learning_rate": 0.00019588866947246498,
"loss": 1.1434,
"step": 264
},
{
"epoch": 0.39,
"learning_rate": 0.00019585513621100603,
"loss": 1.1125,
"step": 265
},
{
"epoch": 0.4,
"learning_rate": 0.0001958214696444846,
"loss": 1.0812,
"step": 266
},
{
"epoch": 0.4,
"learning_rate": 0.00019578766981972058,
"loss": 1.0611,
"step": 267
},
{
"epoch": 0.4,
"learning_rate": 0.00019575373678371909,
"loss": 1.1029,
"step": 268
},
{
"epoch": 0.4,
"learning_rate": 0.00019571967058367064,
"loss": 1.0692,
"step": 269
},
{
"epoch": 0.4,
"learning_rate": 0.00019568547126695083,
"loss": 1.0581,
"step": 270
},
{
"epoch": 0.4,
"learning_rate": 0.00019565113888112036,
"loss": 0.9841,
"step": 271
},
{
"epoch": 0.41,
"learning_rate": 0.00019561667347392508,
"loss": 1.0173,
"step": 272
},
{
"epoch": 0.41,
"learning_rate": 0.00019558207509329584,
"loss": 1.0805,
"step": 273
},
{
"epoch": 0.41,
"learning_rate": 0.00019554734378734824,
"loss": 1.088,
"step": 274
},
{
"epoch": 0.41,
"learning_rate": 0.00019551247960438296,
"loss": 1.0481,
"step": 275
},
{
"epoch": 0.41,
"learning_rate": 0.00019547748259288536,
"loss": 1.1747,
"step": 276
},
{
"epoch": 0.41,
"learning_rate": 0.0001954423528015255,
"loss": 1.0407,
"step": 277
},
{
"epoch": 0.41,
"learning_rate": 0.00019540709027915818,
"loss": 1.1412,
"step": 278
},
{
"epoch": 0.42,
"learning_rate": 0.0001953716950748227,
"loss": 1.075,
"step": 279
},
{
"epoch": 0.42,
"learning_rate": 0.00019533616723774294,
"loss": 0.9863,
"step": 280
},
{
"epoch": 0.42,
"learning_rate": 0.0001953005068173272,
"loss": 1.1426,
"step": 281
},
{
"epoch": 0.42,
"learning_rate": 0.0001952647138631682,
"loss": 1.0621,
"step": 282
},
{
"epoch": 0.42,
"learning_rate": 0.00019522878842504295,
"loss": 1.1007,
"step": 283
},
{
"epoch": 0.42,
"learning_rate": 0.00019519273055291266,
"loss": 1.0632,
"step": 284
},
{
"epoch": 0.42,
"learning_rate": 0.00019515654029692278,
"loss": 1.126,
"step": 285
},
{
"epoch": 0.43,
"learning_rate": 0.00019512021770740288,
"loss": 1.0946,
"step": 286
},
{
"epoch": 0.43,
"learning_rate": 0.0001950837628348665,
"loss": 1.0639,
"step": 287
},
{
"epoch": 0.43,
"learning_rate": 0.00019504717573001117,
"loss": 1.1432,
"step": 288
},
{
"epoch": 0.43,
"learning_rate": 0.00019501045644371832,
"loss": 1.0619,
"step": 289
},
{
"epoch": 0.43,
"learning_rate": 0.0001949736050270532,
"loss": 1.0597,
"step": 290
},
{
"epoch": 0.43,
"learning_rate": 0.00019493662153126481,
"loss": 1.0743,
"step": 291
},
{
"epoch": 0.44,
"learning_rate": 0.0001948995060077859,
"loss": 1.1114,
"step": 292
},
{
"epoch": 0.44,
"learning_rate": 0.00019486225850823266,
"loss": 1.1435,
"step": 293
},
{
"epoch": 0.44,
"learning_rate": 0.000194824879084405,
"loss": 1.1396,
"step": 294
},
{
"epoch": 0.44,
"learning_rate": 0.00019478736778828624,
"loss": 1.1597,
"step": 295
},
{
"epoch": 0.44,
"learning_rate": 0.00019474972467204297,
"loss": 1.0976,
"step": 296
},
{
"epoch": 0.44,
"learning_rate": 0.00019471194978802533,
"loss": 1.0829,
"step": 297
},
{
"epoch": 0.44,
"learning_rate": 0.0001946740431887665,
"loss": 1.0437,
"step": 298
},
{
"epoch": 0.45,
"learning_rate": 0.00019463600492698296,
"loss": 1.0835,
"step": 299
},
{
"epoch": 0.45,
"learning_rate": 0.00019459783505557424,
"loss": 1.0558,
"step": 300
},
{
"epoch": 0.45,
"learning_rate": 0.0001945595336276229,
"loss": 1.0656,
"step": 301
},
{
"epoch": 0.45,
"learning_rate": 0.00019452110069639452,
"loss": 1.1487,
"step": 302
},
{
"epoch": 0.45,
"learning_rate": 0.00019448253631533744,
"loss": 1.1383,
"step": 303
},
{
"epoch": 0.45,
"learning_rate": 0.00019444384053808288,
"loss": 1.1582,
"step": 304
},
{
"epoch": 0.45,
"learning_rate": 0.00019440501341844483,
"loss": 0.9999,
"step": 305
},
{
"epoch": 0.46,
"learning_rate": 0.00019436605501041987,
"loss": 1.1317,
"step": 306
},
{
"epoch": 0.46,
"learning_rate": 0.00019432696536818717,
"loss": 1.0944,
"step": 307
},
{
"epoch": 0.46,
"learning_rate": 0.00019428774454610843,
"loss": 1.1624,
"step": 308
},
{
"epoch": 0.46,
"learning_rate": 0.00019424839259872778,
"loss": 1.1644,
"step": 309
},
{
"epoch": 0.46,
"learning_rate": 0.00019420890958077167,
"loss": 1.0486,
"step": 310
},
{
"epoch": 0.46,
"learning_rate": 0.00019416929554714888,
"loss": 1.0705,
"step": 311
},
{
"epoch": 0.46,
"learning_rate": 0.00019412955055295034,
"loss": 1.023,
"step": 312
},
{
"epoch": 0.47,
"learning_rate": 0.00019408967465344917,
"loss": 1.1144,
"step": 313
},
{
"epoch": 0.47,
"learning_rate": 0.00019404966790410047,
"loss": 1.0378,
"step": 314
},
{
"epoch": 0.47,
"learning_rate": 0.00019400953036054138,
"loss": 1.036,
