unaligned / trainer_state.json
zodiache's picture
Training in progress, step 10
2a57b00 verified
raw
history blame
159 kB
{
"best_metric": 1.7247449159622192,
"best_model_checkpoint": "lora_lr/google/gemma-1.1-7b-it/unaligned/checkpoint-1000",
"epoch": 1.310300703774792,
"eval_steps": 50,
"global_step": 1024,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 1.0390625,
"learning_rate": 2.0000000000000003e-06,
"loss": 4.7488,
"step": 1
},
{
"epoch": 0.0,
"grad_norm": 0.97265625,
"learning_rate": 4.000000000000001e-06,
"loss": 4.5149,
"step": 2
},
{
"epoch": 0.0,
"grad_norm": 0.9296875,
"learning_rate": 6e-06,
"loss": 4.3836,
"step": 3
},
{
"epoch": 0.01,
"grad_norm": 1.0234375,
"learning_rate": 8.000000000000001e-06,
"loss": 4.6777,
"step": 4
},
{
"epoch": 0.01,
"grad_norm": 1.03125,
"learning_rate": 1e-05,
"loss": 4.6688,
"step": 5
},
{
"epoch": 0.01,
"grad_norm": 0.94921875,
"learning_rate": 1.2e-05,
"loss": 4.5565,
"step": 6
},
{
"epoch": 0.01,
"grad_norm": 1.0078125,
"learning_rate": 1.4000000000000001e-05,
"loss": 4.5658,
"step": 7
},
{
"epoch": 0.01,
"grad_norm": 1.015625,
"learning_rate": 1.6000000000000003e-05,
"loss": 4.6618,
"step": 8
},
{
"epoch": 0.01,
"grad_norm": 1.0546875,
"learning_rate": 1.8e-05,
"loss": 4.6095,
"step": 9
},
{
"epoch": 0.01,
"grad_norm": 1.0703125,
"learning_rate": 2e-05,
"loss": 4.7608,
"step": 10
},
{
"epoch": 0.01,
"grad_norm": 1.0546875,
"learning_rate": 2.2000000000000003e-05,
"loss": 4.5421,
"step": 11
},
{
"epoch": 0.02,
"grad_norm": 0.9609375,
"learning_rate": 2.4e-05,
"loss": 4.2895,
"step": 12
},
{
"epoch": 0.02,
"grad_norm": 1.125,
"learning_rate": 2.6000000000000002e-05,
"loss": 4.8112,
"step": 13
},
{
"epoch": 0.02,
"grad_norm": 1.1328125,
"learning_rate": 2.8000000000000003e-05,
"loss": 4.6709,
"step": 14
},
{
"epoch": 0.02,
"grad_norm": 1.1484375,
"learning_rate": 3e-05,
"loss": 4.5234,
"step": 15
},
{
"epoch": 0.02,
"grad_norm": 1.1328125,
"learning_rate": 3.2000000000000005e-05,
"loss": 4.3751,
"step": 16
},
{
"epoch": 0.02,
"grad_norm": 1.3046875,
"learning_rate": 3.4000000000000007e-05,
"loss": 4.5247,
"step": 17
},
{
"epoch": 0.02,
"grad_norm": 1.265625,
"learning_rate": 3.6e-05,
"loss": 4.3906,
"step": 18
},
{
"epoch": 0.02,
"grad_norm": 1.40625,
"learning_rate": 3.8e-05,
"loss": 4.3193,
"step": 19
},
{
"epoch": 0.03,
"grad_norm": 1.4296875,
"learning_rate": 4e-05,
"loss": 4.2987,
"step": 20
},
{
"epoch": 0.03,
"grad_norm": 1.4375,
"learning_rate": 4.2e-05,
"loss": 4.2167,
"step": 21
},
{
"epoch": 0.03,
"grad_norm": 1.6171875,
"learning_rate": 4.4000000000000006e-05,
"loss": 4.3088,
"step": 22
},
{
"epoch": 0.03,
"grad_norm": 1.6640625,
"learning_rate": 4.600000000000001e-05,
"loss": 4.2658,
"step": 23
},
{
"epoch": 0.03,
"grad_norm": 1.734375,
"learning_rate": 4.8e-05,
"loss": 4.1625,
"step": 24
},
{
"epoch": 0.03,
"grad_norm": 1.8203125,
"learning_rate": 5e-05,
"loss": 4.0392,
"step": 25
},
{
"epoch": 0.03,
"grad_norm": 1.8828125,
"learning_rate": 5.2000000000000004e-05,
"loss": 3.9772,
"step": 26
},
{
"epoch": 0.03,
"grad_norm": 1.8828125,
"learning_rate": 5.4000000000000005e-05,
"loss": 3.9029,
"step": 27
},
{
"epoch": 0.04,
"grad_norm": 1.875,
"learning_rate": 5.6000000000000006e-05,
"loss": 3.8107,
"step": 28
},
{
"epoch": 0.04,
"grad_norm": 1.96875,
"learning_rate": 5.8e-05,
"loss": 3.8199,
"step": 29
},
{
"epoch": 0.04,
"grad_norm": 1.953125,
"learning_rate": 6e-05,
"loss": 3.5035,
"step": 30
},
{
"epoch": 0.04,
"grad_norm": 2.03125,
"learning_rate": 6.2e-05,
"loss": 3.6236,
"step": 31
},
{
"epoch": 0.04,
"grad_norm": 1.796875,
"learning_rate": 6.400000000000001e-05,
"loss": 3.3359,
"step": 32
},
{
"epoch": 0.04,
"grad_norm": 1.7578125,
"learning_rate": 6.6e-05,
"loss": 3.3019,
"step": 33
},
{
"epoch": 0.04,
"grad_norm": 1.7109375,
"learning_rate": 6.800000000000001e-05,
"loss": 3.2003,
"step": 34
},
{
"epoch": 0.04,
"grad_norm": 1.6640625,
"learning_rate": 7e-05,
"loss": 3.1585,
"step": 35
},
{
"epoch": 0.05,
"grad_norm": 1.53125,
"learning_rate": 7.2e-05,
"loss": 2.9377,
"step": 36
},
{
"epoch": 0.05,
"grad_norm": 1.5625,
"learning_rate": 7.4e-05,
"loss": 3.13,
"step": 37
},
{
"epoch": 0.05,
"grad_norm": 1.453125,
"learning_rate": 7.6e-05,
"loss": 2.9445,
"step": 38
},
{
"epoch": 0.05,
"grad_norm": 1.21875,
"learning_rate": 7.800000000000001e-05,
"loss": 2.7348,
"step": 39
},
{
"epoch": 0.05,
"grad_norm": 1.1171875,
"learning_rate": 8e-05,
"loss": 2.6842,
"step": 40
},
{
"epoch": 0.05,
"grad_norm": 0.90625,
"learning_rate": 8.2e-05,
"loss": 2.6921,
"step": 41
},
{
"epoch": 0.05,
"grad_norm": 0.9453125,
"learning_rate": 8.4e-05,
"loss": 2.6504,
"step": 42
},
{
"epoch": 0.06,
"grad_norm": 1.125,
"learning_rate": 8.6e-05,
"loss": 2.4995,
"step": 43
},
{
"epoch": 0.06,
"grad_norm": 1.34375,
"learning_rate": 8.800000000000001e-05,
"loss": 2.4545,
"step": 44
},
{
"epoch": 0.06,
"grad_norm": 1.28125,
"learning_rate": 9e-05,
"loss": 2.4311,
"step": 45
},
{
"epoch": 0.06,
"grad_norm": 0.640625,
"learning_rate": 9.200000000000001e-05,
"loss": 2.4045,
"step": 46
},
{
"epoch": 0.06,
"grad_norm": 0.54296875,
"learning_rate": 9.4e-05,
"loss": 2.413,
"step": 47
},
{
"epoch": 0.06,
"grad_norm": 0.578125,
"learning_rate": 9.6e-05,
"loss": 2.3691,
"step": 48
},
{
"epoch": 0.06,
"grad_norm": 0.65234375,
"learning_rate": 9.8e-05,
"loss": 2.2936,
"step": 49
},
{
"epoch": 0.06,
"grad_norm": 0.62109375,
"learning_rate": 0.0001,
"loss": 2.3459,
"step": 50
},
{
"epoch": 0.06,
"eval_loss": 2.298555374145508,
"eval_runtime": 125.5458,
"eval_samples_per_second": 39.826,
"eval_steps_per_second": 1.251,
"step": 50
},
{
"epoch": 0.07,
"grad_norm": 0.5859375,
"learning_rate": 0.00010200000000000001,
"loss": 2.458,
"step": 51
},
{
"epoch": 0.07,
"grad_norm": 0.61328125,
"learning_rate": 0.00010400000000000001,
"loss": 2.2395,
"step": 52
},
{
"epoch": 0.07,
"grad_norm": 0.55859375,
"learning_rate": 0.00010600000000000002,
"loss": 2.2084,
"step": 53
},
{
"epoch": 0.07,
"grad_norm": 0.83203125,
"learning_rate": 0.00010800000000000001,
"loss": 2.2806,
"step": 54
},
{
"epoch": 0.07,
"grad_norm": 1.15625,
"learning_rate": 0.00011000000000000002,
"loss": 2.1546,
"step": 55
},
{
"epoch": 0.07,
"grad_norm": 0.91015625,
"learning_rate": 0.00011200000000000001,
"loss": 2.2027,
"step": 56
},
{
"epoch": 0.07,
"grad_norm": 0.6640625,
"learning_rate": 0.00011399999999999999,
"loss": 2.1795,
"step": 57
},
{
"epoch": 0.07,
"grad_norm": 0.5,
"learning_rate": 0.000116,
"loss": 2.1918,
"step": 58
},
{
"epoch": 0.08,
"grad_norm": 0.39453125,
"learning_rate": 0.000118,
"loss": 2.143,
"step": 59
},
{
"epoch": 0.08,
"grad_norm": 0.4375,
"learning_rate": 0.00012,
"loss": 2.1451,
"step": 60
},
{
"epoch": 0.08,
"grad_norm": 0.388671875,
"learning_rate": 0.000122,
"loss": 2.1542,
"step": 61
},
{
"epoch": 0.08,
"grad_norm": 0.3984375,
"learning_rate": 0.000124,
"loss": 2.1125,
"step": 62
},
{
"epoch": 0.08,
"grad_norm": 0.6953125,
"learning_rate": 0.000126,
"loss": 2.1123,
"step": 63
},
{
"epoch": 0.08,
"grad_norm": 0.451171875,
"learning_rate": 0.00012800000000000002,
"loss": 2.0354,
"step": 64
},
{
"epoch": 0.08,
"grad_norm": 0.451171875,
"learning_rate": 0.00013000000000000002,
"loss": 2.1228,
"step": 65
},
{
"epoch": 0.08,
"grad_norm": 0.77734375,
"learning_rate": 0.000132,
"loss": 2.1666,
"step": 66
},
{
"epoch": 0.09,
"grad_norm": 0.455078125,
"learning_rate": 0.000134,
"loss": 2.0429,
"step": 67
},
{
"epoch": 0.09,
"grad_norm": 0.384765625,
"learning_rate": 0.00013600000000000003,
"loss": 2.0367,
"step": 68
},
{
"epoch": 0.09,
"grad_norm": 0.365234375,
"learning_rate": 0.000138,
"loss": 2.0139,
"step": 69
},
{
"epoch": 0.09,
"grad_norm": 0.3671875,
"learning_rate": 0.00014,
"loss": 2.0284,
"step": 70
},
{
"epoch": 0.09,
"grad_norm": 0.404296875,
"learning_rate": 0.000142,
"loss": 2.0303,
"step": 71
},
{
"epoch": 0.09,
"grad_norm": 0.3515625,
"learning_rate": 0.000144,
"loss": 2.0645,
"step": 72
},
{
"epoch": 0.09,
"grad_norm": 0.365234375,
"learning_rate": 0.000146,
"loss": 2.001,
"step": 73
},
{
"epoch": 0.09,
"grad_norm": 0.3046875,
"learning_rate": 0.000148,
"loss": 2.0946,
"step": 74
},
{
"epoch": 0.1,
"grad_norm": 0.314453125,
"learning_rate": 0.00015000000000000001,
"loss": 1.9969,
"step": 75
},
{
"epoch": 0.1,
"grad_norm": 0.419921875,
"learning_rate": 0.000152,
"loss": 1.9911,
"step": 76
},
{
"epoch": 0.1,
"grad_norm": 0.328125,
"learning_rate": 0.000154,
"loss": 2.0011,
"step": 77
},
{
"epoch": 0.1,
"grad_norm": 0.234375,
"learning_rate": 0.00015600000000000002,
"loss": 1.9893,
"step": 78
},
{
"epoch": 0.1,
"grad_norm": 0.380859375,
"learning_rate": 0.00015800000000000002,
"loss": 1.9336,
"step": 79
},
{
"epoch": 0.1,
"grad_norm": 0.2890625,
"learning_rate": 0.00016,
"loss": 1.9876,
"step": 80
},
{
"epoch": 0.1,
"grad_norm": 0.255859375,
"learning_rate": 0.000162,
"loss": 1.9679,
"step": 81
},
{
"epoch": 0.1,
"grad_norm": 0.23828125,
"learning_rate": 0.000164,
"loss": 1.9157,
"step": 82
},
{
"epoch": 0.11,
"grad_norm": 0.373046875,
"learning_rate": 0.000166,
"loss": 1.9939,
"step": 83
},
{
"epoch": 0.11,
"grad_norm": 0.255859375,
"learning_rate": 0.000168,
"loss": 1.9457,
"step": 84
},
{
"epoch": 0.11,
"grad_norm": 0.26171875,
"learning_rate": 0.00017,
"loss": 1.9924,
"step": 85
},
{
"epoch": 0.11,
"grad_norm": 0.2275390625,
"learning_rate": 0.000172,
"loss": 1.8708,
"step": 86
},
{
"epoch": 0.11,
"grad_norm": 0.26953125,
"learning_rate": 0.000174,
"loss": 1.946,
"step": 87
},
{
"epoch": 0.11,
"grad_norm": 0.255859375,
"learning_rate": 0.00017600000000000002,
"loss": 1.9743,
"step": 88
},
{
"epoch": 0.11,
"grad_norm": 0.2490234375,
"learning_rate": 0.00017800000000000002,
"loss": 1.9257,
"step": 89
},
{
"epoch": 0.12,
"grad_norm": 0.26953125,
"learning_rate": 0.00018,
"loss": 1.9041,
"step": 90
},
{
"epoch": 0.12,
"grad_norm": 0.265625,
"learning_rate": 0.000182,
"loss": 1.9502,
"step": 91
},
{
"epoch": 0.12,
"grad_norm": 0.240234375,
"learning_rate": 0.00018400000000000003,
"loss": 1.8514,
"step": 92
},
{
"epoch": 0.12,
"grad_norm": 0.255859375,
"learning_rate": 0.00018600000000000002,
"loss": 2.0176,
"step": 93
},
{
"epoch": 0.12,
"grad_norm": 0.298828125,
"learning_rate": 0.000188,
"loss": 1.9056,
"step": 94
},
{
"epoch": 0.12,
"grad_norm": 0.26171875,
"learning_rate": 0.00019,
"loss": 1.9149,
"step": 95
},
{
"epoch": 0.12,
"grad_norm": 0.212890625,
"learning_rate": 0.000192,
"loss": 1.9587,
"step": 96
},
{
"epoch": 0.12,
"grad_norm": 0.26953125,
"learning_rate": 0.000194,
"loss": 1.9103,
"step": 97
},
{
"epoch": 0.13,
"grad_norm": 0.28515625,
"learning_rate": 0.000196,
"loss": 1.8814,
"step": 98
},
{
"epoch": 0.13,
"grad_norm": 0.25,
"learning_rate": 0.00019800000000000002,
"loss": 1.842,
"step": 99
},
{
"epoch": 0.13,
"grad_norm": 0.205078125,
"learning_rate": 0.0002,
"loss": 1.8251,
"step": 100
},
{
"epoch": 0.13,
"eval_loss": 1.8968226909637451,
"eval_runtime": 125.222,
"eval_samples_per_second": 39.929,
"eval_steps_per_second": 1.254,
"step": 100
},
{
"epoch": 0.13,
"grad_norm": 0.275390625,
"learning_rate": 0.00019978354978354978,
"loss": 1.84,
"step": 101
},
{
"epoch": 0.13,
"grad_norm": 0.2236328125,
"learning_rate": 0.00019956709956709957,
"loss": 1.9066,
"step": 102
},
{
"epoch": 0.13,
"grad_norm": 0.244140625,
"learning_rate": 0.00019935064935064936,
"loss": 1.9553,
"step": 103
},
{
"epoch": 0.13,
"grad_norm": 0.2451171875,
"learning_rate": 0.00019913419913419916,
"loss": 1.922,
"step": 104
},
{
"epoch": 0.13,
"grad_norm": 0.255859375,
"learning_rate": 0.00019891774891774892,
"loss": 1.8927,
"step": 105
},
{
"epoch": 0.14,
"grad_norm": 0.21484375,
"learning_rate": 0.00019870129870129872,
"loss": 1.9244,
"step": 106
},
{
"epoch": 0.14,
"grad_norm": 0.265625,
"learning_rate": 0.0001984848484848485,
"loss": 1.8875,
"step": 107
},
{
"epoch": 0.14,
"grad_norm": 0.388671875,
"learning_rate": 0.00019826839826839827,
"loss": 1.837,
"step": 108
},
{
"epoch": 0.14,
"grad_norm": 0.228515625,
"learning_rate": 0.00019805194805194807,
"loss": 1.8613,
"step": 109
},
{
"epoch": 0.14,
"grad_norm": 0.2216796875,
"learning_rate": 0.00019783549783549783,
"loss": 1.9369,
"step": 110
},
{
"epoch": 0.14,
"grad_norm": 0.234375,
"learning_rate": 0.00019761904761904763,
"loss": 1.8546,
"step": 111
},
{
"epoch": 0.14,
"grad_norm": 0.3125,
"learning_rate": 0.00019740259740259742,
"loss": 1.8774,
"step": 112
},
{
"epoch": 0.14,
"grad_norm": 0.28125,
"learning_rate": 0.0001971861471861472,
"loss": 1.8799,
"step": 113
},
{
"epoch": 0.15,
"grad_norm": 0.224609375,
"learning_rate": 0.00019696969696969698,
"loss": 1.8776,
"step": 114
},
{
"epoch": 0.15,
"grad_norm": 0.2412109375,
"learning_rate": 0.00019675324675324675,
"loss": 1.8823,
"step": 115
},
{
"epoch": 0.15,
"grad_norm": 0.234375,
"learning_rate": 0.00019653679653679654,
"loss": 1.8877,
"step": 116
},
{
"epoch": 0.15,
"grad_norm": 0.259765625,
"learning_rate": 0.00019632034632034633,
"loss": 1.9692,
"step": 117
},
{
"epoch": 0.15,
"grad_norm": 0.208984375,
"learning_rate": 0.00019610389610389613,
"loss": 1.8985,
"step": 118
},
{
"epoch": 0.15,
"grad_norm": 0.248046875,
"learning_rate": 0.0001958874458874459,
"loss": 1.8564,
"step": 119
},
{
"epoch": 0.15,
"grad_norm": 0.2109375,
"learning_rate": 0.00019567099567099566,
"loss": 1.9001,
"step": 120
},
{
"epoch": 0.15,
"grad_norm": 0.2080078125,
"learning_rate": 0.00019545454545454548,
"loss": 1.879,
"step": 121
},
{
"epoch": 0.16,
"grad_norm": 0.326171875,
"learning_rate": 0.00019523809523809525,
"loss": 1.8385,
"step": 122
},
{
"epoch": 0.16,
"grad_norm": 0.24609375,
"learning_rate": 0.00019502164502164504,
"loss": 1.8581,
"step": 123
},
{
"epoch": 0.16,
"grad_norm": 0.2294921875,
"learning_rate": 0.0001948051948051948,
"loss": 1.8517,
"step": 124
},
{
"epoch": 0.16,
"grad_norm": 0.21875,
"learning_rate": 0.0001945887445887446,
"loss": 1.8695,
"step": 125
},
{
"epoch": 0.16,
"grad_norm": 0.3125,
"learning_rate": 0.0001943722943722944,
"loss": 1.8675,
"step": 126
},
{
"epoch": 0.16,
"grad_norm": 0.220703125,
"learning_rate": 0.00019415584415584416,
"loss": 1.9089,
"step": 127
},
{
"epoch": 0.16,
"grad_norm": 0.2314453125,
"learning_rate": 0.00019393939393939395,
"loss": 1.831,
"step": 128
},
{
"epoch": 0.17,
"grad_norm": 0.2734375,
"learning_rate": 0.00019372294372294372,
"loss": 1.932,
"step": 129
},
{
"epoch": 0.17,
"grad_norm": 0.2216796875,
"learning_rate": 0.00019350649350649354,
"loss": 1.917,
"step": 130
},
{
"epoch": 0.17,
"grad_norm": 0.28125,
"learning_rate": 0.0001932900432900433,
"loss": 1.8179,
"step": 131
},
{
"epoch": 0.17,
"grad_norm": 0.294921875,
"learning_rate": 0.00019307359307359307,
"loss": 1.8764,
"step": 132
},
{
"epoch": 0.17,
"grad_norm": 0.26171875,
"learning_rate": 0.00019285714285714286,
"loss": 1.8926,
"step": 133
},
{
"epoch": 0.17,
"grad_norm": 0.24609375,
"learning_rate": 0.00019264069264069266,
"loss": 1.9443,
"step": 134
},
{
"epoch": 0.17,
"grad_norm": 0.251953125,
"learning_rate": 0.00019242424242424245,
"loss": 1.8702,
"step": 135
