peft_model_2 / trainer_state.json
akjindal53244's picture
Peft model files
1b67f99
raw
history blame contribute delete
No virus
246 kB
{
"best_metric": 0.633979320526123,
"best_model_checkpoint": "./qlora-NIPS-data-200k_RP/checkpoint-1984",
"epoch": 1.9493981822647997,
"eval_steps": 64,
"global_step": 1984,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.0377,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.1046,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 6.000000000000001e-07,
"loss": 1.2066,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 8.000000000000001e-07,
"loss": 1.1604,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.2227,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1.2000000000000002e-06,
"loss": 0.9552,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.0719,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.1246,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.0706,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.8974,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 2.2e-06,
"loss": 0.9522,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.0083,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 2.6e-06,
"loss": 1.0064,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.0825,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 3e-06,
"loss": 0.9912,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.8197,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.9507,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.8242,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.7885,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 4.000000000000001e-06,
"loss": 0.788,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.7664,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 4.4e-06,
"loss": 0.7851,
"step": 22
},
{
"epoch": 0.02,
"learning_rate": 4.600000000000001e-06,
"loss": 0.7254,
"step": 23
},
{
"epoch": 0.02,
"learning_rate": 4.800000000000001e-06,
"loss": 0.8939,
"step": 24
},
{
"epoch": 0.02,
"learning_rate": 5e-06,
"loss": 0.8107,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 5.2e-06,
"loss": 0.722,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 5.400000000000001e-06,
"loss": 0.6442,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 5.600000000000001e-06,
"loss": 0.7847,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 5.8e-06,
"loss": 0.7488,
"step": 29
},
{
"epoch": 0.03,
"learning_rate": 6e-06,
"loss": 0.6961,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 6.200000000000001e-06,
"loss": 0.8512,
"step": 31
},
{
"epoch": 0.03,
"learning_rate": 6.4000000000000006e-06,
"loss": 0.8236,
"step": 32
},
{
"epoch": 0.03,
"learning_rate": 6.600000000000001e-06,
"loss": 0.7719,
"step": 33
},
{
"epoch": 0.03,
"learning_rate": 6.800000000000001e-06,
"loss": 0.9678,
"step": 34
},
{
"epoch": 0.03,
"learning_rate": 7e-06,
"loss": 0.7325,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 7.2000000000000005e-06,
"loss": 0.7484,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 7.4e-06,
"loss": 0.6518,
"step": 37
},
{
"epoch": 0.04,
"learning_rate": 7.600000000000001e-06,
"loss": 0.724,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 7.800000000000002e-06,
"loss": 0.6204,
"step": 39
},
{
"epoch": 0.04,
"learning_rate": 8.000000000000001e-06,
"loss": 0.7711,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 8.2e-06,
"loss": 0.7612,
"step": 41
},
{
"epoch": 0.04,
"learning_rate": 8.400000000000001e-06,
"loss": 0.6336,
"step": 42
},
{
"epoch": 0.04,
"learning_rate": 8.6e-06,
"loss": 0.6547,
"step": 43
},
{
"epoch": 0.04,
"learning_rate": 8.8e-06,
"loss": 0.8205,
"step": 44
},
{
"epoch": 0.04,
"learning_rate": 9e-06,
"loss": 0.726,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 9.200000000000002e-06,
"loss": 0.6829,
"step": 46
},
{
"epoch": 0.05,
"learning_rate": 9.4e-06,
"loss": 0.6351,
"step": 47
},
{
"epoch": 0.05,
"learning_rate": 9.600000000000001e-06,
"loss": 0.7184,
"step": 48
},
{
"epoch": 0.05,
"learning_rate": 9.800000000000001e-06,
"loss": 0.5917,
"step": 49
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 0.7204,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 1.02e-05,
"loss": 0.6352,
"step": 51
},
{
"epoch": 0.05,
"learning_rate": 1.04e-05,
"loss": 0.7705,
"step": 52