"step": 315
},
{
"epoch": 0.47,
"learning_rate": 0.00019396926207859084,
"loss": 1.0735,
"step": 316
},
{
"epoch": 0.47,
"learning_rate": 0.00019392886311424973,
"loss": 1.0259,
"step": 317
},
{
"epoch": 0.47,
"learning_rate": 0.0001938883335237006,
"loss": 1.1603,
"step": 318
},
{
"epoch": 0.48,
"learning_rate": 0.0001938476733633076,
"loss": 1.1282,
"step": 319
},
{
"epoch": 0.48,
"learning_rate": 0.0001938068826896166,
"loss": 1.063,
"step": 320
},
{
"epoch": 0.48,
"learning_rate": 0.00019376596155935486,
"loss": 1.1176,
"step": 321
},
{
"epoch": 0.48,
"learning_rate": 0.00019372491002943112,
"loss": 1.1307,
"step": 322
},
{
"epoch": 0.48,
"learning_rate": 0.00019368372815693549,
"loss": 1.0412,
"step": 323
},
{
"epoch": 0.48,
"learning_rate": 0.00019364241599913924,
"loss": 1.1353,
"step": 324
},
{
"epoch": 0.48,
"learning_rate": 0.00019360097361349494,
"loss": 1.1293,
"step": 325
},
{
"epoch": 0.49,
"learning_rate": 0.0001935594010576362,
"loss": 1.0885,
"step": 326
},
{
"epoch": 0.49,
"learning_rate": 0.00019351769838937775,
"loss": 1.0944,
"step": 327
},
{
"epoch": 0.49,
"learning_rate": 0.00019347586566671512,
"loss": 1.1435,
"step": 328
},
{
"epoch": 0.49,
"learning_rate": 0.0001934339029478248,
"loss": 1.1217,
"step": 329
},
{
"epoch": 0.49,
"learning_rate": 0.00019339181029106404,
"loss": 1.1801,
"step": 330
},
{
"epoch": 0.49,
"learning_rate": 0.00019334958775497083,
"loss": 1.1846,
"step": 331
},
{
"epoch": 0.49,
"learning_rate": 0.00019330723539826375,
"loss": 1.0897,
"step": 332
},
{
"epoch": 0.5,
"learning_rate": 0.00019326475327984192,
"loss": 1.0643,
"step": 333
},
{
"epoch": 0.5,
"learning_rate": 0.00019322214145878487,
"loss": 1.0246,
"step": 334
},
{
"epoch": 0.5,
"learning_rate": 0.0001931793999943526,
"loss": 1.1108,
"step": 335
},
{
"epoch": 0.5,
"learning_rate": 0.00019313652894598543,
"loss": 1.0619,
"step": 336
},
{
"epoch": 0.5,
"eval_loss": 1.048388123512268,
"eval_runtime": 2.6045,
"eval_samples_per_second": 419.273,
"eval_steps_per_second": 26.493,
"step": 336
},
{
"epoch": 0.5,
"learning_rate": 0.00019309352837330372,
"loss": 1.0014,
"step": 337
},
{
"epoch": 0.5,
"learning_rate": 0.0001930503983361081,
"loss": 1.0786,
"step": 338
},
{
"epoch": 0.51,
"learning_rate": 0.00019300713889437926,
"loss": 1.014,
"step": 339
},
{
"epoch": 0.51,
"learning_rate": 0.00019296375010827773,
"loss": 1.1233,
"step": 340
},
{
"epoch": 0.51,
"learning_rate": 0.000192920232038144,
"loss": 1.1052,
"step": 341
},
{
"epoch": 0.51,
"learning_rate": 0.0001928765847444984,
"loss": 1.0138,
"step": 342
},
{
"epoch": 0.51,
"learning_rate": 0.00019283280828804081,
"loss": 1.1536,
"step": 343
},
{
"epoch": 0.51,
"learning_rate": 0.00019278890272965096,
"loss": 0.992,
"step": 344
},
{
"epoch": 0.51,
"learning_rate": 0.0001927448681303879,
"loss": 1.1165,
"step": 345
},
{
"epoch": 0.52,
"learning_rate": 0.0001927007045514903,
"loss": 1.0565,
"step": 346
},
{
"epoch": 0.52,
"learning_rate": 0.00019265641205437611,
"loss": 1.0664,
"step": 347
},
{
"epoch": 0.52,
"learning_rate": 0.0001926119907006426,
"loss": 1.0625,
"step": 348
},
{
"epoch": 0.52,
"learning_rate": 0.00019256744055206622,
"loss": 1.0393,
"step": 349
},
{
"epoch": 0.52,
"learning_rate": 0.0001925227616706026,
"loss": 1.125,
"step": 350
},
{
"epoch": 0.52,
"learning_rate": 0.00019247795411838627,
"loss": 1.0375,
"step": 351
},
{
"epoch": 0.52,
"learning_rate": 0.00019243301795773086,
"loss": 1.0648,
"step": 352
},
{
"epoch": 0.53,
"learning_rate": 0.0001923879532511287,
"loss": 1.0903,
"step": 353
},
{
"epoch": 0.53,
"learning_rate": 0.000192342760061251,
"loss": 1.1219,
"step": 354
},
{
"epoch": 0.53,
"learning_rate": 0.00019229743845094755,
"loss": 1.054,
"step": 355
},
{
"epoch": 0.53,
"learning_rate": 0.0001922519884832469,
"loss": 1.1206,
"step": 356
},
{
"epoch": 0.53,
"learning_rate": 0.00019220641022135588,
"loss": 1.1125,
"step": 357
},
{
"epoch": 0.53,
"learning_rate": 0.00019216070372865996,
"loss": 1.064,
"step": 358
},
{
"epoch": 0.54,
"learning_rate": 0.0001921148690687228,
"loss": 1.0843,
"step": 359
},
{
"epoch": 0.54,
"learning_rate": 0.00019206890630528634,
"loss": 1.1378,
"step": 360
},
{
"epoch": 0.54,
"learning_rate": 0.00019202281550227064,
"loss": 1.0399,
"step": 361
},
{
"epoch": 0.54,
"learning_rate": 0.0001919765967237739,
"loss": 1.1762,
"step": 362
},
{
"epoch": 0.54,
"learning_rate": 0.0001919302500340722,
"loss": 1.0538,
"step": 363
},
{
"epoch": 0.54,
"learning_rate": 0.00019188377549761963,
"loss": 1.0343,
"step": 364
},
{
"epoch": 0.54,
"learning_rate": 0.0001918371731790479,
"loss": 1.1027,