},
{
"epoch": 0.17,
"grad_norm": 0.32421875,
"learning_rate": 0.00019220779220779222,
"loss": 1.8728,
"step": 136
},
{
"epoch": 0.18,
"grad_norm": 0.287109375,
"learning_rate": 0.000191991341991342,
"loss": 1.7953,
"step": 137
},
{
"epoch": 0.18,
"grad_norm": 0.283203125,
"learning_rate": 0.00019177489177489178,
"loss": 1.7883,
"step": 138
},
{
"epoch": 0.18,
"grad_norm": 0.302734375,
"learning_rate": 0.00019155844155844157,
"loss": 1.8741,
"step": 139
},
{
"epoch": 0.18,
"grad_norm": 0.25390625,
"learning_rate": 0.00019134199134199136,
"loss": 1.8094,
"step": 140
},
{
"epoch": 0.18,
"grad_norm": 0.302734375,
"learning_rate": 0.00019112554112554113,
"loss": 1.8629,
"step": 141
},
{
"epoch": 0.18,
"grad_norm": 0.2333984375,
"learning_rate": 0.00019090909090909092,
"loss": 1.855,
"step": 142
},
{
"epoch": 0.18,
"grad_norm": 0.236328125,
"learning_rate": 0.0001906926406926407,
"loss": 1.848,
"step": 143
},
{
"epoch": 0.18,
"grad_norm": 0.265625,
"learning_rate": 0.00019047619047619048,
"loss": 1.8853,
"step": 144
},
{
"epoch": 0.19,
"grad_norm": 0.47265625,
"learning_rate": 0.00019025974025974027,
"loss": 1.8435,
"step": 145
},
{
"epoch": 0.19,
"grad_norm": 0.263671875,
"learning_rate": 0.00019004329004329004,
"loss": 1.8619,
"step": 146
},
{
"epoch": 0.19,
"grad_norm": 0.37890625,
"learning_rate": 0.00018982683982683983,
"loss": 1.8298,
"step": 147
},
{
"epoch": 0.19,
"grad_norm": 0.236328125,
"learning_rate": 0.00018961038961038963,
"loss": 1.7478,
"step": 148
},
{
"epoch": 0.19,
"grad_norm": 0.275390625,
"learning_rate": 0.00018939393939393942,
"loss": 1.906,
"step": 149
},
{
"epoch": 0.19,
"grad_norm": 0.3046875,
"learning_rate": 0.0001891774891774892,
"loss": 1.9013,
"step": 150
},
{
"epoch": 0.19,
"eval_loss": 1.8299968242645264,
"eval_runtime": 125.2613,
"eval_samples_per_second": 39.917,
"eval_steps_per_second": 1.253,
"step": 150
},
{
"epoch": 0.19,
"grad_norm": 0.29296875,
"learning_rate": 0.00018896103896103895,
"loss": 1.7772,
"step": 151
},
{
"epoch": 0.19,
"grad_norm": 0.2490234375,
"learning_rate": 0.00018874458874458875,
"loss": 1.9428,
"step": 152
},
{
"epoch": 0.2,
"grad_norm": 0.2314453125,
"learning_rate": 0.00018852813852813854,
"loss": 1.8121,
"step": 153
},
{
"epoch": 0.2,
"grad_norm": 0.29296875,
"learning_rate": 0.00018831168831168833,
"loss": 1.7921,
"step": 154
},
{
"epoch": 0.2,
"grad_norm": 0.357421875,
"learning_rate": 0.0001880952380952381,
"loss": 1.846,
"step": 155
},
{
"epoch": 0.2,
"grad_norm": 0.2236328125,
"learning_rate": 0.0001878787878787879,
"loss": 1.7703,
"step": 156
},
{
"epoch": 0.2,
"grad_norm": 0.2119140625,
"learning_rate": 0.00018766233766233769,
"loss": 1.8048,
"step": 157
},
{
"epoch": 0.2,
"grad_norm": 0.33203125,
"learning_rate": 0.00018744588744588745,
"loss": 1.8353,
"step": 158
},
{
"epoch": 0.2,
"grad_norm": 0.26953125,
"learning_rate": 0.00018722943722943725,
"loss": 1.8538,
"step": 159
},
{
"epoch": 0.2,
"grad_norm": 0.259765625,
"learning_rate": 0.000187012987012987,
"loss": 1.828,
"step": 160
},
{
"epoch": 0.21,
"grad_norm": 0.2412109375,
"learning_rate": 0.0001867965367965368,
"loss": 1.8555,
"step": 161
},
{
"epoch": 0.21,
"grad_norm": 0.3125,
"learning_rate": 0.0001865800865800866,
"loss": 1.8,
"step": 162
},
{
"epoch": 0.21,
"grad_norm": 0.236328125,
"learning_rate": 0.00018636363636363636,
"loss": 1.8241,
"step": 163
},
{
"epoch": 0.21,
"grad_norm": 0.25,
"learning_rate": 0.00018614718614718616,
"loss": 1.7903,
"step": 164
},
{
"epoch": 0.21,
"grad_norm": 0.2431640625,
"learning_rate": 0.00018593073593073592,
"loss": 1.7279,
"step": 165
},
{
"epoch": 0.21,
"grad_norm": 0.33984375,
"learning_rate": 0.00018571428571428572,
"loss": 1.8231,
"step": 166
},
{
"epoch": 0.21,
"grad_norm": 0.2451171875,
"learning_rate": 0.0001854978354978355,
"loss": 1.8534,
"step": 167
},
{
"epoch": 0.21,
"grad_norm": 0.2470703125,
"learning_rate": 0.0001852813852813853,
"loss": 1.9175,
"step": 168
},
{
"epoch": 0.22,
"grad_norm": 0.341796875,
"learning_rate": 0.00018506493506493507,
"loss": 1.7986,
"step": 169
},
{
"epoch": 0.22,
"grad_norm": 0.294921875,
"learning_rate": 0.00018484848484848484,
"loss": 1.9097,
"step": 170
},
{
"epoch": 0.22,
"grad_norm": 0.3046875,
"learning_rate": 0.00018463203463203466,
"loss": 1.8232,
"step": 171
},
{
"epoch": 0.22,
"grad_norm": 0.38671875,
"learning_rate": 0.00018441558441558442,
"loss": 1.7505,
"step": 172
},
{
"epoch": 0.22,
"grad_norm": 0.283203125,
"learning_rate": 0.00018419913419913422,
"loss": 1.8454,
"step": 173
},
{
"epoch": 0.22,
"grad_norm": 0.306640625,
"learning_rate": 0.00018398268398268398,
"loss": 1.8028,
"step": 174
},
{
"epoch": 0.22,
"grad_norm": 0.28125,
"learning_rate": 0.00018376623376623378,
"loss": 1.9089,
"step": 175
},
{
"epoch": 0.23,
"grad_norm": 0.26953125,
"learning_rate": 0.00018354978354978357,
"loss": 1.8681,
"step": 176
},
{
"epoch": 0.23,
"grad_norm": 0.45703125,
"learning_rate": 0.00018333333333333334,
"loss": 1.8012,
"step": 177
},
{
"epoch": 0.23,
"grad_norm": 0.376953125,
"learning_rate": 0.00018311688311688313,
"loss": 1.7399,
"step": 178
},
{
"epoch": 0.23,
"grad_norm": 0.3125,
"learning_rate": 0.0001829004329004329,
"loss": 1.8339,
"step": 179
},
{
"epoch": 0.23,
"grad_norm": 0.470703125,
"learning_rate": 0.00018268398268398272,
"loss": 1.8236,
"step": 180
},
{
"epoch": 0.23,
"grad_norm": 0.466796875,
"learning_rate": 0.00018246753246753248,
"loss": 1.8088,
"step": 181
},
{
"epoch": 0.23,
"grad_norm": 0.2890625,
"learning_rate": 0.00018225108225108225,
"loss": 1.77,
"step": 182
},
{
"epoch": 0.23,
"grad_norm": 0.453125,
"learning_rate": 0.00018203463203463204,
"loss": 1.7954,
"step": 183
},
{
"epoch": 0.24,
"grad_norm": 0.53125,
"learning_rate": 0.00018181818181818183,
"loss": 1.7682,
"step": 184
},
{
"epoch": 0.24,
"grad_norm": 0.248046875,
"learning_rate": 0.00018160173160173163,
"loss": 1.9032,
"step": 185
},
{
"epoch": 0.24,
"grad_norm": 0.2431640625,
"learning_rate": 0.0001813852813852814,
"loss": 1.8145,
"step": 186
},
{
"epoch": 0.24,
"grad_norm": 0.482421875,
"learning_rate": 0.0001811688311688312,
"loss": 1.8433,
"step": 187
},
{
"epoch": 0.24,
"grad_norm": 0.3515625,
"learning_rate": 0.00018095238095238095,
"loss": 1.7845,
"step": 188
},
{
"epoch": 0.24,
"grad_norm": 0.306640625,
"learning_rate": 0.00018073593073593075,
"loss": 1.8512,
"step": 189
},
{
"epoch": 0.24,
"grad_norm": 0.328125,
"learning_rate": 0.00018051948051948054,
"loss": 1.8208,
"step": 190
},
{
"epoch": 0.24,
"grad_norm": 0.28515625,
"learning_rate": 0.0001803030303030303,
"loss": 1.8353,
"step": 191
},
{
"epoch": 0.25,
"grad_norm": 0.251953125,
"learning_rate": 0.0001800865800865801,
"loss": 1.8627,
"step": 192
},
{
"epoch": 0.25,
"grad_norm": 0.275390625,
"learning_rate": 0.00017987012987012987,
"loss": 1.7228,
"step": 193
},
{
"epoch": 0.25,
"grad_norm": 0.279296875,
"learning_rate": 0.00017965367965367966,
"loss": 1.878,
"step": 194
},
{
"epoch": 0.25,
"grad_norm": 0.255859375,
"learning_rate": 0.00017943722943722945,
"loss": 1.7724,
"step": 195
},
{
"epoch": 0.25,
"grad_norm": 0.251953125,
"learning_rate": 0.00017922077922077922,
"loss": 1.7845,
"step": 196
},
{
"epoch": 0.25,
"grad_norm": 0.326171875,
"learning_rate": 0.000179004329004329,
"loss": 1.7848,
"step": 197
},
{
"epoch": 0.25,
"grad_norm": 0.265625,
"learning_rate": 0.0001787878787878788,
"loss": 1.808,
"step": 198
},
{
"epoch": 0.25,
"grad_norm": 0.310546875,
"learning_rate": 0.0001785714285714286,
"loss": 1.834,
"step": 199
},
{
"epoch": 0.26,
"grad_norm": 0.275390625,
"learning_rate": 0.00017835497835497836,
"loss": 1.7679,
"step": 200
},
{
"epoch": 0.26,
"eval_loss": 1.8024407625198364,
"eval_runtime": 125.3989,
"eval_samples_per_second": 39.873,
"eval_steps_per_second": 1.252,
"step": 200
},
{
"epoch": 0.26,
"grad_norm": 0.283203125,
"learning_rate": 0.00017813852813852813,
"loss": 1.8003,
"step": 201
},
{
"epoch": 0.26,
"grad_norm": 0.267578125,
"learning_rate": 0.00017792207792207792,
"loss": 1.8544,
"step": 202
},
{
"epoch": 0.26,
"grad_norm": 0.259765625,
"learning_rate": 0.00017770562770562772,
"loss": 1.8894,
"step": 203
},
{
"epoch": 0.26,
"grad_norm": 0.28125,
"learning_rate": 0.0001774891774891775,
"loss": 1.8496,
"step": 204
},
{
"epoch": 0.26,
"grad_norm": 0.265625,
"learning_rate": 0.00017727272727272728,
"loss": 1.7319,
"step": 205
},
{
"epoch": 0.26,
"grad_norm": 0.29296875,
"learning_rate": 0.00017705627705627707,
"loss": 1.8156,
"step": 206
},
{
"epoch": 0.26,
"grad_norm": 0.294921875,
"learning_rate": 0.00017683982683982684,
"loss": 1.6916,
"step": 207
},
{
"epoch": 0.27,
"grad_norm": 0.267578125,
"learning_rate": 0.00017662337662337663,
"loss": 1.826,
"step": 208
},
{
"epoch": 0.27,
"grad_norm": 0.3046875,
"learning_rate": 0.00017640692640692642,
"loss": 1.8066,
"step": 209
},
{
"epoch": 0.27,
"grad_norm": 0.32421875,
"learning_rate": 0.0001761904761904762,
"loss": 1.8503,
"step": 210
},
{
"epoch": 0.27,
"grad_norm": 0.279296875,
"learning_rate": 0.00017597402597402598,
"loss": 1.8168,
"step": 211
},
{
"epoch": 0.27,
"grad_norm": 0.26953125,
"learning_rate": 0.00017575757575757578,
"loss": 1.7903,
"step": 212
},
{
"epoch": 0.27,
"grad_norm": 0.287109375,
"learning_rate": 0.00017554112554112554,
"loss": 1.8139,
"step": 213
},
{
"epoch": 0.27,
"grad_norm": 0.26171875,
"learning_rate": 0.00017532467532467534,
"loss": 1.7982,
"step": 214
},
{
"epoch": 0.28,
"grad_norm": 0.291015625,
"learning_rate": 0.0001751082251082251,
"loss": 1.7828,
"step": 215
},
{
"epoch": 0.28,
"grad_norm": 0.26953125,
"learning_rate": 0.0001748917748917749,
"loss": 1.7416,
"step": 216
},
{
"epoch": 0.28,
"grad_norm": 0.34375,
"learning_rate": 0.0001746753246753247,
"loss": 1.806,
"step": 217
},
{
"epoch": 0.28,
"grad_norm": 0.265625,
"learning_rate": 0.00017445887445887448,
"loss": 1.8822,
"step": 218
},
{
"epoch": 0.28,
"grad_norm": 0.345703125,
"learning_rate": 0.00017424242424242425,
"loss": 1.7818,
"step": 219
},
{
"epoch": 0.28,
"grad_norm": 0.275390625,
"learning_rate": 0.00017402597402597401,
"loss": 1.843,
"step": 220
},
{
"epoch": 0.28,
"grad_norm": 0.33984375,
"learning_rate": 0.00017380952380952383,
"loss": 1.8087,
"step": 221
},
{
"epoch": 0.28,
"grad_norm": 0.27734375,
"learning_rate": 0.0001735930735930736,
"loss": 1.8346,
"step": 222
},
{
"epoch": 0.29,
"grad_norm": 0.296875,
"learning_rate": 0.0001733766233766234,
"loss": 1.7843,
"step": 223
},
{
"epoch": 0.29,
"grad_norm": 0.330078125,
"learning_rate": 0.00017316017316017316,
"loss": 1.7974,
"step": 224
},
{
"epoch": 0.29,
"grad_norm": 0.26953125,
"learning_rate": 0.00017294372294372295,
"loss": 1.7798,
"step": 225
},
{
"epoch": 0.29,
"grad_norm": 0.287109375,
"learning_rate": 0.00017272727272727275,
"loss": 1.7318,
"step": 226
},
{
"epoch": 0.29,
"grad_norm": 0.27734375,
"learning_rate": 0.0001725108225108225,
"loss": 1.8244,
"step": 227
},
{
"epoch": 0.29,
"grad_norm": 0.345703125,
"learning_rate": 0.0001722943722943723,
"loss": 1.8291,
"step": 228
},
{
"epoch": 0.29,
"grad_norm": 0.275390625,
"learning_rate": 0.00017207792207792207,
"loss": 1.7127,
"step": 229
},
{
"epoch": 0.29,
"grad_norm": 0.27734375,
"learning_rate": 0.00017186147186147187,
"loss": 1.8416,
"step": 230
},
{
"epoch": 0.3,
"grad_norm": 0.283203125,
"learning_rate": 0.00017164502164502166,
"loss": 1.8327,
"step": 231
},
{
"epoch": 0.3,
"grad_norm": 0.29296875,
"learning_rate": 0.00017142857142857143,
"loss": 1.7058,
"step": 232
},
{
"epoch": 0.3,
"grad_norm": 0.3046875,
"learning_rate": 0.00017121212121212122,
"loss": 1.7438,
"step": 233
},
{
"epoch": 0.3,
"grad_norm": 0.298828125,
"learning_rate": 0.00017099567099567098,
"loss": 1.822,
"step": 234
},
{
"epoch": 0.3,
"grad_norm": 0.275390625,
"learning_rate": 0.0001707792207792208,
"loss": 1.8308,
"step": 235
},
{
"epoch": 0.3,
"grad_norm": 0.283203125,
"learning_rate": 0.00017056277056277057,
"loss": 1.8354,
"step": 236
},
{
"epoch": 0.3,
"grad_norm": 0.265625,
"learning_rate": 0.00017034632034632036,
"loss": 1.7753,
"step": 237
},
{
"epoch": 0.3,
"grad_norm": 0.337890625,
"learning_rate": 0.00017012987012987013,
"loss": 1.8091,
"step": 238
},
{
"epoch": 0.31,
"grad_norm": 0.3046875,
"learning_rate": 0.00016991341991341992,
"loss": 1.8526,
"step": 239
},
{
"epoch": 0.31,
"grad_norm": 0.33984375,
"learning_rate": 0.00016969696969696972,
"loss": 1.8296,
"step": 240
},
{
"epoch": 0.31,
"grad_norm": 0.322265625,
"learning_rate": 0.00016948051948051948,
"loss": 1.8309,
"step": 241
},
{
"epoch": 0.31,
"grad_norm": 0.310546875,
"learning_rate": 0.00016926406926406928,
"loss": 1.7423,
"step": 242
},
{
"epoch": 0.31,
"grad_norm": 0.310546875,
"learning_rate": 0.00016904761904761904,
"loss": 1.7644,
"step": 243
},
{
"epoch": 0.31,
"grad_norm": 0.30859375,
"learning_rate": 0.00016883116883116884,
"loss": 1.7392,
"step": 244
},
{
"epoch": 0.31,
"grad_norm": 0.349609375,
"learning_rate": 0.00016861471861471863,
"loss": 1.8515,
"step": 245
},
{
"epoch": 0.31,
"grad_norm": 0.30859375,
"learning_rate": 0.0001683982683982684,
"loss": 1.751,
"step": 246
},
{
"epoch": 0.32,
"grad_norm": 0.3046875,
"learning_rate": 0.0001681818181818182,
"loss": 1.8196,
"step": 247
},
{
"epoch": 0.32,
"grad_norm": 0.28515625,
"learning_rate": 0.00016796536796536798,
"loss": 1.8556,
"step": 248
},
{
"epoch": 0.32,
"grad_norm": 0.390625,
"learning_rate": 0.00016774891774891778,
"loss": 1.7934,
"step": 249
},
{
"epoch": 0.32,
"grad_norm": 0.29296875,
"learning_rate": 0.00016753246753246754,
"loss": 1.753,
"step": 250
},
{
"epoch": 0.32,
"eval_loss": 1.7896223068237305,
"eval_runtime": 125.3191,
"eval_samples_per_second": 39.898,
"eval_steps_per_second": 1.253,
"step": 250
},
{
"epoch": 0.32,
"grad_norm": 0.2890625,
"learning_rate": 0.0001673160173160173,
"loss": 1.8485,
"step": 251
},
{
"epoch": 0.32,
"grad_norm": 0.33984375,
"learning_rate": 0.0001670995670995671,
"loss": 1.7847,
"step": 252
},
{
"epoch": 0.32,
"grad_norm": 0.294921875,
"learning_rate": 0.0001668831168831169,
"loss": 1.688,
"step": 253
},
{
"epoch": 0.33,
"grad_norm": 0.271484375,
"learning_rate": 0.0001666666666666667,
"loss": 1.7079,
"step": 254
},
{
"epoch": 0.33,
"grad_norm": 0.33203125,
"learning_rate": 0.00016645021645021645,
"loss": 1.7858,
"step": 255
},
{
"epoch": 0.33,
"grad_norm": 0.310546875,
"learning_rate": 0.00016623376623376625,
"loss": 1.8125,
"step": 256
},
{
"epoch": 0.33,
"grad_norm": 0.32421875,
"learning_rate": 0.00016601731601731601,
"loss": 1.7826,
"step": 257
},
{
"epoch": 0.33,
"grad_norm": 0.3515625,
"learning_rate": 0.0001658008658008658,
"loss": 1.7352,
"step": 258
},
{
"epoch": 0.33,
"grad_norm": 0.357421875,
"learning_rate": 0.0001655844155844156,
"loss": 1.7863,
"step": 259
},
{
"epoch": 0.33,
"grad_norm": 0.283203125,
"learning_rate": 0.00016536796536796537,
"loss": 1.7868,
"step": 260
},
{
"epoch": 0.33,
"grad_norm": 0.279296875,
"learning_rate": 0.00016515151515151516,
"loss": 1.7958,
"step": 261
},
{
"epoch": 0.34,
"grad_norm": 0.29296875,
"learning_rate": 0.00016493506493506495,