"step": 365
},
{
"epoch": 0.55,
"learning_rate": 0.00019179044314316664,
"loss": 1.036,
"step": 366
},
{
"epoch": 0.55,
"learning_rate": 0.00019174358545496288,
"loss": 1.041,
"step": 367
},
{
"epoch": 0.55,
"learning_rate": 0.00019169660017960137,
"loss": 1.0762,
"step": 368
},
{
"epoch": 0.55,
"learning_rate": 0.00019164948738242409,
"loss": 1.0807,
"step": 369
},
{
"epoch": 0.55,
"learning_rate": 0.00019160224712895055,
"loss": 1.037,
"step": 370
},
{
"epoch": 0.55,
"learning_rate": 0.00019155487948487748,
"loss": 1.0625,
"step": 371
},
{
"epoch": 0.55,
"learning_rate": 0.0001915073845160786,
"loss": 1.062,
"step": 372
},
{
"epoch": 0.56,
"learning_rate": 0.00019145976228860496,
"loss": 1.1882,
"step": 373
},
{
"epoch": 0.56,
"learning_rate": 0.00019141201286868435,
"loss": 1.1338,
"step": 374
},
{
"epoch": 0.56,
"learning_rate": 0.00019136413632272163,
"loss": 1.0174,
"step": 375
},
{
"epoch": 0.56,
"learning_rate": 0.00019131613271729833,
"loss": 1.0585,
"step": 376
},
{
"epoch": 0.56,
"learning_rate": 0.00019126800211917276,
"loss": 1.0495,
"step": 377
},
{
"epoch": 0.56,
"learning_rate": 0.0001912197445952798,
"loss": 1.123,
"step": 378
},
{
"epoch": 0.56,
"learning_rate": 0.00019117136021273075,
"loss": 1.0517,
"step": 379
},
{
"epoch": 0.57,
"learning_rate": 0.0001911228490388136,
"loss": 1.0545,
"step": 380
},
{
"epoch": 0.57,
"learning_rate": 0.00019107421114099237,
"loss": 1.0302,
"step": 381
},
{
"epoch": 0.57,
"learning_rate": 0.00019102544658690748,
"loss": 1.0908,
"step": 382
},
{
"epoch": 0.57,
"learning_rate": 0.00019097655544437545,
"loss": 1.1425,
"step": 383
},
{
"epoch": 0.57,
"learning_rate": 0.00019092753778138886,
"loss": 1.0686,
"step": 384
},
{
"epoch": 0.57,
"learning_rate": 0.0001908783936661162,
"loss": 1.06,
"step": 385
},
{
"epoch": 0.58,
"learning_rate": 0.0001908291231669019,
"loss": 1.1296,
"step": 386
},
{
"epoch": 0.58,
"learning_rate": 0.00019077972635226604,
"loss": 1.1029,
"step": 387
},
{
"epoch": 0.58,
"learning_rate": 0.00019073020329090444,
"loss": 1.0469,
"step": 388
},
{
"epoch": 0.58,
"learning_rate": 0.0001906805540516885,
"loss": 1.0427,
"step": 389
},
{
"epoch": 0.58,
"learning_rate": 0.000190630778703665,
"loss": 1.0075,
"step": 390
},
{
"epoch": 0.58,
"learning_rate": 0.00019058087731605624,
"loss": 1.1146,
"step": 391
},
{
"epoch": 0.58,
"learning_rate": 0.0001905308499582597,
"loss": 1.1161,
"step": 392
},
{
"epoch": 0.59,
"learning_rate": 0.00019048069669984802,
"loss": 1.1419,
"step": 393
},
{
"epoch": 0.59,
"learning_rate": 0.00019043041761056907,
"loss": 1.1586,
"step": 394
},
{
"epoch": 0.59,
"learning_rate": 0.00019038001276034557,
"loss": 1.0765,
"step": 395
},
{
"epoch": 0.59,
"learning_rate": 0.00019032948221927524,
"loss": 1.1225,
"step": 396
},
{
"epoch": 0.59,
"learning_rate": 0.0001902788260576305,
"loss": 1.0247,
"step": 397
},
{
"epoch": 0.59,
"learning_rate": 0.00019022804434585852,
"loss": 1.135,
"step": 398
},
{
"epoch": 0.59,
"learning_rate": 0.0001901771371545811,
"loss": 1.1122,
"step": 399
},
{
"epoch": 0.6,
"learning_rate": 0.00019012610455459446,
"loss": 1.075,
"step": 400
},
{
"epoch": 0.6,
"learning_rate": 0.00019007494661686935,
"loss": 1.1121,
"step": 401
},
{
"epoch": 0.6,
"learning_rate": 0.0001900236634125507,
"loss": 1.0531,
"step": 402
},
{
"epoch": 0.6,
"learning_rate": 0.00018997225501295772,
"loss": 1.0561,
"step": 403
},
{
"epoch": 0.6,
"learning_rate": 0.00018992072148958368,
"loss": 1.0803,
"step": 404
},
{
"epoch": 0.6,
"learning_rate": 0.00018986906291409595,
"loss": 1.0579,
"step": 405
},
{
"epoch": 0.61,
"learning_rate": 0.00018981727935833567,
"loss": 1.0614,
"step": 406
},
{
"epoch": 0.61,
"learning_rate": 0.0001897653708943179,
"loss": 0.9982,
"step": 407
},
{
"epoch": 0.61,
"learning_rate": 0.00018971333759423142,
"loss": 1.1498,
"step": 408
},
{
"epoch": 0.61,
"learning_rate": 0.00018966117953043852,
"loss": 1.1165,
"step": 409
},
{
"epoch": 0.61,
"learning_rate": 0.00018960889677547505,
"loss": 1.1155,
"step": 410
},
{
"epoch": 0.61,
"learning_rate": 0.00018955648940205028,
"loss": 1.0017,
"step": 411
},
{
"epoch": 0.61,
"learning_rate": 0.00018950395748304678,
"loss": 1.0556,
"step": 412
},
{
"epoch": 0.62,
"learning_rate": 0.00018945130109152033,
"loss": 1.0248,
"step": 413
},
{
"epoch": 0.62,
"learning_rate": 0.00018939852030069981,
"loss": 1.0155,
"step": 414
},
{
"epoch": 0.62,
"learning_rate": 0.00018934561518398706,
"loss": 1.0248,
"step": 415
},
{
"epoch": 0.62,
"learning_rate": 0.00018929258581495685,
"loss": 0.9835,
"step": 416
},
{
"epoch": 0.62,
"learning_rate": 0.0001892394322673568,