"loss": 1.7685,
"step": 262
},
{
"epoch": 0.34,
"grad_norm": 0.279296875,
"learning_rate": 0.00016471861471861472,
"loss": 1.7561,
"step": 263
},
{
"epoch": 0.34,
"grad_norm": 0.2890625,
"learning_rate": 0.0001645021645021645,
"loss": 1.7634,
"step": 264
},
{
"epoch": 0.34,
"grad_norm": 0.296875,
"learning_rate": 0.00016428571428571428,
"loss": 1.8092,
"step": 265
},
{
"epoch": 0.34,
"grad_norm": 0.31640625,
"learning_rate": 0.00016406926406926407,
"loss": 1.8324,
"step": 266
},
{
"epoch": 0.34,
"grad_norm": 0.28125,
"learning_rate": 0.00016385281385281387,
"loss": 1.7221,
"step": 267
},
{
"epoch": 0.34,
"grad_norm": 0.298828125,
"learning_rate": 0.00016363636363636366,
"loss": 1.7796,
"step": 268
},
{
"epoch": 0.34,
"grad_norm": 0.302734375,
"learning_rate": 0.00016341991341991343,
"loss": 1.7713,
"step": 269
},
{
"epoch": 0.35,
"grad_norm": 0.265625,
"learning_rate": 0.0001632034632034632,
"loss": 1.8178,
"step": 270
},
{
"epoch": 0.35,
"grad_norm": 0.404296875,
"learning_rate": 0.000162987012987013,
"loss": 1.8104,
"step": 271
},
{
"epoch": 0.35,
"grad_norm": 0.3125,
"learning_rate": 0.00016277056277056278,
"loss": 1.8387,
"step": 272
},
{
"epoch": 0.35,
"grad_norm": 0.310546875,
"learning_rate": 0.00016255411255411257,
"loss": 1.8897,
"step": 273
},
{
"epoch": 0.35,
"grad_norm": 0.28125,
"learning_rate": 0.00016233766233766234,
"loss": 1.8162,
"step": 274
},
{
"epoch": 0.35,
"grad_norm": 0.40625,
"learning_rate": 0.00016212121212121213,
"loss": 1.8086,
"step": 275
},
{
"epoch": 0.35,
"grad_norm": 0.283203125,
"learning_rate": 0.00016190476190476192,
"loss": 1.9186,
"step": 276
},
{
"epoch": 0.35,
"grad_norm": 0.345703125,
"learning_rate": 0.0001616883116883117,
"loss": 1.8123,
"step": 277
},
{
"epoch": 0.36,
"grad_norm": 0.27734375,
"learning_rate": 0.00016147186147186148,
"loss": 1.8115,
"step": 278
},
{
"epoch": 0.36,
"grad_norm": 0.33203125,
"learning_rate": 0.00016125541125541125,
"loss": 1.8785,
"step": 279
},
{
"epoch": 0.36,
"grad_norm": 0.3125,
"learning_rate": 0.00016103896103896104,
"loss": 1.805,
"step": 280
},
{
"epoch": 0.36,
"grad_norm": 0.3046875,
"learning_rate": 0.00016082251082251084,
"loss": 1.8656,
"step": 281
},
{
"epoch": 0.36,
"grad_norm": 0.3515625,
"learning_rate": 0.0001606060606060606,
"loss": 1.7848,
"step": 282
},
{
"epoch": 0.36,
"grad_norm": 0.3125,
"learning_rate": 0.0001603896103896104,
"loss": 1.7817,
"step": 283
},
{
"epoch": 0.36,
"grad_norm": 0.30078125,
"learning_rate": 0.00016017316017316016,
"loss": 1.8217,
"step": 284
},
{
"epoch": 0.36,
"grad_norm": 0.318359375,
"learning_rate": 0.00015995670995670998,
"loss": 1.8771,
"step": 285
},
{
"epoch": 0.37,
"grad_norm": 0.31640625,
"learning_rate": 0.00015974025974025975,
"loss": 1.8028,
"step": 286
},
{
"epoch": 0.37,
"grad_norm": 0.291015625,
"learning_rate": 0.00015952380952380954,
"loss": 1.8331,
"step": 287
},
{
"epoch": 0.37,
"grad_norm": 0.357421875,
"learning_rate": 0.0001593073593073593,
"loss": 1.7528,
"step": 288
},
{
"epoch": 0.37,
"grad_norm": 0.267578125,
"learning_rate": 0.0001590909090909091,
"loss": 1.8012,
"step": 289
},
{
"epoch": 0.37,
"grad_norm": 0.2734375,
"learning_rate": 0.0001588744588744589,
"loss": 1.7787,
"step": 290
},
{
"epoch": 0.37,
"grad_norm": 0.3125,
"learning_rate": 0.00015865800865800866,
"loss": 1.803,
"step": 291
},
{
"epoch": 0.37,
"grad_norm": 0.4375,
"learning_rate": 0.00015844155844155845,
"loss": 1.7466,
"step": 292
},
{
"epoch": 0.37,
"grad_norm": 0.30078125,
"learning_rate": 0.00015822510822510822,
"loss": 1.8551,
"step": 293
},
{
"epoch": 0.38,
"grad_norm": 0.279296875,
"learning_rate": 0.00015800865800865801,
"loss": 1.7932,
"step": 294
},
{
"epoch": 0.38,
"grad_norm": 0.359375,
"learning_rate": 0.0001577922077922078,
"loss": 1.7295,
"step": 295
},
{
"epoch": 0.38,
"grad_norm": 0.318359375,
"learning_rate": 0.00015757575757575757,
"loss": 1.7984,
"step": 296
},
{
"epoch": 0.38,
"grad_norm": 0.40234375,
"learning_rate": 0.00015735930735930737,
"loss": 1.8666,
"step": 297
},
{
"epoch": 0.38,
"grad_norm": 0.287109375,
"learning_rate": 0.00015714285714285716,
"loss": 1.7149,
"step": 298
},
{
"epoch": 0.38,
"grad_norm": 0.462890625,
"learning_rate": 0.00015692640692640695,
"loss": 1.7447,
"step": 299
},
{
"epoch": 0.38,
"grad_norm": 0.4296875,
"learning_rate": 0.00015670995670995672,
"loss": 1.8199,
"step": 300
},
{
"epoch": 0.38,
"eval_loss": 1.7805144786834717,
"eval_runtime": 125.5041,
"eval_samples_per_second": 39.839,
"eval_steps_per_second": 1.251,
"step": 300
},
{
"epoch": 0.39,
"grad_norm": 0.29296875,
"learning_rate": 0.00015649350649350649,
"loss": 1.7937,
"step": 301
},
{
"epoch": 0.39,
"grad_norm": 0.400390625,
"learning_rate": 0.00015627705627705628,
"loss": 1.7617,
"step": 302
},
{
"epoch": 0.39,
"grad_norm": 0.435546875,
"learning_rate": 0.00015606060606060607,
"loss": 1.7755,
"step": 303
},
{
"epoch": 0.39,
"grad_norm": 0.326171875,
"learning_rate": 0.00015584415584415587,
"loss": 1.862,
"step": 304
},
{
"epoch": 0.39,
"grad_norm": 0.365234375,
"learning_rate": 0.00015562770562770563,
"loss": 1.8572,
"step": 305
},
{
"epoch": 0.39,
"grad_norm": 0.330078125,
"learning_rate": 0.00015541125541125543,
"loss": 1.7678,
"step": 306
},
{
"epoch": 0.39,
"grad_norm": 0.359375,
"learning_rate": 0.0001551948051948052,
"loss": 1.7435,
"step": 307
},
{
"epoch": 0.39,
"grad_norm": 0.326171875,
"learning_rate": 0.00015497835497835498,
"loss": 1.7535,
"step": 308
},
{
"epoch": 0.4,
"grad_norm": 0.39453125,
"learning_rate": 0.00015476190476190478,
"loss": 1.7495,
"step": 309
},
{
"epoch": 0.4,
"grad_norm": 0.28515625,
"learning_rate": 0.00015454545454545454,
"loss": 1.7107,
"step": 310
},
{
"epoch": 0.4,
"grad_norm": 0.298828125,
"learning_rate": 0.00015432900432900434,
"loss": 1.7419,
"step": 311
},
{
"epoch": 0.4,
"grad_norm": 0.296875,
"learning_rate": 0.00015411255411255413,
"loss": 1.7466,
"step": 312
},
{
"epoch": 0.4,
"grad_norm": 0.3046875,
"learning_rate": 0.0001538961038961039,
"loss": 1.8045,
"step": 313
},
{
"epoch": 0.4,
"grad_norm": 0.369140625,
"learning_rate": 0.0001536796536796537,
"loss": 1.7756,
"step": 314
},
{
"epoch": 0.4,
"grad_norm": 0.35546875,
"learning_rate": 0.00015346320346320346,
"loss": 1.8018,
"step": 315
},
{
"epoch": 0.4,
"grad_norm": 0.287109375,
"learning_rate": 0.00015324675324675325,
"loss": 1.8246,
"step": 316
},
{
"epoch": 0.41,
"grad_norm": 0.28515625,
"learning_rate": 0.00015303030303030304,
"loss": 1.761,
"step": 317
},
{
"epoch": 0.41,
"grad_norm": 0.29296875,
"learning_rate": 0.00015281385281385284,
"loss": 1.773,
"step": 318
},
{
"epoch": 0.41,
"grad_norm": 0.345703125,
"learning_rate": 0.0001525974025974026,
"loss": 1.7889,
"step": 319
},
{
"epoch": 0.41,
"grad_norm": 0.38671875,
"learning_rate": 0.00015238095238095237,
"loss": 1.827,
"step": 320
},
{
"epoch": 0.41,
"grad_norm": 0.333984375,
"learning_rate": 0.0001521645021645022,
"loss": 1.7928,
"step": 321
},
{
"epoch": 0.41,
"grad_norm": 0.33203125,
"learning_rate": 0.00015194805194805196,
"loss": 1.7618,
"step": 322
},
{
"epoch": 0.41,
"grad_norm": 0.36328125,
"learning_rate": 0.00015173160173160175,
"loss": 1.7576,
"step": 323
},
{
"epoch": 0.41,
"grad_norm": 0.2890625,
"learning_rate": 0.00015151515151515152,
"loss": 1.6683,
"step": 324
},
{
"epoch": 0.42,
"grad_norm": 0.27734375,
"learning_rate": 0.0001512987012987013,
"loss": 1.7967,
"step": 325
},
{
"epoch": 0.42,
"grad_norm": 0.28125,
"learning_rate": 0.0001510822510822511,
"loss": 1.8209,
"step": 326
},
{
"epoch": 0.42,
"grad_norm": 0.39453125,
"learning_rate": 0.00015086580086580087,
"loss": 1.8743,
"step": 327
},
{
"epoch": 0.42,
"grad_norm": 0.27734375,
"learning_rate": 0.00015064935064935066,
"loss": 1.8559,
"step": 328
},
{
"epoch": 0.42,
"grad_norm": 0.337890625,
"learning_rate": 0.00015043290043290043,
"loss": 1.7791,
"step": 329
},
{
"epoch": 0.42,
"grad_norm": 0.353515625,
"learning_rate": 0.00015021645021645022,
"loss": 1.8626,
"step": 330
},
{
"epoch": 0.42,
"grad_norm": 0.4140625,
"learning_rate": 0.00015000000000000001,
"loss": 1.8169,
"step": 331
},
{
"epoch": 0.42,
"grad_norm": 0.373046875,
"learning_rate": 0.00014978354978354978,
"loss": 1.8006,
"step": 332
},
{
"epoch": 0.43,
"grad_norm": 0.302734375,
"learning_rate": 0.00014956709956709957,
"loss": 1.8818,
"step": 333
},
{
"epoch": 0.43,
"grad_norm": 0.423828125,
"learning_rate": 0.00014935064935064934,
"loss": 1.7898,
"step": 334
},
{
"epoch": 0.43,
"grad_norm": 0.314453125,
"learning_rate": 0.00014913419913419916,
"loss": 1.7639,
"step": 335
},
{
"epoch": 0.43,
"grad_norm": 0.375,
"learning_rate": 0.00014891774891774893,
"loss": 1.8276,
"step": 336
},
{
"epoch": 0.43,
"grad_norm": 0.34375,
"learning_rate": 0.00014870129870129872,
"loss": 1.8718,
"step": 337
},
{
"epoch": 0.43,
"grad_norm": 0.310546875,
"learning_rate": 0.00014848484848484849,
"loss": 1.7142,
"step": 338
},
{
"epoch": 0.43,
"grad_norm": 0.330078125,
"learning_rate": 0.00014826839826839828,
"loss": 1.8261,
"step": 339
},
{
"epoch": 0.44,
"grad_norm": 0.328125,
"learning_rate": 0.00014805194805194807,
"loss": 1.8177,
"step": 340
},
{
"epoch": 0.44,
"grad_norm": 0.357421875,
"learning_rate": 0.00014783549783549784,
"loss": 1.739,
"step": 341
},
{
"epoch": 0.44,
"grad_norm": 0.291015625,
"learning_rate": 0.00014761904761904763,
"loss": 1.7867,
"step": 342
},
{
"epoch": 0.44,
"grad_norm": 0.380859375,
"learning_rate": 0.0001474025974025974,
"loss": 1.7825,
"step": 343
},
{
"epoch": 0.44,
"grad_norm": 0.29296875,
"learning_rate": 0.0001471861471861472,
"loss": 1.7784,
"step": 344
},
{
"epoch": 0.44,
"grad_norm": 0.2890625,
"learning_rate": 0.00014696969696969698,
"loss": 1.8077,
"step": 345
},
{
"epoch": 0.44,
"grad_norm": 0.296875,
"learning_rate": 0.00014675324675324675,
"loss": 1.7616,
"step": 346
},
{
"epoch": 0.44,
"grad_norm": 0.2890625,
"learning_rate": 0.00014653679653679654,
"loss": 1.7738,
"step": 347
},
{
"epoch": 0.45,
"grad_norm": 0.345703125,
"learning_rate": 0.00014632034632034634,
"loss": 1.7019,
"step": 348
},
{
"epoch": 0.45,
"grad_norm": 0.33984375,
"learning_rate": 0.00014610389610389613,
"loss": 1.6911,
"step": 349
},
{
"epoch": 0.45,
"grad_norm": 0.3359375,
"learning_rate": 0.0001458874458874459,
"loss": 1.7708,
"step": 350
},
{
"epoch": 0.45,
"eval_loss": 1.7709890604019165,
"eval_runtime": 125.3163,
"eval_samples_per_second": 39.899,
"eval_steps_per_second": 1.253,
"step": 350
},
{
"epoch": 0.45,
"grad_norm": 0.349609375,
"learning_rate": 0.00014567099567099566,
"loss": 1.76,
"step": 351
},
{
"epoch": 0.45,
"grad_norm": 0.38671875,
"learning_rate": 0.00014545454545454546,
"loss": 1.7913,
"step": 352
},
{
"epoch": 0.45,
"grad_norm": 0.421875,
"learning_rate": 0.00014523809523809525,
"loss": 1.8083,
"step": 353
},
{
"epoch": 0.45,
"grad_norm": 0.388671875,
"learning_rate": 0.00014502164502164504,
"loss": 1.7886,
"step": 354
},
{
"epoch": 0.45,
"grad_norm": 0.265625,
"learning_rate": 0.0001448051948051948,
"loss": 1.8125,
"step": 355
},
{
"epoch": 0.46,
"grad_norm": 0.353515625,
"learning_rate": 0.00014458874458874458,
"loss": 1.6922,
"step": 356
},
{
"epoch": 0.46,
"grad_norm": 0.41796875,
"learning_rate": 0.00014437229437229437,
"loss": 1.6483,
"step": 357
},
{
"epoch": 0.46,
"grad_norm": 0.38671875,
"learning_rate": 0.00014415584415584416,
"loss": 1.805,
"step": 358
},
{
"epoch": 0.46,
"grad_norm": 0.29296875,
"learning_rate": 0.00014393939393939396,
"loss": 1.7458,
"step": 359
},
{
"epoch": 0.46,
"grad_norm": 0.416015625,
"learning_rate": 0.00014372294372294372,
"loss": 1.7989,
"step": 360
},
{
"epoch": 0.46,
"grad_norm": 0.404296875,
"learning_rate": 0.00014350649350649352,
"loss": 1.7271,
"step": 361
},
{
"epoch": 0.46,
"grad_norm": 0.296875,
"learning_rate": 0.0001432900432900433,
"loss": 1.7804,
"step": 362
},
{
"epoch": 0.46,
"grad_norm": 0.296875,
"learning_rate": 0.00014307359307359307,
"loss": 1.8581,
"step": 363
},
{
"epoch": 0.47,
"grad_norm": 0.353515625,
"learning_rate": 0.00014285714285714287,
"loss": 1.757,
"step": 364
},
{
"epoch": 0.47,
"grad_norm": 0.3203125,
"learning_rate": 0.00014264069264069263,
"loss": 1.7536,
"step": 365
},
{
"epoch": 0.47,
"grad_norm": 0.3203125,
"learning_rate": 0.00014242424242424243,
"loss": 1.7191,
"step": 366
},
{
"epoch": 0.47,
"grad_norm": 0.384765625,
"learning_rate": 0.00014220779220779222,
"loss": 1.7741,
"step": 367
},
{
"epoch": 0.47,
"grad_norm": 0.3359375,
"learning_rate": 0.00014199134199134201,
"loss": 1.7626,
"step": 368
},
{
"epoch": 0.47,
"grad_norm": 0.4140625,
"learning_rate": 0.00014177489177489178,
"loss": 1.8351,
"step": 369
},
{
"epoch": 0.47,
"grad_norm": 0.4921875,
"learning_rate": 0.00014155844155844155,
"loss": 1.7943,
"step": 370
},
{
"epoch": 0.47,
"grad_norm": 0.28515625,
"learning_rate": 0.00014134199134199137,
"loss": 1.7729,
"step": 371
},
{
"epoch": 0.48,
"grad_norm": 0.36328125,
"learning_rate": 0.00014112554112554113,
"loss": 1.853,
"step": 372
},
{
"epoch": 0.48,
"grad_norm": 0.373046875,
"learning_rate": 0.00014090909090909093,
"loss": 1.7805,
"step": 373
},
{
"epoch": 0.48,
"grad_norm": 0.375,
"learning_rate": 0.0001406926406926407,
"loss": 1.805,
"step": 374
},
{
"epoch": 0.48,
"grad_norm": 0.365234375,
"learning_rate": 0.00014047619047619049,
"loss": 1.7717,
"step": 375
},
{
"epoch": 0.48,
"grad_norm": 0.375,
"learning_rate": 0.00014025974025974028,
"loss": 1.793,
"step": 376
},
{
"epoch": 0.48,
"grad_norm": 0.353515625,
"learning_rate": 0.00014004329004329005,
"loss": 1.8017,
"step": 377
},
{
"epoch": 0.48,
"grad_norm": 0.359375,
"learning_rate": 0.00013982683982683984,
"loss": 1.758,
"step": 378
},
{
"epoch": 0.48,
"grad_norm": 0.35546875,
"learning_rate": 0.0001396103896103896,
"loss": 1.7761,
"step": 379
},
{
"epoch": 0.49,
"grad_norm": 0.33203125,
"learning_rate": 0.0001393939393939394,
"loss": 1.7626,
"step": 380
},
{
"epoch": 0.49,
"grad_norm": 0.361328125,
"learning_rate": 0.0001391774891774892,
"loss": 1.8463,
"step": 381
},
{
"epoch": 0.49,
"grad_norm": 0.4140625,
"learning_rate": 0.00013896103896103896,
"loss": 1.7563,
"step": 382
},
{
"epoch": 0.49,
"grad_norm": 0.318359375,
"learning_rate": 0.00013874458874458875,
"loss": 1.7085,
"step": 383
},
{
"epoch": 0.49,
"grad_norm": 0.337890625,
"learning_rate": 0.00013852813852813852,
"loss": 1.8202,
"step": 384
},
{
"epoch": 0.49,
"grad_norm": 0.30078125,
"learning_rate": 0.00013831168831168834,
"loss": 1.7618,
"step": 385
},
{
"epoch": 0.49,
"grad_norm": 0.3046875,
"learning_rate": 0.0001380952380952381,
"loss": 1.8142,
"step": 386
},
{
"epoch": 0.5,
"grad_norm": 0.318359375,
"learning_rate": 0.0001378787878787879,
"loss": 1.6778,
"step": 387
},
{
"epoch": 0.5,
"grad_norm": 0.287109375,
"learning_rate": 0.00013766233766233766,
"loss": 1.749,
"step": 388
},
{
"epoch": 0.5,
"grad_norm": 0.310546875,
"learning_rate": 0.00013744588744588746,
"loss": 1.7236,
"step": 389
},
{
"epoch": 0.5,
"grad_norm": 0.322265625,
"learning_rate": 0.00013722943722943725,
"loss": 1.7329,
"step": 390