"loss": 1.1602,
"step": 417
},
{
"epoch": 0.62,
"learning_rate": 0.0001891861546151071,
"loss": 1.021,
"step": 418
},
{
"epoch": 0.62,
"learning_rate": 0.00018913275293230069,
"loss": 1.0526,
"step": 419
},
{
"epoch": 0.63,
"learning_rate": 0.00018907922729320285,
"loss": 1.0585,
"step": 420
},
{
"epoch": 0.63,
"learning_rate": 0.00018902557777225135,
"loss": 1.0327,
"step": 421
},
{
"epoch": 0.63,
"learning_rate": 0.00018897180444405614,
"loss": 1.0448,
"step": 422
},
{
"epoch": 0.63,
"learning_rate": 0.0001889179073833995,
"loss": 1.0776,
"step": 423
},
{
"epoch": 0.63,
"learning_rate": 0.0001888638866652356,
"loss": 1.0748,
"step": 424
},
{
"epoch": 0.63,
"learning_rate": 0.0001888097423646907,
"loss": 1.0482,
"step": 425
},
{
"epoch": 0.63,
"learning_rate": 0.00018875547455706295,
"loss": 1.0394,
"step": 426
},
{
"epoch": 0.64,
"learning_rate": 0.00018870108331782217,
"loss": 1.0646,
"step": 427
},
{
"epoch": 0.64,
"learning_rate": 0.00018864656872260985,
"loss": 1.0338,
"step": 428
},
{
"epoch": 0.64,
"learning_rate": 0.00018859193084723913,
"loss": 0.9848,
"step": 429
},
{
"epoch": 0.64,
"learning_rate": 0.0001885371697676944,
"loss": 1.0587,
"step": 430
},
{
"epoch": 0.64,
"learning_rate": 0.0001884822855601316,
"loss": 1.0711,
"step": 431
},
{
"epoch": 0.64,
"learning_rate": 0.00018842727830087778,
"loss": 1.0964,
"step": 432
},
{
"epoch": 0.65,
"learning_rate": 0.00018837214806643115,
"loss": 1.0254,
"step": 433
},
{
"epoch": 0.65,
"learning_rate": 0.00018831689493346095,
"loss": 1.0748,
"step": 434
},
{
"epoch": 0.65,
"learning_rate": 0.00018826151897880728,
"loss": 1.0797,
"step": 435
},
{
"epoch": 0.65,
"learning_rate": 0.00018820602027948114,
"loss": 1.1068,
"step": 436
},
{
"epoch": 0.65,
"learning_rate": 0.00018815039891266418,
"loss": 1.081,
"step": 437
},
{
"epoch": 0.65,
"learning_rate": 0.0001880946549557086,
"loss": 1.0685,
"step": 438
},
{
"epoch": 0.65,
"learning_rate": 0.00018803878848613716,
"loss": 1.0916,
"step": 439
},
{
"epoch": 0.66,
"learning_rate": 0.00018798279958164295,
"loss": 1.115,
"step": 440
},
{
"epoch": 0.66,
"learning_rate": 0.00018792668832008936,
"loss": 1.0048,
"step": 441
},
{
"epoch": 0.66,
"learning_rate": 0.0001878704547795099,
"loss": 1.0386,
"step": 442
},
{
"epoch": 0.66,
"learning_rate": 0.00018781409903810821,
"loss": 1.0283,
"step": 443
},
{
"epoch": 0.66,
"learning_rate": 0.00018775762117425777,
"loss": 1.085,
"step": 444
},
{
"epoch": 0.66,
"learning_rate": 0.00018770102126650198,
"loss": 1.0582,
"step": 445
},
{
"epoch": 0.66,
"learning_rate": 0.00018764429939355392,
"loss": 1.0705,
"step": 446
},
{
"epoch": 0.67,
"learning_rate": 0.0001875874556342963,
"loss": 1.1426,
"step": 447
},
{
"epoch": 0.67,
"learning_rate": 0.00018753049006778132,
"loss": 1.0337,
"step": 448
},
{
"epoch": 0.67,
"learning_rate": 0.0001874734027732306,
"loss": 1.0993,
"step": 449
},
{
"epoch": 0.67,
"learning_rate": 0.00018741619383003507,
"loss": 1.0661,
"step": 450
},
{
"epoch": 0.67,
"learning_rate": 0.00018735886331775476,
"loss": 1.0564,
"step": 451
},
{
"epoch": 0.67,
"learning_rate": 0.00018730141131611882,
"loss": 1.0989,
"step": 452
},
{
"epoch": 0.68,
"learning_rate": 0.0001872438379050254,
"loss": 1.0984,
"step": 453
},
{
"epoch": 0.68,
"learning_rate": 0.00018718614316454133,
"loss": 1.1173,
"step": 454
},
{
"epoch": 0.68,
"learning_rate": 0.00018712832717490235,
"loss": 1.1005,
"step": 455
},
{
"epoch": 0.68,
"learning_rate": 0.00018707039001651277,
"loss": 1.0008,
"step": 456
},
{
"epoch": 0.68,
"learning_rate": 0.00018701233176994533,
"loss": 1.0701,
"step": 457
},
{
"epoch": 0.68,
"learning_rate": 0.00018695415251594123,
"loss": 1.0831,
"step": 458
},
{
"epoch": 0.68,
"learning_rate": 0.00018689585233541003,
"loss": 1.1165,
"step": 459
},
{
"epoch": 0.69,
"learning_rate": 0.00018683743130942928,
"loss": 1.0884,
"step": 460
},
{
"epoch": 0.69,
"learning_rate": 0.00018677888951924474,
"loss": 0.9882,
"step": 461
},
{
"epoch": 0.69,
"learning_rate": 0.00018672022704627002,
"loss": 1.086,
"step": 462
},
{
"epoch": 0.69,
"learning_rate": 0.00018666144397208668,
"loss": 1.0545,
"step": 463
},
{
"epoch": 0.69,
"learning_rate": 0.00018660254037844388,
"loss": 1.0274,
"step": 464
},
{
"epoch": 0.69,
"learning_rate": 0.0001865435163472584,
"loss": 1.0795,
"step": 465
},
{
"epoch": 0.69,
"learning_rate": 0.00018648437196061462,
"loss": 1.022,
"step": 466
},
{
"epoch": 0.7,
"learning_rate": 0.0001864251073007642,
"loss": 1.0717,
"step": 467
},
{
"epoch": 0.7,
"learning_rate": 0.00018636572245012606,
"loss": 1.1501,
"step": 468
},
{
"epoch": 0.7,