},
{
"epoch": 0.5,
"grad_norm": 0.384765625,
"learning_rate": 0.00013701298701298702,
"loss": 1.8287,
"step": 391
},
{
"epoch": 0.5,
"grad_norm": 0.318359375,
"learning_rate": 0.0001367965367965368,
"loss": 1.8173,
"step": 392
},
{
"epoch": 0.5,
"grad_norm": 0.5234375,
"learning_rate": 0.00013658008658008658,
"loss": 1.8881,
"step": 393
},
{
"epoch": 0.5,
"grad_norm": 0.4453125,
"learning_rate": 0.00013636363636363637,
"loss": 1.7895,
"step": 394
},
{
"epoch": 0.51,
"grad_norm": 0.310546875,
"learning_rate": 0.00013614718614718616,
"loss": 1.7531,
"step": 395
},
{
"epoch": 0.51,
"grad_norm": 0.337890625,
"learning_rate": 0.00013593073593073593,
"loss": 1.7601,
"step": 396
},
{
"epoch": 0.51,
"grad_norm": 0.353515625,
"learning_rate": 0.00013571428571428572,
"loss": 1.6574,
"step": 397
},
{
"epoch": 0.51,
"grad_norm": 0.345703125,
"learning_rate": 0.0001354978354978355,
"loss": 1.7577,
"step": 398
},
{
"epoch": 0.51,
"grad_norm": 0.455078125,
"learning_rate": 0.0001352813852813853,
"loss": 1.6886,
"step": 399
},
{
"epoch": 0.51,
"grad_norm": 0.337890625,
"learning_rate": 0.00013506493506493507,
"loss": 1.7786,
"step": 400
},
{
"epoch": 0.51,
"eval_loss": 1.7625454664230347,
"eval_runtime": 125.3037,
"eval_samples_per_second": 39.903,
"eval_steps_per_second": 1.253,
"step": 400
},
{
"epoch": 0.51,
"grad_norm": 0.392578125,
"learning_rate": 0.00013484848484848484,
"loss": 1.7421,
"step": 401
},
{
"epoch": 0.51,
"grad_norm": 0.53125,
"learning_rate": 0.00013463203463203463,
"loss": 1.7626,
"step": 402
},
{
"epoch": 0.52,
"grad_norm": 0.34765625,
"learning_rate": 0.00013441558441558443,
"loss": 1.7943,
"step": 403
},
{
"epoch": 0.52,
"grad_norm": 0.435546875,
"learning_rate": 0.00013419913419913422,
"loss": 1.8116,
"step": 404
},
{
"epoch": 0.52,
"grad_norm": 0.419921875,
"learning_rate": 0.000133982683982684,
"loss": 1.7532,
"step": 405
},
{
"epoch": 0.52,
"grad_norm": 0.345703125,
"learning_rate": 0.00013376623376623375,
"loss": 1.7478,
"step": 406
},
{
"epoch": 0.52,
"grad_norm": 0.40234375,
"learning_rate": 0.00013354978354978355,
"loss": 1.8208,
"step": 407
},
{
"epoch": 0.52,
"grad_norm": 0.314453125,
"learning_rate": 0.00013333333333333334,
"loss": 1.7518,
"step": 408
},
{
"epoch": 0.52,
"grad_norm": 0.470703125,
"learning_rate": 0.00013311688311688313,
"loss": 1.8063,
"step": 409
},
{
"epoch": 0.52,
"grad_norm": 0.419921875,
"learning_rate": 0.0001329004329004329,
"loss": 1.7366,
"step": 410
},
{
"epoch": 0.53,
"grad_norm": 0.326171875,
"learning_rate": 0.0001326839826839827,
"loss": 1.7605,
"step": 411
},
{
"epoch": 0.53,
"grad_norm": 0.287109375,
"learning_rate": 0.00013246753246753249,
"loss": 1.8454,
"step": 412
},
{
"epoch": 0.53,
"grad_norm": 0.376953125,
"learning_rate": 0.00013225108225108225,
"loss": 1.7342,
"step": 413
},
{
"epoch": 0.53,
"grad_norm": 0.416015625,
"learning_rate": 0.00013203463203463205,
"loss": 1.7031,
"step": 414
},
{
"epoch": 0.53,
"grad_norm": 0.3984375,
"learning_rate": 0.0001318181818181818,
"loss": 1.8397,
"step": 415
},
{
"epoch": 0.53,
"grad_norm": 0.369140625,
"learning_rate": 0.0001316017316017316,
"loss": 1.8038,
"step": 416
},
{
"epoch": 0.53,
"grad_norm": 0.369140625,
"learning_rate": 0.0001313852813852814,
"loss": 1.7529,
"step": 417
},
{
"epoch": 0.53,
"grad_norm": 0.396484375,
"learning_rate": 0.0001311688311688312,
"loss": 1.7746,
"step": 418
},
{
"epoch": 0.54,
"grad_norm": 0.31640625,
"learning_rate": 0.00013095238095238096,
"loss": 1.8441,
"step": 419
},
{
"epoch": 0.54,
"grad_norm": 0.287109375,
"learning_rate": 0.00013073593073593072,
"loss": 1.7302,
"step": 420
},
{
"epoch": 0.54,
"grad_norm": 0.470703125,
"learning_rate": 0.00013051948051948052,
"loss": 1.7149,
"step": 421
},
{
"epoch": 0.54,
"grad_norm": 0.330078125,
"learning_rate": 0.0001303030303030303,
"loss": 1.6881,
"step": 422
},
{
"epoch": 0.54,
"grad_norm": 0.28515625,
"learning_rate": 0.0001300865800865801,
"loss": 1.7627,
"step": 423
},
{
"epoch": 0.54,
"grad_norm": 0.310546875,
"learning_rate": 0.00012987012987012987,
"loss": 1.7386,
"step": 424
},
{
"epoch": 0.54,
"grad_norm": 0.310546875,
"learning_rate": 0.00012965367965367964,
"loss": 1.7331,
"step": 425
},
{
"epoch": 0.55,
"grad_norm": 0.384765625,
"learning_rate": 0.00012943722943722946,
"loss": 1.766,
"step": 426
},
{
"epoch": 0.55,
"grad_norm": 0.3828125,
"learning_rate": 0.00012922077922077922,
"loss": 1.7111,
"step": 427
},
{
"epoch": 0.55,
"grad_norm": 0.37890625,
"learning_rate": 0.00012900432900432902,
"loss": 1.7874,
"step": 428
},
{
"epoch": 0.55,
"grad_norm": 0.380859375,
"learning_rate": 0.00012878787878787878,
"loss": 1.7565,
"step": 429
},
{
"epoch": 0.55,
"grad_norm": 0.37109375,
"learning_rate": 0.00012857142857142858,
"loss": 1.8451,
"step": 430
},
{
"epoch": 0.55,
"grad_norm": 0.419921875,
"learning_rate": 0.00012835497835497837,
"loss": 1.7024,
"step": 431
},
{
"epoch": 0.55,
"grad_norm": 0.294921875,
"learning_rate": 0.00012813852813852814,
"loss": 1.7037,
"step": 432
},
{
"epoch": 0.55,
"grad_norm": 0.310546875,
"learning_rate": 0.00012792207792207793,
"loss": 1.7166,
"step": 433
},
{
"epoch": 0.56,
"grad_norm": 0.404296875,
"learning_rate": 0.0001277056277056277,
"loss": 1.7534,
"step": 434
},
{
"epoch": 0.56,
"grad_norm": 0.3359375,
"learning_rate": 0.00012748917748917752,
"loss": 1.7315,
"step": 435
},
{
"epoch": 0.56,
"grad_norm": 0.349609375,
"learning_rate": 0.00012727272727272728,
"loss": 1.7707,
"step": 436
},
{
"epoch": 0.56,
"grad_norm": 0.328125,
"learning_rate": 0.00012705627705627707,
"loss": 1.811,
"step": 437
},
{
"epoch": 0.56,
"grad_norm": 0.2890625,
"learning_rate": 0.00012683982683982684,
"loss": 1.8211,
"step": 438
},
{
"epoch": 0.56,
"grad_norm": 0.330078125,
"learning_rate": 0.00012662337662337663,
"loss": 1.6992,
"step": 439
},
{
"epoch": 0.56,
"grad_norm": 0.33203125,
"learning_rate": 0.00012640692640692643,
"loss": 1.8294,
"step": 440
},
{
"epoch": 0.56,
"grad_norm": 0.326171875,
"learning_rate": 0.0001261904761904762,
"loss": 1.7351,
"step": 441
},
{
"epoch": 0.57,
"grad_norm": 0.384765625,
"learning_rate": 0.000125974025974026,
"loss": 1.732,
"step": 442
},
{
"epoch": 0.57,
"grad_norm": 0.41796875,
"learning_rate": 0.00012575757575757575,
"loss": 1.7839,
"step": 443
},
{
"epoch": 0.57,
"grad_norm": 0.34375,
"learning_rate": 0.00012554112554112555,
"loss": 1.7892,
"step": 444
},
{
"epoch": 0.57,
"grad_norm": 0.37890625,
"learning_rate": 0.00012532467532467534,
"loss": 1.7428,
"step": 445
},
{
"epoch": 0.57,
"grad_norm": 0.3359375,
"learning_rate": 0.0001251082251082251,
"loss": 1.8055,
"step": 446
},
{
"epoch": 0.57,
"grad_norm": 0.384765625,
"learning_rate": 0.0001248917748917749,
"loss": 1.8227,
"step": 447
},
{
"epoch": 0.57,
"grad_norm": 0.349609375,
"learning_rate": 0.00012467532467532467,
"loss": 1.7273,
"step": 448
},
{
"epoch": 0.57,
"grad_norm": 0.328125,
"learning_rate": 0.00012445887445887449,
"loss": 1.8338,
"step": 449
},
{
"epoch": 0.58,
"grad_norm": 0.4140625,
"learning_rate": 0.00012424242424242425,
"loss": 1.71,
"step": 450
},
{
"epoch": 0.58,
"eval_loss": 1.7571938037872314,
"eval_runtime": 125.7305,
"eval_samples_per_second": 39.768,
"eval_steps_per_second": 1.249,
"step": 450
},
{
"epoch": 0.58,
"grad_norm": 0.408203125,
"learning_rate": 0.00012402597402597402,
"loss": 1.6852,
"step": 451
},
{
"epoch": 0.58,
"grad_norm": 0.3125,
"learning_rate": 0.0001238095238095238,
"loss": 1.7876,
"step": 452
},
{
"epoch": 0.58,
"grad_norm": 0.314453125,
"learning_rate": 0.0001235930735930736,
"loss": 1.7676,
"step": 453
},
{
"epoch": 0.58,
"grad_norm": 0.439453125,
"learning_rate": 0.0001233766233766234,
"loss": 1.7567,
"step": 454
},
{
"epoch": 0.58,
"grad_norm": 0.294921875,
"learning_rate": 0.00012316017316017316,
"loss": 1.7835,
"step": 455
},
{
"epoch": 0.58,
"grad_norm": 0.3046875,
"learning_rate": 0.00012294372294372293,
"loss": 1.8254,
"step": 456
},
{
"epoch": 0.58,
"grad_norm": 0.30078125,
"learning_rate": 0.00012272727272727272,
"loss": 1.7415,
"step": 457
},
{
"epoch": 0.59,
"grad_norm": 0.3359375,
"learning_rate": 0.00012251082251082252,
"loss": 1.7718,
"step": 458
},
{
"epoch": 0.59,
"grad_norm": 0.361328125,
"learning_rate": 0.0001222943722943723,
"loss": 1.7734,
"step": 459
},
{
"epoch": 0.59,
"grad_norm": 0.3125,
"learning_rate": 0.00012207792207792208,
"loss": 1.7413,
"step": 460
},
{
"epoch": 0.59,
"grad_norm": 0.283203125,
"learning_rate": 0.00012186147186147187,
"loss": 1.8832,
"step": 461
},
{
"epoch": 0.59,
"grad_norm": 0.328125,
"learning_rate": 0.00012164502164502165,
"loss": 1.71,
"step": 462
},
{
"epoch": 0.59,
"grad_norm": 0.3203125,
"learning_rate": 0.00012142857142857143,
"loss": 1.7611,
"step": 463
},
{
"epoch": 0.59,
"grad_norm": 0.373046875,
"learning_rate": 0.00012121212121212122,
"loss": 1.809,
"step": 464
},
{
"epoch": 0.6,
"grad_norm": 0.29296875,
"learning_rate": 0.00012099567099567099,
"loss": 1.6685,
"step": 465
},
{
"epoch": 0.6,
"grad_norm": 0.310546875,
"learning_rate": 0.0001207792207792208,
"loss": 1.7246,
"step": 466
},
{
"epoch": 0.6,
"grad_norm": 0.30859375,
"learning_rate": 0.00012056277056277056,
"loss": 1.7187,
"step": 467
},
{
"epoch": 0.6,
"grad_norm": 0.296875,
"learning_rate": 0.00012034632034632037,
"loss": 1.7165,
"step": 468
},
{
"epoch": 0.6,
"grad_norm": 0.353515625,
"learning_rate": 0.00012012987012987014,
"loss": 1.7451,
"step": 469
},
{
"epoch": 0.6,
"grad_norm": 0.33203125,
"learning_rate": 0.00011991341991341991,
"loss": 1.7889,
"step": 470
},
{
"epoch": 0.6,
"grad_norm": 0.34375,
"learning_rate": 0.00011969696969696971,
"loss": 1.8299,
"step": 471
},
{
"epoch": 0.6,
"grad_norm": 0.314453125,
"learning_rate": 0.00011948051948051949,
"loss": 1.7567,
"step": 472
},
{
"epoch": 0.61,
"grad_norm": 0.3359375,
"learning_rate": 0.00011926406926406928,
"loss": 1.7335,
"step": 473
},
{
"epoch": 0.61,
"grad_norm": 0.30859375,
"learning_rate": 0.00011904761904761905,
"loss": 1.7394,
"step": 474
},
{
"epoch": 0.61,
"grad_norm": 0.34765625,
"learning_rate": 0.00011883116883116883,
"loss": 1.7834,
"step": 475
},
{
"epoch": 0.61,
"grad_norm": 0.322265625,
"learning_rate": 0.00011861471861471862,
"loss": 1.7819,
"step": 476
},
{
"epoch": 0.61,
"grad_norm": 0.271484375,
"learning_rate": 0.0001183982683982684,
"loss": 1.7574,
"step": 477
},
{
"epoch": 0.61,
"grad_norm": 0.330078125,
"learning_rate": 0.0001181818181818182,
"loss": 1.7031,
"step": 478
},
{
"epoch": 0.61,
"grad_norm": 0.30859375,
"learning_rate": 0.00011796536796536797,
"loss": 1.7361,
"step": 479
},
{
"epoch": 0.61,
"grad_norm": 0.333984375,
"learning_rate": 0.00011774891774891777,
"loss": 1.7638,
"step": 480
},
{
"epoch": 0.62,
"grad_norm": 0.34375,
"learning_rate": 0.00011753246753246753,
"loss": 1.7476,
"step": 481
},
{
"epoch": 0.62,
"grad_norm": 0.333984375,
"learning_rate": 0.00011731601731601731,
"loss": 1.6884,
"step": 482
},
{
"epoch": 0.62,
"grad_norm": 0.296875,
"learning_rate": 0.0001170995670995671,
"loss": 1.6966,
"step": 483
},
{
"epoch": 0.62,
"grad_norm": 0.306640625,
"learning_rate": 0.00011688311688311689,
"loss": 1.7041,
"step": 484
},
{
"epoch": 0.62,
"grad_norm": 0.33203125,
"learning_rate": 0.00011666666666666668,
"loss": 1.7788,
"step": 485
},
{
"epoch": 0.62,
"grad_norm": 0.328125,
"learning_rate": 0.00011645021645021646,
"loss": 1.7744,
"step": 486
},
{
"epoch": 0.62,
"grad_norm": 0.423828125,
"learning_rate": 0.00011623376623376625,
"loss": 1.7492,
"step": 487
},
{
"epoch": 0.62,
"grad_norm": 0.318359375,
"learning_rate": 0.00011601731601731602,
"loss": 1.7537,
"step": 488
},
{
"epoch": 0.63,
"grad_norm": 0.337890625,
"learning_rate": 0.0001158008658008658,
"loss": 1.7363,
"step": 489
},
{
"epoch": 0.63,
"grad_norm": 0.349609375,
"learning_rate": 0.00011558441558441559,
"loss": 1.7846,
"step": 490
},
{
"epoch": 0.63,
"grad_norm": 0.310546875,
"learning_rate": 0.00011536796536796537,
"loss": 1.7081,
"step": 491
},
{
"epoch": 0.63,
"grad_norm": 0.33203125,
"learning_rate": 0.00011515151515151516,
"loss": 1.7275,
"step": 492
},
{
"epoch": 0.63,
"grad_norm": 0.33203125,
"learning_rate": 0.00011493506493506494,
"loss": 1.7196,
"step": 493
},
{
"epoch": 0.63,
"grad_norm": 0.30078125,
"learning_rate": 0.00011471861471861471,
"loss": 1.6845,
"step": 494
},
{
"epoch": 0.63,
"grad_norm": 0.337890625,
"learning_rate": 0.00011450216450216452,
"loss": 1.7443,
"step": 495
},
{
"epoch": 0.63,
"grad_norm": 0.3359375,
"learning_rate": 0.00011428571428571428,
"loss": 1.7104,
"step": 496
},
{
"epoch": 0.64,
"grad_norm": 0.380859375,
"learning_rate": 0.00011406926406926408,
"loss": 1.7307,
"step": 497
},
{
"epoch": 0.64,
"grad_norm": 0.361328125,
"learning_rate": 0.00011385281385281386,
"loss": 1.8338,
"step": 498
},
{
"epoch": 0.64,
"grad_norm": 0.296875,
"learning_rate": 0.00011363636363636365,
"loss": 1.7235,
"step": 499
},
{
"epoch": 0.64,
"grad_norm": 0.291015625,
"learning_rate": 0.00011341991341991343,
"loss": 1.8493,
"step": 500
},
{
"epoch": 0.64,
"eval_loss": 1.7474199533462524,
"eval_runtime": 125.2746,
"eval_samples_per_second": 39.912,
"eval_steps_per_second": 1.253,
"step": 500
},
{
"epoch": 0.64,
"grad_norm": 0.33203125,
"learning_rate": 0.0001132034632034632,
"loss": 1.7369,
"step": 501
},
{
"epoch": 0.64,
"grad_norm": 0.322265625,
"learning_rate": 0.000112987012987013,
"loss": 1.7215,
"step": 502
},
{
"epoch": 0.64,
"grad_norm": 0.36328125,
"learning_rate": 0.00011277056277056277,
"loss": 1.7981,
"step": 503
},
{
"epoch": 0.64,
"grad_norm": 0.318359375,
"learning_rate": 0.00011255411255411256,
"loss": 1.6949,
"step": 504
},
{
"epoch": 0.65,
"grad_norm": 0.38671875,
"learning_rate": 0.00011233766233766234,
"loss": 1.7577,
"step": 505
},
{
"epoch": 0.65,
"grad_norm": 0.52734375,
"learning_rate": 0.00011212121212121212,
"loss": 1.7396,
"step": 506
},
{
"epoch": 0.65,
"grad_norm": 0.3359375,
"learning_rate": 0.00011190476190476191,
"loss": 1.7094,
"step": 507
},
{
"epoch": 0.65,
"grad_norm": 0.314453125,
"learning_rate": 0.00011168831168831168,
"loss": 1.7354,
"step": 508
},
{
"epoch": 0.65,
"grad_norm": 0.37109375,
"learning_rate": 0.00011147186147186149,
"loss": 1.7109,
"step": 509
},
{
"epoch": 0.65,
"grad_norm": 0.4140625,
"learning_rate": 0.00011125541125541125,
"loss": 1.7809,
"step": 510
},
{
"epoch": 0.65,
"grad_norm": 0.455078125,
"learning_rate": 0.00011103896103896105,
"loss": 1.7939,
"step": 511
},
{
"epoch": 0.66,
"grad_norm": 0.291015625,
"learning_rate": 0.00011082251082251083,
"loss": 1.7942,
"step": 512
},
{
"epoch": 0.66,
"grad_norm": 0.609375,
"learning_rate": 0.00011060606060606061,
"loss": 1.7189,
"step": 513
},
{
"epoch": 0.66,
"grad_norm": 0.67578125,
"learning_rate": 0.0001103896103896104,
"loss": 1.7662,
"step": 514
},
{
"epoch": 0.66,
"grad_norm": 0.353515625,
"learning_rate": 0.00011017316017316017,
"loss": 1.7288,
"step": 515
},
{
"epoch": 0.66,
"grad_norm": 0.322265625,
"learning_rate": 0.00010995670995670997,
"loss": 1.715,
"step": 516
},
{
"epoch": 0.66,
"grad_norm": 0.40625,