"learning_rate": 0.0001863062174912863,
"loss": 1.1034,
"step": 469
},
{
"epoch": 0.7,
"learning_rate": 0.00018624659250699805,
"loss": 1.0784,
"step": 470
},
{
"epoch": 0.7,
"learning_rate": 0.00018618684758018136,
"loss": 1.1274,
"step": 471
},
{
"epoch": 0.7,
"learning_rate": 0.0001861269827939231,
"loss": 1.0643,
"step": 472
},
{
"epoch": 0.7,
"learning_rate": 0.00018606699823147676,
"loss": 1.1394,
"step": 473
},
{
"epoch": 0.71,
"learning_rate": 0.00018600689397626246,
"loss": 0.9665,
"step": 474
},
{
"epoch": 0.71,
"learning_rate": 0.00018594667011186678,
"loss": 1.058,
"step": 475
},
{
"epoch": 0.71,
"learning_rate": 0.00018588632672204264,
"loss": 1.0706,
"step": 476
},
{
"epoch": 0.71,
"learning_rate": 0.0001858258638907091,
"loss": 1.0414,
"step": 477
},
{
"epoch": 0.71,
"learning_rate": 0.00018576528170195146,
"loss": 1.1,
"step": 478
},
{
"epoch": 0.71,
"learning_rate": 0.00018570458024002093,
"loss": 1.1114,
"step": 479
},
{
"epoch": 0.72,
"learning_rate": 0.00018564375958933459,
"loss": 1.0596,
"step": 480
},
{
"epoch": 0.72,
"learning_rate": 0.0001855828198344753,
"loss": 1.0897,
"step": 481
},
{
"epoch": 0.72,
"learning_rate": 0.00018552176106019155,
"loss": 1.0316,
"step": 482
},
{
"epoch": 0.72,
"learning_rate": 0.00018546058335139733,
"loss": 1.0516,
"step": 483
},
{
"epoch": 0.72,
"learning_rate": 0.0001853992867931721,
"loss": 1.0477,
"step": 484
},
{
"epoch": 0.72,
"learning_rate": 0.00018533787147076048,
"loss": 1.0432,
"step": 485
},
{
"epoch": 0.72,
"learning_rate": 0.00018527633746957234,
"loss": 1.0568,
"step": 486
},
{
"epoch": 0.73,
"learning_rate": 0.00018521468487518264,
"loss": 1.114,
"step": 487
},
{
"epoch": 0.73,
"learning_rate": 0.00018515291377333112,
"loss": 1.0664,
"step": 488
},
{
"epoch": 0.73,
"learning_rate": 0.0001850910242499225,
"loss": 1.0162,
"step": 489
},
{
"epoch": 0.73,
"learning_rate": 0.0001850290163910261,
"loss": 1.0829,
"step": 490
},
{
"epoch": 0.73,
"learning_rate": 0.00018496689028287572,
"loss": 1.1078,
"step": 491
},
{
"epoch": 0.73,
"learning_rate": 0.0001849046460118698,
"loss": 1.0533,
"step": 492
},
{
"epoch": 0.73,
"learning_rate": 0.00018484228366457095,
"loss": 1.0923,
"step": 493
},
{
"epoch": 0.74,
"learning_rate": 0.00018477980332770607,
"loss": 1.0516,
"step": 494
},
{
"epoch": 0.74,
"learning_rate": 0.00018471720508816614,
"loss": 0.9826,
"step": 495
},
{
"epoch": 0.74,
"learning_rate": 0.00018465448903300606,
"loss": 1.1581,
"step": 496
},
{
"epoch": 0.74,
"learning_rate": 0.0001845916552494446,
"loss": 1.1268,
"step": 497
},
{
"epoch": 0.74,
"learning_rate": 0.00018452870382486432,
"loss": 1.0483,
"step": 498
},
{
"epoch": 0.74,
"learning_rate": 0.00018446563484681127,
"loss": 1.1792,
"step": 499
},
{
"epoch": 0.75,
"learning_rate": 0.00018440244840299506,
"loss": 1.0918,
"step": 500
},
{
"epoch": 0.75,
"learning_rate": 0.0001843391445812886,
"loss": 0.9691,
"step": 501
},
{
"epoch": 0.75,
"learning_rate": 0.00018427572346972805,
"loss": 1.0581,
"step": 502
},
{
"epoch": 0.75,
"learning_rate": 0.0001842121851565128,
"loss": 1.0072,
"step": 503
},
{
"epoch": 0.75,
"learning_rate": 0.00018414852973000503,
"loss": 0.9686,
"step": 504
},
{
"epoch": 0.75,
"eval_loss": 1.0276715755462646,
"eval_runtime": 2.6054,
"eval_samples_per_second": 419.124,
"eval_steps_per_second": 26.483,
"step": 504
},
{
"epoch": 0.75,
"learning_rate": 0.00018408475727872995,
"loss": 1.1221,
"step": 505
},
{
"epoch": 0.75,
"learning_rate": 0.00018402086789137546,
"loss": 1.087,
"step": 506
},
{
"epoch": 0.76,
"learning_rate": 0.00018395686165679202,
"loss": 1.0599,
"step": 507
},
{
"epoch": 0.76,
"learning_rate": 0.00018389273866399275,
"loss": 1.1844,
"step": 508
},
{
"epoch": 0.76,
"learning_rate": 0.00018382849900215294,
"loss": 1.046,
"step": 509
},
{
"epoch": 0.76,
"learning_rate": 0.00018376414276061032,
"loss": 0.9691,
"step": 510
},
{
"epoch": 0.76,
"learning_rate": 0.00018369967002886464,
"loss": 1.0996,
"step": 511
},
{
"epoch": 0.76,
"learning_rate": 0.0001836350808965776,
"loss": 1.083,
"step": 512
},
{
"epoch": 0.76,
"learning_rate": 0.00018357037545357297,
"loss": 1.0371,
"step": 513
},
{
"epoch": 0.77,
"learning_rate": 0.00018350555378983608,
"loss": 1.018,
"step": 514
},
{
"epoch": 0.77,
"learning_rate": 0.00018344061599551398,
"loss": 1.095,
"step": 515
},
{
"epoch": 0.77,
"learning_rate": 0.00018337556216091517,
"loss": 1.0871,
"step": 516
},
{
"epoch": 0.77,
"learning_rate": 0.0001833103923765096,
"loss": 1.0774,
"step": 517
},
{
"epoch": 0.77,
"learning_rate": 0.00018324510673292842,
"loss": 1.0337,
"step": 518
},
{
"epoch": 0.77,
"learning_rate": 0.0001831797053209639,
"loss": 1.0059,
"step": 519
},
{
"epoch": 0.77,
"learning_rate": 0.00018311418823156936,
"loss": 1.0744,
"step": 520
},
{
"epoch": 0.78,
"learning_rate": 0.00018304855555585894,
"loss": 0.9732,
"step": 521
},
{
"epoch": 0.78,
"learning_rate": 0.00018298280738510752,
"loss": 1.1176,
"step": 522
},
{
"epoch": 0.78,
"learning_rate": 0.00018291694381075056,
"loss": 1.1485,
"step": 523
},
{
"epoch": 0.78,
"learning_rate": 0.00018285096492438424,
"loss": 1.1044,
"step": 524
},
{
"epoch": 0.78,
"learning_rate": 0.00018278487081776476,
"loss": 0.9812,
"step": 525
},
{
"epoch": 0.78,
"learning_rate": 0.00018271866158280884,
"loss": 1.0966,
"step": 526
},
{
"epoch": 0.79,
"learning_rate": 0.0001826523373115931,
"loss": 1.2406,
"step": 527
},
{
"epoch": 0.79,
"learning_rate": 0.0001825858980963543,
"loss": 1.0727,
"step": 528
},
{
"epoch": 0.79,
"learning_rate": 0.000182519344029489,
"loss": 0.9966,
"step": 529
},
{
"epoch": 0.79,
"learning_rate": 0.00018245267520355346,
"loss": 1.081,
"step": 530
},
{
"epoch": 0.79,
"learning_rate": 0.00018238589171126353,
"loss": 1.1104,
"step": 531
},
{
"epoch": 0.79,
"learning_rate": 0.00018231899364549455,
"loss": 1.0535,
"step": 532
},
{
"epoch": 0.79,
"learning_rate": 0.00018225198109928114,
"loss": 1.0801,
"step": 533
},
{
"epoch": 0.8,
"learning_rate": 0.00018218485416581726,
"loss": 1.0726,
"step": 534
},
{
"epoch": 0.8,
"learning_rate": 0.00018211761293845585,
"loss": 1.0923,
"step": 535
},
{
"epoch": 0.8,
"learning_rate": 0.00018205025751070875,
"loss": 1.0551,
"step": 536
},
{
"epoch": 0.8,
"learning_rate": 0.00018198278797624675,
"loss": 1.0495,
"step": 537
},
{
"epoch": 0.8,
"learning_rate": 0.0001819152044288992,
"loss": 1.0589,
"step": 538
},
{
"epoch": 0.8,
"learning_rate": 0.00018184750696265408,
"loss": 1.0487,
"step": 539
},
{
"epoch": 0.8,
"learning_rate": 0.0001817796956716578,
"loss": 1.0491,
"step": 540
},
{
"epoch": 0.81,
"learning_rate": 0.000181711770650215,
"loss": 1.0981,
"step": 541
},
{
"epoch": 0.81,
"learning_rate": 0.00018164373199278856,
"loss": 1.1706,
"step": 542
},
{
"epoch": 0.81,
"learning_rate": 0.0001815755797939994,
"loss": 1.1024,
"step": 543
},
{
"epoch": 0.81,
"learning_rate": 0.00018150731414862622,
"loss": 1.0488,
"step": 544
},
{
"epoch": 0.81,
"learning_rate": 0.00018143893515160564,
"loss": 1.165,
"step": 545
},
{
"epoch": 0.81,
"learning_rate": 0.00018137044289803181,
"loss": 1.0346,
"step": 546
},
{
"epoch": 0.82,
"learning_rate": 0.00018130183748315645,
"loss": 1.1179,
"step": 547
},
{
"epoch": 0.82,
"learning_rate": 0.0001812331190023886,
"loss": 1.0027,
"step": 548
},
{
"epoch": 0.82,
"learning_rate": 0.00018116428755129459,
"loss": 1.1106,
"step": 549
},
{
"epoch": 0.82,
"learning_rate": 0.00018109534322559783,
"loss": 1.0479,
"step": 550
},
{
"epoch": 0.82,
"learning_rate": 0.00018102628612117865,
"loss": 1.0046,
"step": 551
},
{
"epoch": 0.82,
"learning_rate": 0.0001809571163340744,
"loss": 0.9883,
"step": 552
},
{
"epoch": 0.82,
"learning_rate": 0.00018088783396047893,
"loss": 1.1018,
"step": 553
},
{
"epoch": 0.83,
"learning_rate": 0.00018081843909674276,
"loss": 1.1389,
"step": 554
},
{
"epoch": 0.83,
"learning_rate": 0.00018074893183937283,
"loss": 1.0751,
"step": 555
},
{
"epoch": 0.83,
"learning_rate": 0.00018067931228503246,
"loss": 1.1475,
"step": 556
},
{
"epoch": 0.83,
"learning_rate": 0.00018060958053054096,
"loss": 1.0829,
"step": 557
},
{
"epoch": 0.83,
"learning_rate": 0.00018053973667287387,
"loss": 1.0272,
"step": 558
},
{
"epoch": 0.83,
"learning_rate": 0.00018046978080916252,
"loss": 1.0668,
"step": 559
},
{
"epoch": 0.83,
"learning_rate": 0.00018039971303669407,
"loss": 1.0988,
"step": 560
},
{
"epoch": 0.84,
"learning_rate": 0.00018032953345291123,
"loss": 1.0339,
"step": 561
},
{
"epoch": 0.84,
"learning_rate": 0.0001802592421554123,
"loss": 1.0654,
"step": 562
},
{
"epoch": 0.84,
"learning_rate": 0.00018018883924195085,
"loss": 1.0157,
"step": 563
},
{
"epoch": 0.84,
"learning_rate": 0.00018011832481043576,
"loss": 1.0738,
"step": 564
},
{
"epoch": 0.84,
"learning_rate": 0.0001800476989589309,
"loss": 1.0742,
"step": 565
},
{
"epoch": 0.84,
"learning_rate": 0.0001799769617856552,
"loss": 0.9861,
"step": 566
},
{
"epoch": 0.85,
"learning_rate": 0.0001799061133889823,
"loss": 1.0788,
"step": 567
},
{
"epoch": 0.85,
"learning_rate": 0.00017983515386744061,
"loss": 1.0539,
"step": 568
},
{
"epoch": 0.85,
"learning_rate": 0.00017976408331971298,
"loss": 1.0875,
"step": 569
},
{
"epoch": 0.85,
"learning_rate": 0.0001796929018446368,