"learning_rate": 0.00010974025974025974,
"loss": 1.6725,
"step": 517
},
{
"epoch": 0.66,
"grad_norm": 0.52734375,
"learning_rate": 0.00010952380952380953,
"loss": 1.7752,
"step": 518
},
{
"epoch": 0.66,
"grad_norm": 0.48828125,
"learning_rate": 0.00010930735930735931,
"loss": 1.7345,
"step": 519
},
{
"epoch": 0.67,
"grad_norm": 0.3203125,
"learning_rate": 0.00010909090909090909,
"loss": 1.7054,
"step": 520
},
{
"epoch": 0.67,
"grad_norm": 0.45703125,
"learning_rate": 0.00010887445887445889,
"loss": 1.8508,
"step": 521
},
{
"epoch": 0.67,
"grad_norm": 0.50390625,
"learning_rate": 0.00010865800865800865,
"loss": 1.723,
"step": 522
},
{
"epoch": 0.67,
"grad_norm": 0.361328125,
"learning_rate": 0.00010844155844155846,
"loss": 1.7008,
"step": 523
},
{
"epoch": 0.67,
"grad_norm": 0.330078125,
"learning_rate": 0.00010822510822510823,
"loss": 1.6947,
"step": 524
},
{
"epoch": 0.67,
"grad_norm": 0.439453125,
"learning_rate": 0.000108008658008658,
"loss": 1.8002,
"step": 525
},
{
"epoch": 0.67,
"grad_norm": 0.419921875,
"learning_rate": 0.0001077922077922078,
"loss": 1.7645,
"step": 526
},
{
"epoch": 0.67,
"grad_norm": 0.392578125,
"learning_rate": 0.00010757575757575758,
"loss": 1.7568,
"step": 527
},
{
"epoch": 0.68,
"grad_norm": 0.34375,
"learning_rate": 0.00010735930735930737,
"loss": 1.7684,
"step": 528
},
{
"epoch": 0.68,
"grad_norm": 0.337890625,
"learning_rate": 0.00010714285714285715,
"loss": 1.7795,
"step": 529
},
{
"epoch": 0.68,
"grad_norm": 0.375,
"learning_rate": 0.00010692640692640694,
"loss": 1.7471,
"step": 530
},
{
"epoch": 0.68,
"grad_norm": 0.369140625,
"learning_rate": 0.00010670995670995671,
"loss": 1.8058,
"step": 531
},
{
"epoch": 0.68,
"grad_norm": 0.326171875,
"learning_rate": 0.00010649350649350649,
"loss": 1.673,
"step": 532
},
{
"epoch": 0.68,
"grad_norm": 0.365234375,
"learning_rate": 0.00010627705627705628,
"loss": 1.728,
"step": 533
},
{
"epoch": 0.68,
"grad_norm": 0.423828125,
"learning_rate": 0.00010606060606060606,
"loss": 1.6786,
"step": 534
},
{
"epoch": 0.68,
"grad_norm": 0.37890625,
"learning_rate": 0.00010584415584415586,
"loss": 1.733,
"step": 535
},
{
"epoch": 0.69,
"grad_norm": 0.34375,
"learning_rate": 0.00010562770562770564,
"loss": 1.7435,
"step": 536
},
{
"epoch": 0.69,
"grad_norm": 0.3125,
"learning_rate": 0.00010541125541125543,
"loss": 1.7421,
"step": 537
},
{
"epoch": 0.69,
"grad_norm": 0.376953125,
"learning_rate": 0.0001051948051948052,
"loss": 1.8177,
"step": 538
},
{
"epoch": 0.69,
"grad_norm": 0.390625,
"learning_rate": 0.00010497835497835498,
"loss": 1.853,
"step": 539
},
{
"epoch": 0.69,
"grad_norm": 0.384765625,
"learning_rate": 0.00010476190476190477,
"loss": 1.7235,
"step": 540
},
{
"epoch": 0.69,
"grad_norm": 0.35546875,
"learning_rate": 0.00010454545454545455,
"loss": 1.6917,
"step": 541
},
{
"epoch": 0.69,
"grad_norm": 0.314453125,
"learning_rate": 0.00010432900432900434,
"loss": 1.7533,
"step": 542
},
{
"epoch": 0.69,
"grad_norm": 0.390625,
"learning_rate": 0.00010411255411255412,
"loss": 1.699,
"step": 543
},
{
"epoch": 0.7,
"grad_norm": 0.32421875,
"learning_rate": 0.00010389610389610389,
"loss": 1.7324,
"step": 544
},
{
"epoch": 0.7,
"grad_norm": 0.3515625,
"learning_rate": 0.00010367965367965368,
"loss": 1.7698,
"step": 545
},
{
"epoch": 0.7,
"grad_norm": 0.294921875,
"learning_rate": 0.00010346320346320346,
"loss": 1.7495,
"step": 546
},
{
"epoch": 0.7,
"grad_norm": 0.318359375,
"learning_rate": 0.00010324675324675325,
"loss": 1.7885,
"step": 547
},
{
"epoch": 0.7,
"grad_norm": 0.310546875,
"learning_rate": 0.00010303030303030303,
"loss": 1.7624,
"step": 548
},
{
"epoch": 0.7,
"grad_norm": 0.306640625,
"learning_rate": 0.00010281385281385283,
"loss": 1.7373,
"step": 549
},
{
"epoch": 0.7,
"grad_norm": 0.353515625,
"learning_rate": 0.00010259740259740261,
"loss": 1.7663,
"step": 550
},
{
"epoch": 0.7,
"eval_loss": 1.7420332431793213,
"eval_runtime": 125.4197,
"eval_samples_per_second": 39.866,
"eval_steps_per_second": 1.252,
"step": 550
},
{
"epoch": 0.71,
"grad_norm": 0.326171875,
"learning_rate": 0.00010238095238095237,
"loss": 1.8104,
"step": 551
},
{
"epoch": 0.71,
"grad_norm": 0.34375,
"learning_rate": 0.00010216450216450218,
"loss": 1.7708,
"step": 552
},
{
"epoch": 0.71,
"grad_norm": 0.3984375,
"learning_rate": 0.00010194805194805195,
"loss": 1.7057,
"step": 553
},
{
"epoch": 0.71,
"grad_norm": 0.328125,
"learning_rate": 0.00010173160173160174,
"loss": 1.718,
"step": 554
},
{
"epoch": 0.71,
"grad_norm": 0.3671875,
"learning_rate": 0.00010151515151515152,
"loss": 1.6913,
"step": 555
},
{
"epoch": 0.71,
"grad_norm": 0.5078125,
"learning_rate": 0.0001012987012987013,
"loss": 1.7444,
"step": 556
},
{
"epoch": 0.71,
"grad_norm": 0.357421875,
"learning_rate": 0.00010108225108225109,
"loss": 1.7699,
"step": 557
},
{
"epoch": 0.71,
"grad_norm": 0.423828125,
"learning_rate": 0.00010086580086580086,
"loss": 1.8066,
"step": 558
},
{
"epoch": 0.72,
"grad_norm": 0.333984375,
"learning_rate": 0.00010064935064935067,
"loss": 1.7054,
"step": 559
},
{
"epoch": 0.72,
"grad_norm": 0.41796875,
"learning_rate": 0.00010043290043290043,
"loss": 1.7562,
"step": 560
},
{
"epoch": 0.72,
"grad_norm": 0.41015625,
"learning_rate": 0.00010021645021645023,
"loss": 1.6979,
"step": 561
},
{
"epoch": 0.72,
"grad_norm": 0.34765625,
"learning_rate": 0.0001,
"loss": 1.8067,
"step": 562
},
{
"epoch": 0.72,
"grad_norm": 0.31640625,
"learning_rate": 9.978354978354978e-05,
"loss": 1.7718,
"step": 563
},
{
"epoch": 0.72,
"grad_norm": 0.36328125,
"learning_rate": 9.956709956709958e-05,
"loss": 1.8256,
"step": 564
},
{
"epoch": 0.72,
"grad_norm": 0.33984375,
"learning_rate": 9.935064935064936e-05,
"loss": 1.7328,
"step": 565
},
{
"epoch": 0.72,
"grad_norm": 0.361328125,
"learning_rate": 9.913419913419914e-05,
"loss": 1.6943,
"step": 566
},
{
"epoch": 0.73,
"grad_norm": 0.380859375,
"learning_rate": 9.891774891774892e-05,
"loss": 1.7398,
"step": 567
},
{
"epoch": 0.73,
"grad_norm": 0.39453125,
"learning_rate": 9.870129870129871e-05,
"loss": 1.6486,
"step": 568
},
{
"epoch": 0.73,
"grad_norm": 0.388671875,
"learning_rate": 9.848484848484849e-05,
"loss": 1.7058,
"step": 569
},
{
"epoch": 0.73,
"grad_norm": 0.30859375,
"learning_rate": 9.826839826839827e-05,
"loss": 1.7299,
"step": 570
},
{
"epoch": 0.73,
"grad_norm": 0.30078125,
"learning_rate": 9.805194805194806e-05,
"loss": 1.7634,
"step": 571
},
{
"epoch": 0.73,
"grad_norm": 0.34375,
"learning_rate": 9.783549783549783e-05,
"loss": 1.7341,
"step": 572
},
{
"epoch": 0.73,
"grad_norm": 0.337890625,
"learning_rate": 9.761904761904762e-05,
"loss": 1.7888,
"step": 573
},
{
"epoch": 0.73,
"grad_norm": 0.34375,
"learning_rate": 9.74025974025974e-05,
"loss": 1.7765,
"step": 574
},
{
"epoch": 0.74,
"grad_norm": 0.55078125,
"learning_rate": 9.71861471861472e-05,
"loss": 1.7764,
"step": 575
},
{
"epoch": 0.74,
"grad_norm": 0.314453125,
"learning_rate": 9.696969696969698e-05,
"loss": 1.745,
"step": 576
},
{
"epoch": 0.74,
"grad_norm": 0.357421875,
"learning_rate": 9.675324675324677e-05,
"loss": 1.7382,
"step": 577
},
{
"epoch": 0.74,
"grad_norm": 0.384765625,
"learning_rate": 9.653679653679654e-05,
"loss": 1.7118,
"step": 578
},
{
"epoch": 0.74,
"grad_norm": 0.380859375,
"learning_rate": 9.632034632034633e-05,
"loss": 1.6819,
"step": 579
},
{
"epoch": 0.74,
"grad_norm": 0.326171875,
"learning_rate": 9.610389610389611e-05,
"loss": 1.8091,
"step": 580
},
{
"epoch": 0.74,
"grad_norm": 0.380859375,
"learning_rate": 9.588744588744589e-05,
"loss": 1.796,
"step": 581
},
{
"epoch": 0.74,
"grad_norm": 0.380859375,
"learning_rate": 9.567099567099568e-05,
"loss": 1.7027,
"step": 582
},
{
"epoch": 0.75,
"grad_norm": 0.43359375,
"learning_rate": 9.545454545454546e-05,
"loss": 1.736,
"step": 583
},
{
"epoch": 0.75,
"grad_norm": 0.337890625,
"learning_rate": 9.523809523809524e-05,
"loss": 1.738,
"step": 584
},
{
"epoch": 0.75,
"grad_norm": 0.369140625,
"learning_rate": 9.502164502164502e-05,
"loss": 1.7425,
"step": 585
},
{
"epoch": 0.75,
"grad_norm": 0.333984375,
"learning_rate": 9.480519480519481e-05,
"loss": 1.6909,
"step": 586
},
{
"epoch": 0.75,
"grad_norm": 0.50390625,
"learning_rate": 9.45887445887446e-05,
"loss": 1.7845,
"step": 587
},
{
"epoch": 0.75,
"grad_norm": 0.44140625,
"learning_rate": 9.437229437229437e-05,
"loss": 1.7345,
"step": 588
},
{
"epoch": 0.75,
"grad_norm": 0.283203125,
"learning_rate": 9.415584415584417e-05,
"loss": 1.7717,
"step": 589
},
{
"epoch": 0.75,
"grad_norm": 0.44921875,
"learning_rate": 9.393939393939395e-05,
"loss": 1.7243,
"step": 590
},
{
"epoch": 0.76,
"grad_norm": 0.431640625,
"learning_rate": 9.372294372294373e-05,
"loss": 1.7662,
"step": 591
},
{
"epoch": 0.76,
"grad_norm": 0.40625,
"learning_rate": 9.35064935064935e-05,
"loss": 1.7209,
"step": 592
},
{
"epoch": 0.76,
"grad_norm": 0.3828125,
"learning_rate": 9.32900432900433e-05,
"loss": 1.6923,
"step": 593
},
{
"epoch": 0.76,
"grad_norm": 0.34375,
"learning_rate": 9.307359307359308e-05,
"loss": 1.8138,
"step": 594
},
{
"epoch": 0.76,
"grad_norm": 0.3515625,
"learning_rate": 9.285714285714286e-05,
"loss": 1.7474,
"step": 595
},
{
"epoch": 0.76,
"grad_norm": 0.421875,
"learning_rate": 9.264069264069265e-05,
"loss": 1.776,
"step": 596
},
{
"epoch": 0.76,
"grad_norm": 0.361328125,
"learning_rate": 9.242424242424242e-05,
"loss": 1.7624,
"step": 597
},
{
"epoch": 0.77,
"grad_norm": 0.341796875,
"learning_rate": 9.220779220779221e-05,
"loss": 1.733,
"step": 598
},
{
"epoch": 0.77,
"grad_norm": 0.326171875,
"learning_rate": 9.199134199134199e-05,
"loss": 1.7617,
"step": 599
},
{
"epoch": 0.77,
"grad_norm": 0.326171875,
"learning_rate": 9.177489177489178e-05,
"loss": 1.6983,
"step": 600
},
{
"epoch": 0.77,
"eval_loss": 1.7379374504089355,
"eval_runtime": 124.9706,
"eval_samples_per_second": 40.009,
"eval_steps_per_second": 1.256,
"step": 600
},
{
"epoch": 0.77,
"grad_norm": 0.34375,
"learning_rate": 9.155844155844156e-05,
"loss": 1.7099,
"step": 601
},
{
"epoch": 0.77,
"grad_norm": 0.32421875,
"learning_rate": 9.134199134199136e-05,
"loss": 1.671,
"step": 602
},
{
"epoch": 0.77,
"grad_norm": 0.302734375,
"learning_rate": 9.112554112554112e-05,
"loss": 1.7249,
"step": 603
},
{
"epoch": 0.77,
"grad_norm": 0.318359375,
"learning_rate": 9.090909090909092e-05,
"loss": 1.7958,
"step": 604
},
{
"epoch": 0.77,
"grad_norm": 0.37109375,
"learning_rate": 9.06926406926407e-05,
"loss": 1.7202,
"step": 605
},
{
"epoch": 0.78,
"grad_norm": 0.33203125,
"learning_rate": 9.047619047619048e-05,
"loss": 1.7261,
"step": 606
},
{
"epoch": 0.78,
"grad_norm": 0.32421875,
"learning_rate": 9.025974025974027e-05,
"loss": 1.8016,
"step": 607
},
{
"epoch": 0.78,
"grad_norm": 0.310546875,
"learning_rate": 9.004329004329005e-05,
"loss": 1.7957,
"step": 608
},
{
"epoch": 0.78,
"grad_norm": 0.3125,
"learning_rate": 8.982683982683983e-05,
"loss": 1.7856,
"step": 609
},
{
"epoch": 0.78,
"grad_norm": 0.341796875,
"learning_rate": 8.961038961038961e-05,
"loss": 1.7807,
"step": 610
},
{
"epoch": 0.78,
"grad_norm": 0.341796875,
"learning_rate": 8.93939393939394e-05,
"loss": 1.7536,
"step": 611
},
{
"epoch": 0.78,
"grad_norm": 0.3125,
"learning_rate": 8.917748917748918e-05,
"loss": 1.7499,
"step": 612
},
{
"epoch": 0.78,
"grad_norm": 0.365234375,
"learning_rate": 8.896103896103896e-05,
"loss": 1.7726,
"step": 613
},
{
"epoch": 0.79,
"grad_norm": 0.37109375,
"learning_rate": 8.874458874458876e-05,
"loss": 1.7558,
"step": 614
},
{
"epoch": 0.79,
"grad_norm": 0.298828125,
"learning_rate": 8.852813852813854e-05,
"loss": 1.726,
"step": 615
},
{
"epoch": 0.79,
"grad_norm": 0.330078125,
"learning_rate": 8.831168831168831e-05,
"loss": 1.7632,
"step": 616
},
{
"epoch": 0.79,
"grad_norm": 0.361328125,
"learning_rate": 8.80952380952381e-05,
"loss": 1.7293,
"step": 617
},
{
"epoch": 0.79,
"grad_norm": 0.337890625,
"learning_rate": 8.787878787878789e-05,
"loss": 1.7263,
"step": 618
},
{
"epoch": 0.79,
"grad_norm": 0.35546875,
"learning_rate": 8.766233766233767e-05,
"loss": 1.8403,
"step": 619
},
{
"epoch": 0.79,
"grad_norm": 0.33984375,
"learning_rate": 8.744588744588745e-05,
"loss": 1.6896,
"step": 620
},
{
"epoch": 0.79,
"grad_norm": 0.328125,
"learning_rate": 8.722943722943724e-05,
"loss": 1.797,
"step": 621
},
{
"epoch": 0.8,
"grad_norm": 0.439453125,
"learning_rate": 8.701298701298701e-05,
"loss": 1.7971,
"step": 622
},
{
"epoch": 0.8,
"grad_norm": 0.39453125,
"learning_rate": 8.67965367965368e-05,
"loss": 1.7697,
"step": 623
},
{
"epoch": 0.8,
"grad_norm": 0.326171875,
"learning_rate": 8.658008658008658e-05,
"loss": 1.7567,
"step": 624
},
{
"epoch": 0.8,
"grad_norm": 0.3203125,
"learning_rate": 8.636363636363637e-05,
"loss": 1.659,
"step": 625
},
{
"epoch": 0.8,
"grad_norm": 0.3671875,
"learning_rate": 8.614718614718615e-05,
"loss": 1.7546,
"step": 626
},
{
"epoch": 0.8,
"grad_norm": 0.32421875,
"learning_rate": 8.593073593073593e-05,
"loss": 1.6824,
"step": 627
},
{
"epoch": 0.8,
"grad_norm": 0.42578125,
"learning_rate": 8.571428571428571e-05,
"loss": 1.7049,
"step": 628
},
{
"epoch": 0.8,
"grad_norm": 0.3125,
"learning_rate": 8.549783549783549e-05,
"loss": 1.6639,
"step": 629
},
{
"epoch": 0.81,
"grad_norm": 0.337890625,
"learning_rate": 8.528138528138529e-05,
"loss": 1.7667,
"step": 630
},
{
"epoch": 0.81,
"grad_norm": 0.326171875,
"learning_rate": 8.506493506493507e-05,
"loss": 1.7703,
"step": 631
},
{
"epoch": 0.81,
"grad_norm": 0.388671875,
"learning_rate": 8.484848484848486e-05,
"loss": 1.7526,
"step": 632
},
{
"epoch": 0.81,
"grad_norm": 0.376953125,
"learning_rate": 8.463203463203464e-05,
"loss": 1.7658,
"step": 633
},
{
"epoch": 0.81,
"grad_norm": 0.318359375,
"learning_rate": 8.441558441558442e-05,
"loss": 1.7888,
"step": 634
},
{
"epoch": 0.81,
"grad_norm": 0.3125,
"learning_rate": 8.41991341991342e-05,
"loss": 1.7197,
"step": 635
},
{
"epoch": 0.81,
"grad_norm": 0.328125,
"learning_rate": 8.398268398268399e-05,
"loss": 1.6745,
"step": 636
},
{
"epoch": 0.82,
"grad_norm": 0.369140625,
"learning_rate": 8.376623376623377e-05,
"loss": 1.7168,
"step": 637
},
{
"epoch": 0.82,
"grad_norm": 0.33984375,
"learning_rate": 8.354978354978355e-05,
"loss": 1.6904,
"step": 638
},
{
"epoch": 0.82,
"grad_norm": 0.396484375,
"learning_rate": 8.333333333333334e-05,
"loss": 1.6792,
"step": 639
},
{
"epoch": 0.82,
"grad_norm": 0.34375,
"learning_rate": 8.311688311688312e-05,
"loss": 1.7299,
"step": 640
},
{
"epoch": 0.82,
"grad_norm": 0.365234375,
"learning_rate": 8.29004329004329e-05,
"loss": 1.7334,
"step": 641
},
{
"epoch": 0.82,
"grad_norm": 0.32421875,
"learning_rate": 8.268398268398268e-05,
"loss": 1.7236,
"step": 642
},
{
"epoch": 0.82,
"grad_norm": 0.408203125,
"learning_rate": 8.246753246753248e-05,
"loss": 1.7398,
"step": 643
},
{
"epoch": 0.82,
"grad_norm": 0.337890625,
"learning_rate": 8.225108225108226e-05,
"loss": 1.7407,
"step": 644
},
{
"epoch": 0.83,
"grad_norm": 0.34375,
"learning_rate": 8.203463203463204e-05,
"loss": 1.8405,
"step": 645
},
{
"epoch": 0.83,
"grad_norm": 0.306640625,
"learning_rate": 8.181818181818183e-05,
"loss": 1.7225,
"step": 646
},
{
"epoch": 0.83,
"grad_norm": 0.318359375,
"learning_rate": 8.16017316017316e-05,
"loss": 1.8285,
"step": 647
},
{
"epoch": 0.83,
"grad_norm": 0.4453125,
"learning_rate": 8.138528138528139e-05,
"loss": 1.7646,
"step": 648
},
{
"epoch": 0.83,
"grad_norm": 0.3203125,
"learning_rate": 8.116883116883117e-05,
"loss": 1.7172,
"step": 649
},
{
"epoch": 0.83,
"grad_norm": 0.39453125,
"learning_rate": 8.095238095238096e-05,
"loss": 1.8033,
"step": 650
},
{
"epoch": 0.83,
"eval_loss": 1.7356816530227661,
"eval_runtime": 125.4294,
"eval_samples_per_second": 39.863,
"eval_steps_per_second": 1.252,
"step": 650
},
{
"epoch": 0.83,
"grad_norm": 0.30859375,
"learning_rate": 8.073593073593074e-05,
"loss": 1.7494,
"step": 651
},
{
"epoch": 0.83,
"grad_norm": 0.40234375,
"learning_rate": 8.051948051948052e-05,
"loss": 1.7573,
"step": 652
},
{
"epoch": 0.84,
"grad_norm": 0.46484375,
"learning_rate": 8.03030303030303e-05,
"loss": 1.7712,
"step": 653
},
{
"epoch": 0.84,
"grad_norm": 0.40234375,
"learning_rate": 8.008658008658008e-05,
"loss": 1.6894,
"step": 654
},
{
"epoch": 0.84,
"grad_norm": 0.361328125,
"learning_rate": 7.987012987012987e-05,
"loss": 1.6714,
"step": 655
},
{
"epoch": 0.84,
"grad_norm": 0.33984375,
"learning_rate": 7.965367965367965e-05,
"loss": 1.801,
"step": 656
},
{
"epoch": 0.84,
"grad_norm": 0.41015625,
"learning_rate": 7.943722943722945e-05,
"loss": 1.75,
"step": 657
},
{
"epoch": 0.84,
"grad_norm": 0.421875,
"learning_rate": 7.922077922077923e-05,
"loss": 1.6875,
"step": 658
},
{
"epoch": 0.84,
"grad_norm": 0.421875,
"learning_rate": 7.900432900432901e-05,
"loss": 1.6635,
"step": 659
},
{
"epoch": 0.84,
"grad_norm": 0.302734375,
"learning_rate": 7.878787878787879e-05,
"loss": 1.782,
"step": 660
},
{
"epoch": 0.85,
"grad_norm": 0.3671875,
"learning_rate": 7.857142857142858e-05,
"loss": 1.6838,
"step": 661
},
{
"epoch": 0.85,
"grad_norm": 0.341796875,
"learning_rate": 7.835497835497836e-05,
"loss": 1.6957,
"step": 662
},
{
"epoch": 0.85,
"grad_norm": 0.3359375,
"learning_rate": 7.813852813852814e-05,
"loss": 1.7366,
"step": 663
},
{
"epoch": 0.85,
"grad_norm": 0.404296875,
"learning_rate": 7.792207792207793e-05,
"loss": 1.6709,
"step": 664
},
{
"epoch": 0.85,
"grad_norm": 0.373046875,
"learning_rate": 7.770562770562771e-05,
"loss": 1.7653,
"step": 665
},
{
"epoch": 0.85,
"grad_norm": 0.375,
"learning_rate": 7.748917748917749e-05,
"loss": 1.7467,
"step": 666
},
{
"epoch": 0.85,
"grad_norm": 0.3046875,
"learning_rate": 7.727272727272727e-05,
"loss": 1.7499,
"step": 667
},
{
"epoch": 0.85,
"grad_norm": 0.337890625,
"learning_rate": 7.705627705627707e-05,
"loss": 1.7462,
"step": 668
},
{
"epoch": 0.86,
"grad_norm": 0.3828125,
"learning_rate": 7.683982683982685e-05,
"loss": 1.6883,
"step": 669
},
{
"epoch": 0.86,
"grad_norm": 0.337890625,
"learning_rate": 7.662337662337662e-05,
"loss": 1.7674,
"step": 670
},
{
"epoch": 0.86,
"grad_norm": 0.37890625,
"learning_rate": 7.640692640692642e-05,
"loss": 1.7388,
"step": 671
},
{
"epoch": 0.86,
"grad_norm": 0.33203125,
"learning_rate": 7.619047619047618e-05,
"loss": 1.7206,
"step": 672
},
{
"epoch": 0.86,
"grad_norm": 0.341796875,
"learning_rate": 7.597402597402598e-05,
"loss": 1.749,
"step": 673
},
{
"epoch": 0.86,
"grad_norm": 0.361328125,
"learning_rate": 7.575757575757576e-05,
"loss": 1.7318,
"step": 674
},
{
"epoch": 0.86,
"grad_norm": 0.333984375,
"learning_rate": 7.554112554112555e-05,
"loss": 1.7234,
"step": 675
},
{
"epoch": 0.87,
"grad_norm": 0.3359375,
"learning_rate": 7.532467532467533e-05,
"loss": 1.6407,
"step": 676
},
{
"epoch": 0.87,
"grad_norm": 0.431640625,
"learning_rate": 7.510822510822511e-05,
"loss": 1.7951,
"step": 677
},
{
"epoch": 0.87,
"grad_norm": 0.49609375,
"learning_rate": 7.489177489177489e-05,
"loss": 1.7958,
"step": 678
},
{
"epoch": 0.87,
"grad_norm": 0.345703125,
"learning_rate": 7.467532467532467e-05,
"loss": 1.745,
"step": 679
},
{
"epoch": 0.87,
"grad_norm": 0.396484375,
"learning_rate": 7.445887445887446e-05,
"loss": 1.6285,
"step": 680
},
{
"epoch": 0.87,
"grad_norm": 0.390625,
"learning_rate": 7.424242424242424e-05,
"loss": 1.792,
"step": 681
},
{
"epoch": 0.87,
"grad_norm": 0.466796875,
"learning_rate": 7.402597402597404e-05,
"loss": 1.8207,
"step": 682
},
{
"epoch": 0.87,
"grad_norm": 0.4609375,
"learning_rate": 7.380952380952382e-05,
"loss": 1.7013,
"step": 683
},
{
"epoch": 0.88,
"grad_norm": 0.349609375,
"learning_rate": 7.35930735930736e-05,
"loss": 1.759,
"step": 684
},
{
"epoch": 0.88,
"grad_norm": 0.3671875,
"learning_rate": 7.337662337662338e-05,
"loss": 1.7398,
"step": 685
},
{
"epoch": 0.88,
"grad_norm": 0.318359375,
"learning_rate": 7.316017316017317e-05,
"loss": 1.6995,
"step": 686
},
{
"epoch": 0.88,
"grad_norm": 0.4296875,
"learning_rate": 7.294372294372295e-05,
"loss": 1.7617,
"step": 687
},
{
"epoch": 0.88,
"grad_norm": 0.431640625,
"learning_rate": 7.272727272727273e-05,
"loss": 1.6959,
"step": 688
},
{
"epoch": 0.88,
"grad_norm": 0.322265625,
"learning_rate": 7.251082251082252e-05,
"loss": 1.7879,
"step": 689
},
{
"epoch": 0.88,
"grad_norm": 0.35546875,
"learning_rate": 7.229437229437229e-05,
"loss": 1.6613,
"step": 690
},
{
"epoch": 0.88,
"grad_norm": 0.3515625,
"learning_rate": 7.207792207792208e-05,
"loss": 1.6485,
"step": 691
},
{
"epoch": 0.89,
"grad_norm": 0.400390625,
"learning_rate": 7.186147186147186e-05,
"loss": 1.719,
"step": 692
},
{
"epoch": 0.89,
"grad_norm": 0.32421875,
"learning_rate": 7.164502164502165e-05,
"loss": 1.7316,
"step": 693
},
{
"epoch": 0.89,
"grad_norm": 0.33984375,
"learning_rate": 7.142857142857143e-05,
"loss": 1.7509,
"step": 694
},
{
"epoch": 0.89,
"grad_norm": 0.375,
"learning_rate": 7.121212121212121e-05,
"loss": 1.785,
"step": 695
},
{
"epoch": 0.89,
"grad_norm": 0.328125,
"learning_rate": 7.099567099567101e-05,
"loss": 1.7643,
"step": 696
},
{
"epoch": 0.89,
"grad_norm": 0.341796875,
"learning_rate": 7.077922077922077e-05,
"loss": 1.7058,
"step": 697
},
{
"epoch": 0.89,
"grad_norm": 0.34375,
"learning_rate": 7.056277056277057e-05,
"loss": 1.807,
"step": 698
},
{
"epoch": 0.89,
"grad_norm": 0.349609375,
"learning_rate": 7.034632034632035e-05,
"loss": 1.6489,
"step": 699
},
{
"epoch": 0.9,
"grad_norm": 0.359375,
"learning_rate": 7.012987012987014e-05,
"loss": 1.8146,
"step": 700
},
{
"epoch": 0.9,
"eval_loss": 1.7302906513214111,
"eval_runtime": 125.8875,
"eval_samples_per_second": 39.718,
"eval_steps_per_second": 1.247,
"step": 700
},
{
"epoch": 0.9,
"grad_norm": 0.298828125,
"learning_rate": 6.991341991341992e-05,
"loss": 1.6505,
"step": 701
},
{
"epoch": 0.9,
"grad_norm": 0.39453125,
"learning_rate": 6.96969696969697e-05,
"loss": 1.7259,
"step": 702
},
{
"epoch": 0.9,
"grad_norm": 0.314453125,
"learning_rate": 6.948051948051948e-05,
"loss": 1.81,
"step": 703
},
{
"epoch": 0.9,
"grad_norm": 0.3515625,
"learning_rate": 6.926406926406926e-05,
"loss": 1.7801,
"step": 704
},
{
"epoch": 0.9,
"grad_norm": 0.3359375,
"learning_rate": 6.904761904761905e-05,
"loss": 1.7213,
"step": 705
},
{
"epoch": 0.9,
"grad_norm": 0.3125,
"learning_rate": 6.883116883116883e-05,
"loss": 1.8054,
"step": 706
},
{
"epoch": 0.9,
"grad_norm": 0.31640625,
"learning_rate": 6.861471861471862e-05,
"loss": 1.7339,
"step": 707
},
{
"epoch": 0.91,
"grad_norm": 0.328125,
"learning_rate": 6.83982683982684e-05,
"loss": 1.79,
"step": 708
},
{
"epoch": 0.91,
"grad_norm": 0.36328125,
"learning_rate": 6.818181818181818e-05,
"loss": 1.6615,
"step": 709
},
{
"epoch": 0.91,
"grad_norm": 0.306640625,
"learning_rate": 6.796536796536796e-05,
"loss": 1.8298,
"step": 710
},
{
"epoch": 0.91,
"grad_norm": 0.298828125,
"learning_rate": 6.774891774891774e-05,
"loss": 1.6835,
"step": 711
},
{
"epoch": 0.91,
"grad_norm": 0.32421875,
"learning_rate": 6.753246753246754e-05,
"loss": 1.7739,
"step": 712
},
{
"epoch": 0.91,
"grad_norm": 0.337890625,
"learning_rate": 6.731601731601732e-05,
"loss": 1.7431,
"step": 713
},
{
"epoch": 0.91,
"grad_norm": 0.337890625,
"learning_rate": 6.709956709956711e-05,
"loss": 1.7816,
"step": 714
},
{
"epoch": 0.91,
"grad_norm": 0.32421875,
"learning_rate": 6.688311688311688e-05,
"loss": 1.7516,
"step": 715
},
{
"epoch": 0.92,
"grad_norm": 0.341796875,
"learning_rate": 6.666666666666667e-05,
"loss": 1.7276,
"step": 716
},
{
"epoch": 0.92,
"grad_norm": 0.330078125,
"learning_rate": 6.645021645021645e-05,
"loss": 1.7521,
"step": 717
},
{
"epoch": 0.92,
"grad_norm": 0.36328125,
"learning_rate": 6.623376623376624e-05,
"loss": 1.7368,
"step": 718
},
{
"epoch": 0.92,
"grad_norm": 0.3828125,
"learning_rate": 6.601731601731602e-05,
"loss": 1.7896,
"step": 719
},
{
"epoch": 0.92,
"grad_norm": 0.365234375,
"learning_rate": 6.58008658008658e-05,
"loss": 1.8057,
"step": 720
},
{
"epoch": 0.92,
"grad_norm": 0.3828125,
"learning_rate": 6.55844155844156e-05,
"loss": 1.7596,
"step": 721
},
{
"epoch": 0.92,
"grad_norm": 0.40625,
"learning_rate": 6.536796536796536e-05,
"loss": 1.7793,
"step": 722
},
{
"epoch": 0.93,
"grad_norm": 0.365234375,
"learning_rate": 6.515151515151516e-05,
"loss": 1.6966,
"step": 723
},
{
"epoch": 0.93,
"grad_norm": 0.32421875,
"learning_rate": 6.493506493506494e-05,
"loss": 1.6619,
"step": 724
},
{
"epoch": 0.93,
"grad_norm": 0.3359375,
"learning_rate": 6.471861471861473e-05,
"loss": 1.7305,
"step": 725
},
{
"epoch": 0.93,
"grad_norm": 0.365234375,
"learning_rate": 6.450216450216451e-05,
"loss": 1.7337,
"step": 726
},
{
"epoch": 0.93,
"grad_norm": 0.37890625,
"learning_rate": 6.428571428571429e-05,
"loss": 1.7255,
"step": 727
},
{
"epoch": 0.93,
"grad_norm": 0.345703125,
"learning_rate": 6.406926406926407e-05,
"loss": 1.75,
"step": 728
},
{
"epoch": 0.93,
"grad_norm": 0.337890625,
"learning_rate": 6.385281385281385e-05,
"loss": 1.7166,
"step": 729
},
{
"epoch": 0.93,
"grad_norm": 0.3203125,
"learning_rate": 6.363636363636364e-05,
"loss": 1.7407,
"step": 730
},
{
"epoch": 0.94,
"grad_norm": 0.349609375,
"learning_rate": 6.341991341991342e-05,
"loss": 1.6759,
"step": 731
},
{
"epoch": 0.94,
"grad_norm": 0.33203125,
"learning_rate": 6.320346320346321e-05,
"loss": 1.7485,
"step": 732
},
{
"epoch": 0.94,
"grad_norm": 0.37890625,
"learning_rate": 6.2987012987013e-05,
"loss": 1.8,
"step": 733
},
{
"epoch": 0.94,
"grad_norm": 0.404296875,
"learning_rate": 6.277056277056277e-05,
"loss": 1.6966,
"step": 734
},
{
"epoch": 0.94,
"grad_norm": 0.37890625,
"learning_rate": 6.255411255411255e-05,
"loss": 1.7524,
"step": 735
},
{
"epoch": 0.94,
"grad_norm": 0.3515625,
"learning_rate": 6.233766233766233e-05,
"loss": 1.7087,
"step": 736
},
{
"epoch": 0.94,
"grad_norm": 0.37109375,
"learning_rate": 6.212121212121213e-05,
"loss": 1.7963,
"step": 737
},
{
"epoch": 0.94,
"grad_norm": 0.361328125,
"learning_rate": 6.19047619047619e-05,
"loss": 1.7043,
"step": 738
},
{
"epoch": 0.95,
"grad_norm": 0.3046875,
"learning_rate": 6.16883116883117e-05,
"loss": 1.6797,
"step": 739
},
{
"epoch": 0.95,
"grad_norm": 0.396484375,
"learning_rate": 6.147186147186147e-05,
"loss": 1.6791,
"step": 740
},
{
"epoch": 0.95,
"grad_norm": 0.330078125,
"learning_rate": 6.125541125541126e-05,
"loss": 1.7069,
"step": 741
},
{
"epoch": 0.95,
"grad_norm": 0.33984375,
"learning_rate": 6.103896103896104e-05,
"loss": 1.6997,
"step": 742
},
{
"epoch": 0.95,
"grad_norm": 0.376953125,
"learning_rate": 6.0822510822510825e-05,
"loss": 1.7395,
"step": 743
},
{
"epoch": 0.95,
"grad_norm": 0.388671875,
"learning_rate": 6.060606060606061e-05,
"loss": 1.7289,
"step": 744
},
{
"epoch": 0.95,
"grad_norm": 0.375,
"learning_rate": 6.03896103896104e-05,
"loss": 1.7963,
"step": 745
},
{
"epoch": 0.95,
"grad_norm": 0.318359375,
"learning_rate": 6.0173160173160184e-05,
"loss": 1.8322,
"step": 746
},
{
"epoch": 0.96,
"grad_norm": 0.3984375,
"learning_rate": 5.995670995670996e-05,
"loss": 1.6923,
"step": 747
},
{
"epoch": 0.96,
"grad_norm": 0.306640625,
"learning_rate": 5.9740259740259744e-05,
"loss": 1.7534,
"step": 748
},
{
"epoch": 0.96,
"grad_norm": 0.326171875,
"learning_rate": 5.9523809523809524e-05,
"loss": 1.7843,
"step": 749
},
{
"epoch": 0.96,
"grad_norm": 0.330078125,
"learning_rate": 5.930735930735931e-05,
"loss": 1.7837,
"step": 750
},
{
"epoch": 0.96,
"eval_loss": 1.728518009185791,
"eval_runtime": 125.8224,
"eval_samples_per_second": 39.739,
"eval_steps_per_second": 1.248,
"step": 750
},
{
"epoch": 0.96,
"grad_norm": 0.34375,
"learning_rate": 5.90909090909091e-05,
"loss": 1.8208,
"step": 751
},
{
"epoch": 0.96,
"grad_norm": 0.39453125,
"learning_rate": 5.887445887445888e-05,
"loss": 1.7173,
"step": 752
},
{
"epoch": 0.96,
"grad_norm": 0.37109375,
"learning_rate": 5.8658008658008656e-05,
"loss": 1.6923,
"step": 753
},
{
"epoch": 0.96,
"grad_norm": 0.41015625,
"learning_rate": 5.844155844155844e-05,
"loss": 1.7685,
"step": 754
},
{
"epoch": 0.97,
"grad_norm": 0.3125,
"learning_rate": 5.822510822510823e-05,
"loss": 1.677,
"step": 755
},
{
"epoch": 0.97,
"grad_norm": 0.33203125,
"learning_rate": 5.800865800865801e-05,
"loss": 1.6898,
"step": 756
},
{
"epoch": 0.97,
"grad_norm": 0.3671875,
"learning_rate": 5.7792207792207796e-05,
"loss": 1.7492,
"step": 757
},
{
"epoch": 0.97,
"grad_norm": 0.478515625,
"learning_rate": 5.757575757575758e-05,
"loss": 1.7804,
"step": 758
},
{
"epoch": 0.97,
"grad_norm": 0.388671875,
"learning_rate": 5.7359307359307355e-05,
"loss": 1.7285,
"step": 759
},
{
"epoch": 0.97,
"grad_norm": 0.34765625,
"learning_rate": 5.714285714285714e-05,
"loss": 1.7054,
"step": 760
},
{
"epoch": 0.97,
"grad_norm": 0.361328125,
"learning_rate": 5.692640692640693e-05,
"loss": 1.7949,
"step": 761
},
{
"epoch": 0.98,
"grad_norm": 0.3828125,
"learning_rate": 5.6709956709956715e-05,
"loss": 1.6984,
"step": 762
},
{
"epoch": 0.98,
"grad_norm": 0.3359375,
"learning_rate": 5.64935064935065e-05,
"loss": 1.5885,
"step": 763
},
{
"epoch": 0.98,
"grad_norm": 0.373046875,
"learning_rate": 5.627705627705628e-05,
"loss": 1.8189,
"step": 764
},
{
"epoch": 0.98,
"grad_norm": 0.3359375,
"learning_rate": 5.606060606060606e-05,
"loss": 1.7489,
"step": 765
},
{
"epoch": 0.98,
"grad_norm": 0.318359375,
"learning_rate": 5.584415584415584e-05,
"loss": 1.692,
"step": 766
},
{
"epoch": 0.98,
"grad_norm": 0.337890625,
"learning_rate": 5.562770562770563e-05,
"loss": 1.7128,
"step": 767
},
{
"epoch": 0.98,
"grad_norm": 0.369140625,
"learning_rate": 5.5411255411255414e-05,
"loss": 1.7056,
"step": 768
},
{
"epoch": 0.98,
"grad_norm": 0.345703125,
"learning_rate": 5.51948051948052e-05,
"loss": 1.8224,
"step": 769
},
{
"epoch": 0.99,
"grad_norm": 0.310546875,
"learning_rate": 5.497835497835499e-05,
"loss": 1.7297,
"step": 770
},
{
"epoch": 0.99,
"grad_norm": 0.34375,
"learning_rate": 5.4761904761904766e-05,
"loss": 1.7245,
"step": 771
},
{
"epoch": 0.99,
"grad_norm": 0.330078125,
"learning_rate": 5.4545454545454546e-05,
"loss": 1.7286,
"step": 772
},
{
"epoch": 0.99,
"grad_norm": 0.357421875,
"learning_rate": 5.4329004329004326e-05,
"loss": 1.616,
"step": 773
},
{
"epoch": 0.99,