"loss": 1.0765,
"step": 570
},
{
"epoch": 0.85,
"learning_rate": 0.00017962160954120354,
"loss": 1.1336,
"step": 571
},
{
"epoch": 0.85,
"learning_rate": 0.000179550206508559,
"loss": 0.9674,
"step": 572
},
{
"epoch": 0.85,
"learning_rate": 0.00017947869284600282,
"loss": 1.0607,
"step": 573
},
{
"epoch": 0.86,
"learning_rate": 0.0001794070686529886,
"loss": 0.9959,
"step": 574
},
{
"epoch": 0.86,
"learning_rate": 0.00017933533402912354,
"loss": 1.038,
"step": 575
},
{
"epoch": 0.86,
"learning_rate": 0.0001792634890741685,
"loss": 1.1342,
"step": 576
},
{
"epoch": 0.86,
"learning_rate": 0.00017919153388803774,
"loss": 1.0941,
"step": 577
},
{
"epoch": 0.86,
"learning_rate": 0.00017911946857079888,
"loss": 1.1286,
"step": 578
},
{
"epoch": 0.86,
"learning_rate": 0.00017904729322267256,
"loss": 1.0354,
"step": 579
},
{
"epoch": 0.86,
"learning_rate": 0.0001789750079440326,
"loss": 1.1314,
"step": 580
},
{
"epoch": 0.87,
"learning_rate": 0.00017890261283540562,
"loss": 1.0365,
"step": 581
},
{
"epoch": 0.87,
"learning_rate": 0.00017883010799747099,
"loss": 1.091,
"step": 582
},
{
"epoch": 0.87,
"learning_rate": 0.00017875749353106062,
"loss": 0.9995,
"step": 583
},
{
"epoch": 0.87,
"learning_rate": 0.000178684769537159,
"loss": 1.0435,
"step": 584
},
{
"epoch": 0.87,
"learning_rate": 0.00017861193611690287,
"loss": 1.0555,
"step": 585
},
{
"epoch": 0.87,
"learning_rate": 0.00017853899337158112,
"loss": 1.0637,
"step": 586
},
{
"epoch": 0.87,
"learning_rate": 0.00017846594140263474,
"loss": 1.064,
"step": 587
},
{
"epoch": 0.88,
"learning_rate": 0.00017839278031165658,
"loss": 0.9879,
"step": 588
},
{
"epoch": 0.88,
"learning_rate": 0.00017831951020039126,
"loss": 1.0846,
"step": 589
},
{
"epoch": 0.88,
"learning_rate": 0.000178246131170735,
"loss": 1.0373,
"step": 590
},
{
"epoch": 0.88,
"learning_rate": 0.00017817264332473546,
"loss": 1.0377,
"step": 591
},
{
"epoch": 0.88,
"learning_rate": 0.00017809904676459177,
"loss": 1.0932,
"step": 592
},
{
"epoch": 0.88,
"learning_rate": 0.00017802534159265404,
"loss": 1.085,
"step": 593
},
{
"epoch": 0.89,
"learning_rate": 0.0001779515279114236,
"loss": 1.0975,
"step": 594
},
{
"epoch": 0.89,
"learning_rate": 0.0001778776058235526,
"loss": 1.1283,
"step": 595
},
{
"epoch": 0.89,
"learning_rate": 0.00017780357543184397,
"loss": 1.0652,
"step": 596
},
{
"epoch": 0.89,
"learning_rate": 0.00017772943683925122,
"loss": 1.0336,
"step": 597
},
{
"epoch": 0.89,
"learning_rate": 0.00017765519014887842,
"loss": 0.9761,
"step": 598
},
{
"epoch": 0.89,
"learning_rate": 0.0001775808354639799,
"loss": 1.0688,
"step": 599
},
{
"epoch": 0.89,
"learning_rate": 0.00017750637288796016,
"loss": 1.1031,
"step": 600
},
{
"epoch": 0.9,
"learning_rate": 0.00017743180252437383,
"loss": 1.083,
"step": 601
},
{
"epoch": 0.9,
"learning_rate": 0.00017735712447692538,
"loss": 1.1612,
"step": 602
},
{
"epoch": 0.9,
"learning_rate": 0.00017728233884946903,
"loss": 1.1618,
"step": 603
},
{
"epoch": 0.9,
"learning_rate": 0.00017720744574600863,
"loss": 1.144,
"step": 604
},
{
"epoch": 0.9,
"learning_rate": 0.0001771324452706975,
"loss": 1.1174,
"step": 605
},
{
"epoch": 0.9,
"learning_rate": 0.00017705733752783825,
"loss": 0.9728,
"step": 606
},
{
"epoch": 0.9,
"learning_rate": 0.0001769821226218827,
"loss": 1.0599,
"step": 607
},
{
"epoch": 0.91,
"learning_rate": 0.0001769068006574317,
"loss": 1.0639,
"step": 608
},
{
"epoch": 0.91,
"learning_rate": 0.00017683137173923495,
"loss": 1.1278,
"step": 609
},
{
"epoch": 0.91,
"learning_rate": 0.00017675583597219095,
"loss": 0.9925,
"step": 610
},
{
"epoch": 0.91,
"learning_rate": 0.0001766801934613467,
"loss": 1.0457,
"step": 611
},
{
"epoch": 0.91,
"learning_rate": 0.0001766044443118978,
"loss": 1.0348,
"step": 612
},
{
"epoch": 0.91,
"learning_rate": 0.000176528588629188,
"loss": 1.022,
"step": 613
},
{
"epoch": 0.92,
"learning_rate": 0.00017645262651870926,
"loss": 1.0027,
"step": 614
},
{
"epoch": 0.92,
"learning_rate": 0.00017637655808610156,
"loss": 1.0491,
"step": 615
},
{
"epoch": 0.92,
"learning_rate": 0.00017630038343715275,
"loss": 1.0413,
"step": 616
},
{
"epoch": 0.92,
"learning_rate": 0.00017622410267779834,
"loss": 1.0358,
"step": 617
},
{
"epoch": 0.92,
"learning_rate": 0.00017614771591412148,
"loss": 1.1125,
"step": 618
},
{
"epoch": 0.92,
"learning_rate": 0.00017607122325235267,
"loss": 1.1185,
"step": 619
},
{
"epoch": 0.92,
"learning_rate": 0.00017599462479886974,
"loss": 1.0738,
"step": 620
},
{
"epoch": 0.93,
"learning_rate": 0.00017591792066019765,
"loss": 1.102,
"step": 621
},
{
"epoch": 0.93,