"grad_norm": 0.361328125,
"learning_rate": 5.411255411255411e-05,
"loss": 1.7709,
"step": 774
},
{
"epoch": 0.99,
"grad_norm": 0.423828125,
"learning_rate": 5.38961038961039e-05,
"loss": 1.7746,
"step": 775
},
{
"epoch": 0.99,
"grad_norm": 0.34765625,
"learning_rate": 5.3679653679653686e-05,
"loss": 1.7077,
"step": 776
},
{
"epoch": 0.99,
"grad_norm": 0.3515625,
"learning_rate": 5.346320346320347e-05,
"loss": 1.6281,
"step": 777
},
{
"epoch": 1.0,
"grad_norm": 0.361328125,
"learning_rate": 5.3246753246753245e-05,
"loss": 1.7438,
"step": 778
},
{
"epoch": 1.0,
"grad_norm": 0.353515625,
"learning_rate": 5.303030303030303e-05,
"loss": 1.6973,
"step": 779
},
{
"epoch": 1.0,
"grad_norm": 0.380859375,
"learning_rate": 5.281385281385282e-05,
"loss": 1.7698,
"step": 780
},
{
"epoch": 1.0,
"grad_norm": 0.40234375,
"learning_rate": 5.25974025974026e-05,
"loss": 1.7707,
"step": 781
},
{
"epoch": 1.0,
"grad_norm": 0.375,
"learning_rate": 5.2380952380952384e-05,
"loss": 1.7133,
"step": 782
},
{
"epoch": 1.0,
"grad_norm": 0.34765625,
"learning_rate": 5.216450216450217e-05,
"loss": 1.7593,
"step": 783
},
{
"epoch": 1.0,
"grad_norm": 0.349609375,
"learning_rate": 5.1948051948051944e-05,
"loss": 1.7286,
"step": 784
},
{
"epoch": 1.0,
"grad_norm": 0.33984375,
"learning_rate": 5.173160173160173e-05,
"loss": 1.724,
"step": 785
},
{
"epoch": 1.01,
"grad_norm": 0.3359375,
"learning_rate": 5.151515151515152e-05,
"loss": 1.6978,
"step": 786
},
{
"epoch": 1.01,
"grad_norm": 0.32421875,
"learning_rate": 5.1298701298701304e-05,
"loss": 1.8041,
"step": 787
},
{
"epoch": 1.01,
"grad_norm": 0.287109375,
"learning_rate": 5.108225108225109e-05,
"loss": 1.7141,
"step": 788
},
{
"epoch": 1.01,
"grad_norm": 0.326171875,
"learning_rate": 5.086580086580087e-05,
"loss": 1.6585,
"step": 789
},
{
"epoch": 1.01,
"grad_norm": 0.33203125,
"learning_rate": 5.064935064935065e-05,
"loss": 1.733,
"step": 790
},
{
"epoch": 1.01,
"grad_norm": 0.388671875,
"learning_rate": 5.043290043290043e-05,
"loss": 1.7602,
"step": 791
},
{
"epoch": 1.01,
"grad_norm": 0.310546875,
"learning_rate": 5.0216450216450216e-05,
"loss": 1.804,
"step": 792
},
{
"epoch": 1.01,
"grad_norm": 0.302734375,
"learning_rate": 5e-05,
"loss": 1.6816,
"step": 793
},
{
"epoch": 1.02,
"grad_norm": 0.34375,
"learning_rate": 4.978354978354979e-05,
"loss": 1.7515,
"step": 794
},
{
"epoch": 1.02,
"grad_norm": 0.33203125,
"learning_rate": 4.956709956709957e-05,
"loss": 1.6996,
"step": 795
},
{
"epoch": 1.02,
"grad_norm": 0.333984375,
"learning_rate": 4.9350649350649355e-05,
"loss": 1.7045,
"step": 796
},
{
"epoch": 1.02,
"grad_norm": 0.357421875,
"learning_rate": 4.9134199134199135e-05,
"loss": 1.7026,
"step": 797
},
{
"epoch": 1.02,
"grad_norm": 0.30078125,
"learning_rate": 4.8917748917748915e-05,
"loss": 1.6444,
"step": 798
},
{
"epoch": 1.02,
"grad_norm": 0.345703125,
"learning_rate": 4.87012987012987e-05,
"loss": 1.7705,
"step": 799
},
{
"epoch": 1.02,
"grad_norm": 0.35546875,
"learning_rate": 4.848484848484849e-05,
"loss": 1.7178,
"step": 800
},
{
"epoch": 1.02,
"eval_loss": 1.7301437854766846,
"eval_runtime": 124.4902,
"eval_samples_per_second": 40.164,
"eval_steps_per_second": 1.261,
"step": 800
},
{
"epoch": 1.02,
"grad_norm": 0.33203125,
"learning_rate": 4.826839826839827e-05,
"loss": 1.7434,
"step": 801
},
{
"epoch": 1.03,
"grad_norm": 0.365234375,
"learning_rate": 4.8051948051948054e-05,
"loss": 1.7148,
"step": 802
},
{
"epoch": 1.03,
"grad_norm": 0.330078125,
"learning_rate": 4.783549783549784e-05,
"loss": 1.7685,
"step": 803
},
{
"epoch": 1.03,
"grad_norm": 0.3515625,
"learning_rate": 4.761904761904762e-05,
"loss": 1.8048,
"step": 804
},
{
"epoch": 1.03,
"grad_norm": 0.35546875,
"learning_rate": 4.740259740259741e-05,
"loss": 1.7467,
"step": 805
},
{
"epoch": 1.03,
"grad_norm": 0.33203125,
"learning_rate": 4.718614718614719e-05,
"loss": 1.6937,
"step": 806
},
{
"epoch": 1.03,
"grad_norm": 0.306640625,
"learning_rate": 4.696969696969697e-05,
"loss": 1.6432,
"step": 807
},
{
"epoch": 1.03,
"grad_norm": 0.3515625,
"learning_rate": 4.675324675324675e-05,
"loss": 1.6467,
"step": 808
},
{
"epoch": 1.04,
"grad_norm": 0.373046875,
"learning_rate": 4.653679653679654e-05,
"loss": 1.7572,
"step": 809
},
{
"epoch": 1.04,
"grad_norm": 0.365234375,
"learning_rate": 4.6320346320346326e-05,
"loss": 1.7623,
"step": 810
},
{
"epoch": 1.04,
"grad_norm": 0.333984375,
"learning_rate": 4.6103896103896106e-05,
"loss": 1.6898,
"step": 811
},
{
"epoch": 1.04,
"grad_norm": 0.412109375,
"learning_rate": 4.588744588744589e-05,
"loss": 1.6788,
"step": 812
},
{
"epoch": 1.04,
"grad_norm": 0.373046875,
"learning_rate": 4.567099567099568e-05,
"loss": 1.6631,
"step": 813
},
{
"epoch": 1.04,
"grad_norm": 0.33203125,
"learning_rate": 4.545454545454546e-05,
"loss": 1.6311,
"step": 814
},
{
"epoch": 1.04,
"grad_norm": 0.408203125,
"learning_rate": 4.523809523809524e-05,
"loss": 1.6636,
"step": 815
},
{
"epoch": 1.04,
"grad_norm": 0.357421875,
"learning_rate": 4.5021645021645025e-05,
"loss": 1.8099,
"step": 816
},
{
"epoch": 1.05,
"grad_norm": 0.359375,
"learning_rate": 4.4805194805194805e-05,
"loss": 1.6849,
"step": 817
},
{
"epoch": 1.05,
"grad_norm": 0.36328125,
"learning_rate": 4.458874458874459e-05,
"loss": 1.6601,
"step": 818
},
{
"epoch": 1.05,
"grad_norm": 0.365234375,
"learning_rate": 4.437229437229438e-05,
"loss": 1.7999,
"step": 819
},
{
"epoch": 1.05,
"grad_norm": 0.396484375,
"learning_rate": 4.415584415584416e-05,
"loss": 1.6323,
"step": 820
},
{
"epoch": 1.05,
"grad_norm": 0.3203125,
"learning_rate": 4.3939393939393944e-05,
"loss": 1.7141,
"step": 821
},
{
"epoch": 1.05,
"grad_norm": 0.3359375,
"learning_rate": 4.3722943722943724e-05,
"loss": 1.7166,
"step": 822
},
{
"epoch": 1.05,
"grad_norm": 0.421875,
"learning_rate": 4.3506493506493503e-05,
"loss": 1.6969,
"step": 823
},
{
"epoch": 1.05,
"grad_norm": 0.333984375,
"learning_rate": 4.329004329004329e-05,
"loss": 1.674,
"step": 824
},
{
"epoch": 1.06,
"grad_norm": 0.32421875,
"learning_rate": 4.3073593073593077e-05,
"loss": 1.6893,
"step": 825
},
{
"epoch": 1.06,
"grad_norm": 0.36328125,
"learning_rate": 4.2857142857142856e-05,
"loss": 1.6985,
"step": 826
},
{
"epoch": 1.06,
"grad_norm": 0.328125,
"learning_rate": 4.264069264069264e-05,
"loss": 1.7245,
"step": 827
},
{
"epoch": 1.06,
"grad_norm": 0.35546875,
"learning_rate": 4.242424242424243e-05,
"loss": 1.7277,
"step": 828
},
{
"epoch": 1.06,
"grad_norm": 0.3671875,
"learning_rate": 4.220779220779221e-05,
"loss": 1.6765,
"step": 829
},
{
"epoch": 1.06,
"grad_norm": 0.36328125,
"learning_rate": 4.1991341991341996e-05,
"loss": 1.7863,
"step": 830
},
{
"epoch": 1.06,
"grad_norm": 0.33984375,
"learning_rate": 4.1774891774891775e-05,
"loss": 1.6689,
"step": 831
},
{
"epoch": 1.06,
"grad_norm": 0.365234375,
"learning_rate": 4.155844155844156e-05,
"loss": 1.7957,
"step": 832
},
{
"epoch": 1.07,
"grad_norm": 0.298828125,
"learning_rate": 4.134199134199134e-05,
"loss": 1.6454,
"step": 833
},
{
"epoch": 1.07,
"grad_norm": 0.341796875,
"learning_rate": 4.112554112554113e-05,
"loss": 1.6748,
"step": 834
},
{
"epoch": 1.07,
"grad_norm": 0.380859375,
"learning_rate": 4.0909090909090915e-05,
"loss": 1.8057,
"step": 835
},
{
"epoch": 1.07,
"grad_norm": 0.38671875,
"learning_rate": 4.0692640692640695e-05,
"loss": 1.7343,
"step": 836
},
{
"epoch": 1.07,
"grad_norm": 0.353515625,
"learning_rate": 4.047619047619048e-05,
"loss": 1.6868,
"step": 837
},
{
"epoch": 1.07,
"grad_norm": 0.365234375,
"learning_rate": 4.025974025974026e-05,
"loss": 1.6663,
"step": 838
},
{
"epoch": 1.07,
"grad_norm": 0.3359375,
"learning_rate": 4.004329004329004e-05,
"loss": 1.6779,
"step": 839
},
{
"epoch": 1.07,
"grad_norm": 0.353515625,
"learning_rate": 3.982683982683983e-05,
"loss": 1.7324,
"step": 840
},
{
"epoch": 1.08,
"grad_norm": 0.458984375,
"learning_rate": 3.9610389610389614e-05,
"loss": 1.7377,
"step": 841
},
{
"epoch": 1.08,
"grad_norm": 0.3515625,
"learning_rate": 3.939393939393939e-05,
"loss": 1.7468,
"step": 842
},
{
"epoch": 1.08,
"grad_norm": 0.3359375,
"learning_rate": 3.917748917748918e-05,
"loss": 1.703,
"step": 843
},
{
"epoch": 1.08,
"grad_norm": 0.38671875,
"learning_rate": 3.8961038961038966e-05,
"loss": 1.7124,
"step": 844
},
{
"epoch": 1.08,
"grad_norm": 0.341796875,
"learning_rate": 3.8744588744588746e-05,
"loss": 1.6444,
"step": 845
},
{
"epoch": 1.08,
"grad_norm": 0.341796875,
"learning_rate": 3.852813852813853e-05,
"loss": 1.7465,
"step": 846
},
{
"epoch": 1.08,
"grad_norm": 0.41015625,
"learning_rate": 3.831168831168831e-05,
"loss": 1.7153,
"step": 847
},
{
"epoch": 1.09,
"grad_norm": 0.359375,
"learning_rate": 3.809523809523809e-05,
"loss": 1.756,
"step": 848
},
{
"epoch": 1.09,
"grad_norm": 0.37890625,
"learning_rate": 3.787878787878788e-05,
"loss": 1.6992,
"step": 849
},
{
"epoch": 1.09,
"grad_norm": 0.33203125,
"learning_rate": 3.7662337662337665e-05,
"loss": 1.7487,
"step": 850
},
{
"epoch": 1.09,
"eval_loss": 1.725529670715332,
"eval_runtime": 124.4606,
"eval_samples_per_second": 40.173,
"eval_steps_per_second": 1.261,
"step": 850
},
{
"epoch": 1.09,
"grad_norm": 0.3828125,
"learning_rate": 3.7445887445887445e-05,
"loss": 1.7665,
"step": 851
},
{
"epoch": 1.09,
"grad_norm": 0.349609375,
"learning_rate": 3.722943722943723e-05,
"loss": 1.7517,
"step": 852
},
{
"epoch": 1.09,
"grad_norm": 0.353515625,
"learning_rate": 3.701298701298702e-05,
"loss": 1.7896,
"step": 853
},
{
"epoch": 1.09,
"grad_norm": 0.37109375,
"learning_rate": 3.67965367965368e-05,
"loss": 1.7554,
"step": 854
},
{
"epoch": 1.09,
"grad_norm": 0.3515625,
"learning_rate": 3.6580086580086584e-05,
"loss": 1.7757,
"step": 855
},
{
"epoch": 1.1,
"grad_norm": 0.390625,
"learning_rate": 3.6363636363636364e-05,
"loss": 1.7977,
"step": 856
},
{
"epoch": 1.1,
"grad_norm": 0.376953125,
"learning_rate": 3.6147186147186144e-05,
"loss": 1.7066,
"step": 857
},
{
"epoch": 1.1,
"grad_norm": 0.3671875,
"learning_rate": 3.593073593073593e-05,
"loss": 1.7159,
"step": 858
},
{
"epoch": 1.1,
"grad_norm": 0.3515625,
"learning_rate": 3.571428571428572e-05,
"loss": 1.5972,
"step": 859
},
{
"epoch": 1.1,
"grad_norm": 0.365234375,
"learning_rate": 3.5497835497835503e-05,
"loss": 1.7102,
"step": 860
},
{
"epoch": 1.1,
"grad_norm": 0.369140625,
"learning_rate": 3.528138528138528e-05,
"loss": 1.661,
"step": 861
},
{
"epoch": 1.1,
"grad_norm": 0.47265625,
"learning_rate": 3.506493506493507e-05,
"loss": 1.691,
"step": 862
},
{
"epoch": 1.1,
"grad_norm": 0.3125,
"learning_rate": 3.484848484848485e-05,
"loss": 1.7247,
"step": 863
},
{
"epoch": 1.11,
"grad_norm": 0.390625,
"learning_rate": 3.463203463203463e-05,
"loss": 1.6295,
"step": 864
},
{
"epoch": 1.11,
"grad_norm": 0.361328125,
"learning_rate": 3.4415584415584416e-05,
"loss": 1.7508,
"step": 865
},
{
"epoch": 1.11,
"grad_norm": 0.330078125,
"learning_rate": 3.41991341991342e-05,
"loss": 1.6085,
"step": 866
},
{
"epoch": 1.11,
"grad_norm": 0.35546875,
"learning_rate": 3.398268398268398e-05,
"loss": 1.7507,
"step": 867
},
{
"epoch": 1.11,
"grad_norm": 0.296875,
"learning_rate": 3.376623376623377e-05,
"loss": 1.7143,
"step": 868
},
{
"epoch": 1.11,
"grad_norm": 0.34765625,
"learning_rate": 3.3549783549783555e-05,
"loss": 1.7195,
"step": 869
},
{
"epoch": 1.11,
"grad_norm": 0.3984375,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.7606,
"step": 870
},
{
"epoch": 1.11,
"grad_norm": 0.3515625,
"learning_rate": 3.311688311688312e-05,
"loss": 1.7038,
"step": 871
},
{
"epoch": 1.12,
"grad_norm": 0.33984375,
"learning_rate": 3.29004329004329e-05,
"loss": 1.7545,
"step": 872
},
{
"epoch": 1.12,
"grad_norm": 0.306640625,
"learning_rate": 3.268398268398268e-05,
"loss": 1.6866,
"step": 873
},
{
"epoch": 1.12,
"grad_norm": 0.404296875,
"learning_rate": 3.246753246753247e-05,
"loss": 1.683,
"step": 874
},
{
"epoch": 1.12,
"grad_norm": 0.345703125,
"learning_rate": 3.2251082251082254e-05,
"loss": 1.7329,
"step": 875
},
{
"epoch": 1.12,
"grad_norm": 0.341796875,
"learning_rate": 3.2034632034632034e-05,
"loss": 1.7675,
"step": 876
},
{
"epoch": 1.12,
"grad_norm": 0.333984375,
"learning_rate": 3.181818181818182e-05,
"loss": 1.6585,
"step": 877
},
{
"epoch": 1.12,
"grad_norm": 0.34375,
"learning_rate": 3.160173160173161e-05,
"loss": 1.7628,
"step": 878
},
{
"epoch": 1.12,
"grad_norm": 0.384765625,
"learning_rate": 3.1385281385281387e-05,
"loss": 1.6784,
"step": 879
},
{
"epoch": 1.13,
"grad_norm": 0.345703125,
"learning_rate": 3.1168831168831166e-05,
"loss": 1.7177,
"step": 880
},
{
"epoch": 1.13,
"grad_norm": 0.34375,
"learning_rate": 3.095238095238095e-05,
"loss": 1.6945,
"step": 881
},
{
"epoch": 1.13,
"grad_norm": 0.380859375,
"learning_rate": 3.073593073593073e-05,
"loss": 1.7096,
"step": 882
},
{
"epoch": 1.13,
"grad_norm": 0.361328125,
"learning_rate": 3.051948051948052e-05,
"loss": 1.7545,
"step": 883
},
{
"epoch": 1.13,
"grad_norm": 0.369140625,
"learning_rate": 3.0303030303030306e-05,
"loss": 1.7122,
"step": 884
},
{
"epoch": 1.13,
"grad_norm": 0.36328125,
"learning_rate": 3.0086580086580092e-05,
"loss": 1.6433,
"step": 885
},
{
"epoch": 1.13,
"grad_norm": 0.37109375,
"learning_rate": 2.9870129870129872e-05,
"loss": 1.6908,
"step": 886
},
{
"epoch": 1.13,
"grad_norm": 0.326171875,
"learning_rate": 2.9653679653679655e-05,
"loss": 1.8096,
"step": 887
},
{
"epoch": 1.14,
"grad_norm": 0.375,
"learning_rate": 2.943722943722944e-05,
"loss": 1.5972,
"step": 888
},
{
"epoch": 1.14,
"grad_norm": 0.345703125,
"learning_rate": 2.922077922077922e-05,
"loss": 1.7858,
"step": 889
},
{
"epoch": 1.14,
"grad_norm": 0.326171875,
"learning_rate": 2.9004329004329005e-05,
"loss": 1.7353,
"step": 890
},
{
"epoch": 1.14,
"grad_norm": 0.35546875,
"learning_rate": 2.878787878787879e-05,
"loss": 1.7572,
"step": 891
},
{
"epoch": 1.14,
"grad_norm": 0.361328125,
"learning_rate": 2.857142857142857e-05,
"loss": 1.7268,
"step": 892
},
{
"epoch": 1.14,
"grad_norm": 0.37109375,
"learning_rate": 2.8354978354978357e-05,
"loss": 1.7919,
"step": 893
},
{
"epoch": 1.14,
"grad_norm": 0.37109375,
"learning_rate": 2.813852813852814e-05,
"loss": 1.735,
"step": 894
},
{
"epoch": 1.15,
"grad_norm": 0.32421875,
"learning_rate": 2.792207792207792e-05,
"loss": 1.7174,
"step": 895
},
{
"epoch": 1.15,
"grad_norm": 0.37890625,
"learning_rate": 2.7705627705627707e-05,
"loss": 1.6896,
"step": 896
},
{
"epoch": 1.15,
"grad_norm": 0.318359375,
"learning_rate": 2.7489177489177493e-05,
"loss": 1.7908,
"step": 897
},
{
"epoch": 1.15,
"grad_norm": 0.33984375,
"learning_rate": 2.7272727272727273e-05,
"loss": 1.7684,
"step": 898
},
{
"epoch": 1.15,
"grad_norm": 0.33203125,
"learning_rate": 2.7056277056277056e-05,
"loss": 1.7138,
"step": 899
},
{
"epoch": 1.15,
"grad_norm": 0.34375,
"learning_rate": 2.6839826839826843e-05,
"loss": 1.7012,
"step": 900
},
{
"epoch": 1.15,
"eval_loss": 1.725927710533142,
"eval_runtime": 125.737,
"eval_samples_per_second": 39.766,
"eval_steps_per_second": 1.249,
"step": 900
},
{
"epoch": 1.15,
"grad_norm": 0.35546875,
"learning_rate": 2.6623376623376623e-05,
"loss": 1.7415,
"step": 901
},
{
"epoch": 1.15,
"grad_norm": 0.365234375,
"learning_rate": 2.640692640692641e-05,
"loss": 1.7195,
"step": 902
},
{
"epoch": 1.16,
"grad_norm": 0.337890625,
"learning_rate": 2.6190476190476192e-05,
"loss": 1.7539,
"step": 903
},
{
"epoch": 1.16,
"grad_norm": 0.369140625,
"learning_rate": 2.5974025974025972e-05,
"loss": 1.6218,
"step": 904
},
{
"epoch": 1.16,
"grad_norm": 0.3125,
"learning_rate": 2.575757575757576e-05,
"loss": 1.6949,
"step": 905
},
{
"epoch": 1.16,
"grad_norm": 0.361328125,
"learning_rate": 2.5541125541125545e-05,
"loss": 1.7539,
"step": 906
},
{
"epoch": 1.16,
"grad_norm": 0.345703125,
"learning_rate": 2.5324675324675325e-05,
"loss": 1.7398,
"step": 907
},
{
"epoch": 1.16,
"grad_norm": 0.3515625,
"learning_rate": 2.5108225108225108e-05,
"loss": 1.7924,
"step": 908
},
{
"epoch": 1.16,
"grad_norm": 0.34765625,
"learning_rate": 2.4891774891774894e-05,
"loss": 1.7182,
"step": 909
},
{
"epoch": 1.16,
"grad_norm": 0.412109375,
"learning_rate": 2.4675324675324678e-05,
"loss": 1.7197,
"step": 910
},
{
"epoch": 1.17,
"grad_norm": 0.310546875,
"learning_rate": 2.4458874458874457e-05,
"loss": 1.6976,
"step": 911
},
{
"epoch": 1.17,
"grad_norm": 0.369140625,
"learning_rate": 2.4242424242424244e-05,
"loss": 1.7478,
"step": 912
},
{
"epoch": 1.17,
"grad_norm": 0.333984375,
"learning_rate": 2.4025974025974027e-05,
"loss": 1.6187,
"step": 913
},
{
"epoch": 1.17,
"grad_norm": 0.345703125,
"learning_rate": 2.380952380952381e-05,
"loss": 1.7191,
"step": 914
},
{
"epoch": 1.17,
"grad_norm": 0.439453125,
"learning_rate": 2.3593073593073593e-05,
"loss": 1.6616,
"step": 915
},
{
"epoch": 1.17,
"grad_norm": 0.328125,
"learning_rate": 2.3376623376623376e-05,
"loss": 1.6345,
"step": 916
},
{
"epoch": 1.17,
"grad_norm": 0.447265625,
"learning_rate": 2.3160173160173163e-05,
"loss": 1.7367,
"step": 917
},
{
"epoch": 1.17,
"grad_norm": 0.40625,
"learning_rate": 2.2943722943722946e-05,
"loss": 1.7257,
"step": 918
},
{
"epoch": 1.18,
"grad_norm": 0.35546875,
"learning_rate": 2.272727272727273e-05,
"loss": 1.6999,
"step": 919
},
{
"epoch": 1.18,
"grad_norm": 0.37109375,
"learning_rate": 2.2510822510822512e-05,
"loss": 1.6337,
"step": 920
},
{
"epoch": 1.18,
"grad_norm": 0.349609375,
"learning_rate": 2.2294372294372296e-05,
"loss": 1.7632,
"step": 921
},
{
"epoch": 1.18,
"grad_norm": 0.341796875,
"learning_rate": 2.207792207792208e-05,
"loss": 1.7686,
"step": 922
},
{
"epoch": 1.18,
"grad_norm": 0.3671875,
"learning_rate": 2.1861471861471862e-05,
"loss": 1.6897,
"step": 923
},
{
"epoch": 1.18,
"grad_norm": 0.365234375,
"learning_rate": 2.1645021645021645e-05,
"loss": 1.8555,
"step": 924
},
{
"epoch": 1.18,
"grad_norm": 0.408203125,
"learning_rate": 2.1428571428571428e-05,
"loss": 1.7255,
"step": 925
},
{
"epoch": 1.18,
"grad_norm": 0.3359375,
"learning_rate": 2.1212121212121215e-05,
"loss": 1.6774,
"step": 926
},
{
"epoch": 1.19,
"grad_norm": 0.39453125,
"learning_rate": 2.0995670995670998e-05,
"loss": 1.7524,
"step": 927
},
{
"epoch": 1.19,
"grad_norm": 0.328125,
"learning_rate": 2.077922077922078e-05,
"loss": 1.6569,
"step": 928
},
{
"epoch": 1.19,
"grad_norm": 0.5078125,
"learning_rate": 2.0562770562770564e-05,
"loss": 1.7028,
"step": 929
},
{
"epoch": 1.19,
"grad_norm": 0.349609375,
"learning_rate": 2.0346320346320347e-05,
"loss": 1.7377,
"step": 930
},
{
"epoch": 1.19,
"grad_norm": 0.341796875,
"learning_rate": 2.012987012987013e-05,
"loss": 1.6855,
"step": 931
},
{
"epoch": 1.19,
"grad_norm": 0.326171875,
"learning_rate": 1.9913419913419914e-05,
"loss": 1.6917,
"step": 932
},
{
"epoch": 1.19,
"grad_norm": 0.341796875,
"learning_rate": 1.9696969696969697e-05,
"loss": 1.714,
"step": 933
},
{
"epoch": 1.2,
"grad_norm": 0.333984375,
"learning_rate": 1.9480519480519483e-05,
"loss": 1.7653,
"step": 934
},
{
"epoch": 1.2,
"grad_norm": 0.337890625,
"learning_rate": 1.9264069264069266e-05,
"loss": 1.6973,
"step": 935
},
{
"epoch": 1.2,
"grad_norm": 0.34765625,
"learning_rate": 1.9047619047619046e-05,
"loss": 1.7066,
"step": 936
},
{
"epoch": 1.2,
"grad_norm": 0.34375,
"learning_rate": 1.8831168831168833e-05,
"loss": 1.6812,
"step": 937
},
{
"epoch": 1.2,
"grad_norm": 0.341796875,
"learning_rate": 1.8614718614718616e-05,
"loss": 1.7114,
"step": 938
},
{
"epoch": 1.2,
"grad_norm": 0.3984375,
"learning_rate": 1.83982683982684e-05,
"loss": 1.7109,
"step": 939
},
{
"epoch": 1.2,
"grad_norm": 0.375,
"learning_rate": 1.8181818181818182e-05,
"loss": 1.6037,
"step": 940
},
{
"epoch": 1.2,
"grad_norm": 0.34765625,
"learning_rate": 1.7965367965367965e-05,
"loss": 1.7588,
"step": 941
},
{
"epoch": 1.21,
"grad_norm": 0.412109375,
"learning_rate": 1.7748917748917752e-05,
"loss": 1.7093,
"step": 942
},
{
"epoch": 1.21,
"grad_norm": 0.353515625,
"learning_rate": 1.7532467532467535e-05,
"loss": 1.7642,
"step": 943
},
{
"epoch": 1.21,
"grad_norm": 0.466796875,
"learning_rate": 1.7316017316017315e-05,
"loss": 1.724,
"step": 944
},
{
"epoch": 1.21,
"grad_norm": 0.34375,
"learning_rate": 1.70995670995671e-05,
"loss": 1.6136,
"step": 945
},
{
"epoch": 1.21,
"grad_norm": 0.431640625,
"learning_rate": 1.6883116883116884e-05,
"loss": 1.6256,
"step": 946
},
{
"epoch": 1.21,
"grad_norm": 0.400390625,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.6878,
"step": 947
},
{
"epoch": 1.21,
"grad_norm": 0.388671875,
"learning_rate": 1.645021645021645e-05,
"loss": 1.7281,
"step": 948
},
{
"epoch": 1.21,
"grad_norm": 0.3359375,
"learning_rate": 1.6233766233766234e-05,
"loss": 1.7021,
"step": 949
},
{
"epoch": 1.22,
"grad_norm": 0.375,
"learning_rate": 1.6017316017316017e-05,
"loss": 1.7982,
"step": 950
},
{
"epoch": 1.22,
"eval_loss": 1.7258570194244385,
"eval_runtime": 124.9465,
"eval_samples_per_second": 40.017,
"eval_steps_per_second": 1.257,
"step": 950
},
{
"epoch": 1.22,
"grad_norm": 0.400390625,
"learning_rate": 1.5800865800865803e-05,
"loss": 1.641,
"step": 951
},
{
"epoch": 1.22,
"grad_norm": 0.357421875,
"learning_rate": 1.5584415584415583e-05,
"loss": 1.6773,
"step": 952
},
{
"epoch": 1.22,
"grad_norm": 0.341796875,
"learning_rate": 1.5367965367965366e-05,
"loss": 1.654,
"step": 953
},
{
"epoch": 1.22,
"grad_norm": 0.380859375,
"learning_rate": 1.5151515151515153e-05,
"loss": 1.7277,
"step": 954
},
{
"epoch": 1.22,
"grad_norm": 0.359375,
"learning_rate": 1.4935064935064936e-05,
"loss": 1.6995,
"step": 955
},
{
"epoch": 1.22,
"grad_norm": 0.359375,
"learning_rate": 1.471861471861472e-05,
"loss": 1.7112,
"step": 956
},
{
"epoch": 1.22,
"grad_norm": 0.35546875,
"learning_rate": 1.4502164502164502e-05,
"loss": 1.7486,
"step": 957
},
{
"epoch": 1.23,
"grad_norm": 0.40234375,
"learning_rate": 1.4285714285714285e-05,
"loss": 1.7627,
"step": 958
},
{
"epoch": 1.23,
"grad_norm": 0.34375,
"learning_rate": 1.406926406926407e-05,
"loss": 1.6709,
"step": 959
},
{
"epoch": 1.23,
"grad_norm": 0.345703125,
"learning_rate": 1.3852813852813853e-05,
"loss": 1.7112,
"step": 960
},
{
"epoch": 1.23,
"grad_norm": 0.375,
"learning_rate": 1.3636363636363637e-05,
"loss": 1.7299,
"step": 961
},
{
"epoch": 1.23,
"grad_norm": 0.390625,
"learning_rate": 1.3419913419913421e-05,
"loss": 1.6656,
"step": 962
},
{
"epoch": 1.23,
"grad_norm": 0.37890625,
"learning_rate": 1.3203463203463205e-05,
"loss": 1.6621,
"step": 963
},
{
"epoch": 1.23,
"grad_norm": 0.33203125,
"learning_rate": 1.2987012987012986e-05,
"loss": 1.6751,
"step": 964
},
{
"epoch": 1.23,
"grad_norm": 0.48828125,
"learning_rate": 1.2770562770562773e-05,
"loss": 1.7,
"step": 965
},
{
"epoch": 1.24,
"grad_norm": 0.345703125,
"learning_rate": 1.2554112554112554e-05,
"loss": 1.7547,
"step": 966
},
{
"epoch": 1.24,
"grad_norm": 0.357421875,
"learning_rate": 1.2337662337662339e-05,
"loss": 1.6858,
"step": 967
},
{
"epoch": 1.24,
"grad_norm": 0.33984375,
"learning_rate": 1.2121212121212122e-05,
"loss": 1.5868,
"step": 968
},
{
"epoch": 1.24,
"grad_norm": 0.3359375,
"learning_rate": 1.1904761904761905e-05,
"loss": 1.7628,
"step": 969
},
{
"epoch": 1.24,
"grad_norm": 0.314453125,
"learning_rate": 1.1688311688311688e-05,
"loss": 1.6664,
"step": 970
},
{
"epoch": 1.24,
"grad_norm": 0.33984375,
"learning_rate": 1.1471861471861473e-05,
"loss": 1.7387,
"step": 971
},
{
"epoch": 1.24,
"grad_norm": 0.392578125,
"learning_rate": 1.1255411255411256e-05,
"loss": 1.7765,
"step": 972
},
{
"epoch": 1.25,
"grad_norm": 0.341796875,
"learning_rate": 1.103896103896104e-05,
"loss": 1.7887,
"step": 973
},
{
"epoch": 1.25,
"grad_norm": 0.341796875,
"learning_rate": 1.0822510822510823e-05,
"loss": 1.7143,
"step": 974
},
{
"epoch": 1.25,
"grad_norm": 0.33984375,
"learning_rate": 1.0606060606060607e-05,
"loss": 1.6573,
"step": 975
},
{
"epoch": 1.25,
"grad_norm": 0.33203125,
"learning_rate": 1.038961038961039e-05,
"loss": 1.7191,
"step": 976
},
{
"epoch": 1.25,
"grad_norm": 0.337890625,
"learning_rate": 1.0173160173160174e-05,
"loss": 1.7437,
"step": 977
},
{
"epoch": 1.25,
"grad_norm": 0.36328125,
"learning_rate": 9.956709956709957e-06,
"loss": 1.8012,
"step": 978
},
{
"epoch": 1.25,
"grad_norm": 0.3515625,
"learning_rate": 9.740259740259742e-06,
"loss": 1.6769,
"step": 979
},
{
"epoch": 1.25,
"grad_norm": 0.326171875,
"learning_rate": 9.523809523809523e-06,
"loss": 1.7836,
"step": 980
},
{
"epoch": 1.26,
"grad_norm": 0.375,
"learning_rate": 9.307359307359308e-06,
"loss": 1.6654,
"step": 981
},
{
"epoch": 1.26,
"grad_norm": 0.37109375,
"learning_rate": 9.090909090909091e-06,
"loss": 1.7367,
"step": 982
},
{
"epoch": 1.26,
"grad_norm": 0.353515625,
"learning_rate": 8.874458874458876e-06,
"loss": 1.6735,
"step": 983
},
{
"epoch": 1.26,
"grad_norm": 0.32421875,
"learning_rate": 8.658008658008657e-06,
"loss": 1.5795,
"step": 984
},
{
"epoch": 1.26,
"grad_norm": 0.333984375,
"learning_rate": 8.441558441558442e-06,
"loss": 1.6784,
"step": 985
},
{
"epoch": 1.26,
"grad_norm": 0.33203125,
"learning_rate": 8.225108225108225e-06,
"loss": 1.6743,
"step": 986
},
{
"epoch": 1.26,
"grad_norm": 0.3671875,
"learning_rate": 8.008658008658008e-06,
"loss": 1.6877,
"step": 987
},
{
"epoch": 1.26,
"grad_norm": 0.3125,
"learning_rate": 7.792207792207792e-06,
"loss": 1.7913,
"step": 988
},
{
"epoch": 1.27,
"grad_norm": 0.38671875,
"learning_rate": 7.5757575757575764e-06,
"loss": 1.6147,
"step": 989
},
{
"epoch": 1.27,
"grad_norm": 0.33203125,
"learning_rate": 7.35930735930736e-06,
"loss": 1.7615,
"step": 990
},
{
"epoch": 1.27,
"grad_norm": 0.3515625,
"learning_rate": 7.142857142857143e-06,
"loss": 1.7406,
"step": 991
},
{
"epoch": 1.27,
"grad_norm": 0.427734375,
"learning_rate": 6.926406926406927e-06,
"loss": 1.6287,
"step": 992
},
{
"epoch": 1.27,
"grad_norm": 0.345703125,
"learning_rate": 6.709956709956711e-06,
"loss": 1.7655,
"step": 993
},
{
"epoch": 1.27,
"grad_norm": 0.330078125,
"learning_rate": 6.493506493506493e-06,
"loss": 1.7003,
"step": 994
},
{
"epoch": 1.27,
"grad_norm": 0.345703125,
"learning_rate": 6.277056277056277e-06,
"loss": 1.7531,
"step": 995
},
{
"epoch": 1.27,
"grad_norm": 0.365234375,
"learning_rate": 6.060606060606061e-06,
"loss": 1.7475,
"step": 996
},
{
"epoch": 1.28,
"grad_norm": 0.361328125,
"learning_rate": 5.844155844155844e-06,
"loss": 1.6811,
"step": 997
},
{
"epoch": 1.28,
"grad_norm": 0.3203125,
"learning_rate": 5.627705627705628e-06,
"loss": 1.7256,
"step": 998
},
{
"epoch": 1.28,
"grad_norm": 0.349609375,
"learning_rate": 5.411255411255411e-06,
"loss": 1.7238,
"step": 999
},
{
"epoch": 1.28,
"grad_norm": 0.34375,
"learning_rate": 5.194805194805195e-06,
"loss": 1.6972,
"step": 1000
},
{
"epoch": 1.28,
"eval_loss": 1.7247449159622192,
"eval_runtime": 125.5655,
"eval_samples_per_second": 39.82,
"eval_steps_per_second": 1.25,
"step": 1000
},
{
"epoch": 1.28,
"grad_norm": 0.359375,
"learning_rate": 4.978354978354978e-06,
"loss": 1.6889,
"step": 1001
},
{
"epoch": 1.28,
"grad_norm": 0.330078125,
"learning_rate": 4.7619047619047615e-06,
"loss": 1.7495,
"step": 1002
},
{
"epoch": 1.28,
"grad_norm": 0.37890625,
"learning_rate": 4.5454545454545455e-06,
"loss": 1.6499,
"step": 1003
},
{
"epoch": 1.28,
"grad_norm": 0.353515625,
"learning_rate": 4.329004329004329e-06,
"loss": 1.6646,
"step": 1004
},
{
"epoch": 1.29,
"grad_norm": 0.3671875,
"learning_rate": 4.112554112554113e-06,
"loss": 1.7523,
"step": 1005
},
{
"epoch": 1.29,
"grad_norm": 0.333984375,
"learning_rate": 3.896103896103896e-06,
"loss": 1.7232,
"step": 1006
},
{
"epoch": 1.29,
"grad_norm": 0.400390625,
"learning_rate": 3.67965367965368e-06,
"loss": 1.7209,
"step": 1007
},
{
"epoch": 1.29,
"grad_norm": 0.333984375,
"learning_rate": 3.4632034632034634e-06,
"loss": 1.6627,
"step": 1008
},
{
"epoch": 1.29,
"grad_norm": 0.3203125,
"learning_rate": 3.2467532467532465e-06,
"loss": 1.6678,
"step": 1009
},
{
"epoch": 1.29,
"grad_norm": 0.333984375,
"learning_rate": 3.0303030303030305e-06,
"loss": 1.6757,
"step": 1010
},
{
"epoch": 1.29,
"grad_norm": 0.33203125,
"learning_rate": 2.813852813852814e-06,
"loss": 1.7232,
"step": 1011
},
{
"epoch": 1.29,
"grad_norm": 0.33203125,
"learning_rate": 2.5974025974025976e-06,
"loss": 1.6797,
"step": 1012
},
{
"epoch": 1.3,
"grad_norm": 0.337890625,
"learning_rate": 2.3809523809523808e-06,
"loss": 1.825,
"step": 1013
},
{
"epoch": 1.3,
"grad_norm": 0.337890625,
"learning_rate": 2.1645021645021643e-06,
"loss": 1.6841,
"step": 1014
},
{
"epoch": 1.3,
"grad_norm": 0.328125,
"learning_rate": 1.948051948051948e-06,
"loss": 1.726,
"step": 1015
},
{
"epoch": 1.3,
"grad_norm": 0.392578125,
"learning_rate": 1.7316017316017317e-06,
"loss": 1.7702,
"step": 1016
},
{
"epoch": 1.3,
"grad_norm": 0.3359375,
"learning_rate": 1.5151515151515152e-06,
"loss": 1.7689,
"step": 1017
},
{
"epoch": 1.3,
"grad_norm": 0.37109375,
"learning_rate": 1.2987012987012988e-06,
"loss": 1.7003,
"step": 1018
},
{
"epoch": 1.3,
"grad_norm": 0.40234375,
"learning_rate": 1.0822510822510822e-06,
"loss": 1.6841,
"step": 1019
},
{
"epoch": 1.31,
"grad_norm": 0.380859375,
"learning_rate": 8.658008658008658e-07,
"loss": 1.7318,
"step": 1020
},
{
"epoch": 1.31,
"grad_norm": 0.345703125,
"learning_rate": 6.493506493506494e-07,
"loss": 1.7868,
"step": 1021
},
{
"epoch": 1.31,
"grad_norm": 0.34765625,
"learning_rate": 4.329004329004329e-07,
"loss": 1.7199,
"step": 1022
},
{
"epoch": 1.31,
"grad_norm": 0.359375,
"learning_rate": 2.1645021645021646e-07,
"loss": 1.7633,
"step": 1023
},
{
"epoch": 1.31,
"grad_norm": 0.328125,
"learning_rate": 0.0,
"loss": 1.7878,
"step": 1024
},
{
"epoch": 1.31,
"step": 1024,
"total_flos": 7.46638513614422e+17,
"train_loss": 1.8673716291086748,
"train_runtime": 7714.204,
"train_samples_per_second": 8.495,
"train_steps_per_second": 0.133
},
{
"epoch": 1.31,
"eval_loss": 1.7247449159622192,
"eval_runtime": 125.8509,
"eval_samples_per_second": 39.73,
"eval_steps_per_second": 1.248,
"step": 1024
}
],
"logging_steps": 1,
"max_steps": 1024,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"total_flos": 7.46638513614422e+17,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}