"learning_rate": 0.00017584111094300827,
"loss": 1.065,
"step": 622
},
{
"epoch": 0.93,
"learning_rate": 0.0001757641957541203,
"loss": 1.0514,
"step": 623
},
{
"epoch": 0.93,
"learning_rate": 0.0001756871752004992,
"loss": 1.0396,
"step": 624
},
{
"epoch": 0.93,
"learning_rate": 0.00017561004938925688,
"loss": 1.1027,
"step": 625
},
{
"epoch": 0.93,
"learning_rate": 0.00017553281842765169,
"loss": 1.0223,
"step": 626
},
{
"epoch": 0.93,
"learning_rate": 0.00017545548242308816,
"loss": 1.1793,
"step": 627
},
{
"epoch": 0.94,
"learning_rate": 0.00017537804148311695,
"loss": 1.0642,
"step": 628
},
{
"epoch": 0.94,
"learning_rate": 0.00017530049571543464,
"loss": 1.0682,
"step": 629
},
{
"epoch": 0.94,
"learning_rate": 0.00017522284522788353,
"loss": 1.0476,
"step": 630
},
{
"epoch": 0.94,
"learning_rate": 0.00017514509012845164,
"loss": 1.1064,
"step": 631
},
{
"epoch": 0.94,
"learning_rate": 0.00017506723052527242,
"loss": 1.0258,
"step": 632
},
{
"epoch": 0.94,
"learning_rate": 0.00017498926652662476,
"loss": 1.1954,
"step": 633
},
{
"epoch": 0.94,
"learning_rate": 0.0001749111982409325,
"loss": 1.0637,
"step": 634
},
{
"epoch": 0.95,
"learning_rate": 0.00017483302577676475,
"loss": 0.9685,
"step": 635
},
{
"epoch": 0.95,
"learning_rate": 0.00017475474924283536,
"loss": 1.0465,
"step": 636
},
{
"epoch": 0.95,
"learning_rate": 0.000174676368748003,
"loss": 1.0161,
"step": 637
},
{
"epoch": 0.95,
"learning_rate": 0.00017459788440127083,
"loss": 1.0479,
"step": 638
},
{
"epoch": 0.95,
"learning_rate": 0.00017451929631178648,
"loss": 1.1166,
"step": 639
},
{
"epoch": 0.95,
"learning_rate": 0.0001744406045888419,
"loss": 1.0634,
"step": 640
},
{
"epoch": 0.96,
"learning_rate": 0.00017436180934187308,
"loss": 1.0826,
"step": 641
},
{
"epoch": 0.96,
"learning_rate": 0.00017428291068046,
"loss": 1.07,
"step": 642
},
{
"epoch": 0.96,
"learning_rate": 0.00017420390871432647,
"loss": 1.1167,
"step": 643
},
{
"epoch": 0.96,
"learning_rate": 0.00017412480355334005,
"loss": 1.0347,
"step": 644
},
{
"epoch": 0.96,
"learning_rate": 0.00017404559530751162,
"loss": 1.0393,
"step": 645
},
{
"epoch": 0.96,
"learning_rate": 0.00017396628408699555,
"loss": 1.1108,
"step": 646
},
{
"epoch": 0.96,
"learning_rate": 0.00017388687000208946,
"loss": 1.006,
"step": 647
},
{
"epoch": 0.97,
"learning_rate": 0.0001738073531632339,
"loss": 1.0932,
"step": 648
},
{
"epoch": 0.97,
"learning_rate": 0.0001737277336810124,
"loss": 1.0123,
"step": 649
},
{
"epoch": 0.97,
"learning_rate": 0.00017364801166615124,
"loss": 1.1273,
"step": 650
},
{
"epoch": 0.97,
"learning_rate": 0.0001735681872295192,
"loss": 0.9893,
"step": 651
},
{
"epoch": 0.97,
"learning_rate": 0.0001734882604821276,
"loss": 1.0699,
"step": 652
},
{
"epoch": 0.97,
"learning_rate": 0.00017340823153513002,
"loss": 1.0901,
"step": 653
},
{
"epoch": 0.97,
"learning_rate": 0.00017332810049982208,
"loss": 1.0212,
"step": 654
},
{
"epoch": 0.98,
"learning_rate": 0.00017324786748764155,
"loss": 0.9898,
"step": 655
},
{
"epoch": 0.98,
"learning_rate": 0.00017316753261016783,
"loss": 1.0899,
"step": 656
},
{
"epoch": 0.98,
"learning_rate": 0.00017308709597912213,
"loss": 1.085,
"step": 657
},
{
"epoch": 0.98,
"learning_rate": 0.00017300655770636708,
"loss": 1.091,
"step": 658
},
{
"epoch": 0.98,
"learning_rate": 0.00017292591790390665,
"loss": 1.0502,
"step": 659
},
{
"epoch": 0.98,
"learning_rate": 0.0001728451766838861,
"loss": 1.2131,
"step": 660
},
{
"epoch": 0.99,
"learning_rate": 0.00017276433415859167,
"loss": 1.1256,
"step": 661
},
{
"epoch": 0.99,
"learning_rate": 0.00017268339044045042,
"loss": 1.0577,
"step": 662
},
{
"epoch": 0.99,
"learning_rate": 0.00017260234564203032,
"loss": 1.0012,
"step": 663
},
{
"epoch": 0.99,
"learning_rate": 0.00017252119987603973,
"loss": 1.0611,
"step": 664
},
{
"epoch": 0.99,
"learning_rate": 0.00017243995325532755,
"loss": 1.1251,
"step": 665
},
{
"epoch": 0.99,
"learning_rate": 0.00017235860589288277,
"loss": 1.0959,
"step": 666
},
{
"epoch": 0.99,
"learning_rate": 0.0001722771579018347,
"loss": 1.1413,
"step": 667
},
{
"epoch": 1.0,
"learning_rate": 0.00017219560939545246,
"loss": 1.0728,
"step": 668
},
{
"epoch": 1.0,
"learning_rate": 0.00017211396048714498,
"loss": 1.0461,
"step": 669
},
{
"epoch": 1.0,
"learning_rate": 0.0001720322112904608,
"loss": 1.1084,
"step": 670
},
{
"epoch": 1.0,
"learning_rate": 0.00017195036191908797,
"loss": 1.1316,
"step": 671
}
],
"logging_steps": 1,
"max_steps": 2684,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 671,
"total_flos": 2.085255620067328e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}