},
{
"epoch": 0.05,
"learning_rate": 1.0600000000000002e-05,
"loss": 0.6812,
"step": 53
},
{
"epoch": 0.05,
"learning_rate": 1.0800000000000002e-05,
"loss": 0.5732,
"step": 54
},
{
"epoch": 0.05,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.7184,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 1.1200000000000001e-05,
"loss": 0.6628,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 1.14e-05,
"loss": 0.724,
"step": 57
},
{
"epoch": 0.06,
"learning_rate": 1.16e-05,
"loss": 0.6376,
"step": 58
},
{
"epoch": 0.06,
"learning_rate": 1.18e-05,
"loss": 0.5994,
"step": 59
},
{
"epoch": 0.06,
"learning_rate": 1.2e-05,
"loss": 0.7452,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 1.22e-05,
"loss": 0.7187,
"step": 61
},
{
"epoch": 0.06,
"learning_rate": 1.2400000000000002e-05,
"loss": 0.6891,
"step": 62
},
{
"epoch": 0.06,
"learning_rate": 1.2600000000000001e-05,
"loss": 0.6516,
"step": 63
},
{
"epoch": 0.06,
"learning_rate": 1.2800000000000001e-05,
"loss": 0.737,
"step": 64
},
{
"epoch": 0.06,
"eval_loss": 0.7483976483345032,
"eval_runtime": 92.1445,
"eval_samples_per_second": 21.705,
"eval_steps_per_second": 10.853,
"step": 64
},
{
"epoch": 0.06,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.6573,
"step": 65
},
{
"epoch": 0.06,
"learning_rate": 1.3200000000000002e-05,
"loss": 0.6169,
"step": 66
},
{
"epoch": 0.07,
"learning_rate": 1.3400000000000002e-05,
"loss": 0.7558,
"step": 67
},
{
"epoch": 0.07,
"learning_rate": 1.3600000000000002e-05,
"loss": 0.6838,
"step": 68
},
{
"epoch": 0.07,
"learning_rate": 1.38e-05,
"loss": 0.7144,
"step": 69
},
{
"epoch": 0.07,
"learning_rate": 1.4e-05,
"loss": 0.5879,
"step": 70
},
{
"epoch": 0.07,
"learning_rate": 1.4200000000000001e-05,
"loss": 0.5337,
"step": 71
},
{
"epoch": 0.07,
"learning_rate": 1.4400000000000001e-05,
"loss": 0.5077,
"step": 72
},
{
"epoch": 0.07,
"learning_rate": 1.46e-05,
"loss": 0.7427,
"step": 73
},
{
"epoch": 0.07,
"learning_rate": 1.48e-05,
"loss": 0.6866,
"step": 74
},
{
"epoch": 0.07,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.8974,
"step": 75
},
{
"epoch": 0.07,
"learning_rate": 1.5200000000000002e-05,
"loss": 0.5885,
"step": 76
},
{
"epoch": 0.08,
"learning_rate": 1.54e-05,
"loss": 0.5057,
"step": 77
},
{
"epoch": 0.08,
"learning_rate": 1.5600000000000003e-05,
"loss": 0.8,
"step": 78
},
{
"epoch": 0.08,
"learning_rate": 1.58e-05,
"loss": 0.6063,
"step": 79
},
{
"epoch": 0.08,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.5528,
"step": 80
},
{
"epoch": 0.08,
"learning_rate": 1.62e-05,
"loss": 0.7914,
"step": 81
},
{
"epoch": 0.08,
"learning_rate": 1.64e-05,
"loss": 0.6738,
"step": 82
},
{
"epoch": 0.08,
"learning_rate": 1.66e-05,
"loss": 0.6205,
"step": 83
},
{
"epoch": 0.08,
"learning_rate": 1.6800000000000002e-05,
"loss": 0.6988,
"step": 84
},
{
"epoch": 0.08,
"learning_rate": 1.7e-05,
"loss": 0.8053,
"step": 85
},
{
"epoch": 0.08,
"learning_rate": 1.72e-05,
"loss": 0.5992,
"step": 86
},
{
"epoch": 0.09,
"learning_rate": 1.7400000000000003e-05,
"loss": 0.5925,
"step": 87
},
{
"epoch": 0.09,
"learning_rate": 1.76e-05,
"loss": 0.5212,
"step": 88
},
{
"epoch": 0.09,
"learning_rate": 1.7800000000000002e-05,
"loss": 0.5899,
"step": 89
},
{
"epoch": 0.09,
"learning_rate": 1.8e-05,
"loss": 0.6747,
"step": 90
},
{
"epoch": 0.09,
"learning_rate": 1.8200000000000002e-05,
"loss": 0.7438,
"step": 91
},
{
"epoch": 0.09,
"learning_rate": 1.8400000000000003e-05,
"loss": 0.8297,
"step": 92
},
{
"epoch": 0.09,
"learning_rate": 1.86e-05,
"loss": 0.6353,
"step": 93
},
{
"epoch": 0.09,
"learning_rate": 1.88e-05,
"loss": 0.4809,
"step": 94
},
{
"epoch": 0.09,
"learning_rate": 1.9e-05,
"loss": 0.6279,
"step": 95
},
{
"epoch": 0.09,
"learning_rate": 1.9200000000000003e-05,
"loss": 0.6559,
"step": 96
},
{
"epoch": 0.1,
"learning_rate": 1.94e-05,
"loss": 0.6458,
"step": 97
},
{
"epoch": 0.1,
"learning_rate": 1.9600000000000002e-05,
"loss": 0.6687,
"step": 98
},
{
"epoch": 0.1,
"learning_rate": 1.98e-05,
"loss": 0.5882,
"step": 99
},
{
"epoch": 0.1,
"learning_rate": 2e-05,
"loss": 0.6256,
"step": 100
},
{
"epoch": 0.1,
"learning_rate": 1.999999433328606e-05,
"loss": 0.6327,
"step": 101
},
{
"epoch": 0.1,
"learning_rate": 1.999997733315066e-05,
"loss": 0.6028,
"step": 102
},
{
"epoch": 0.1,
"learning_rate": 1.9999948999613074e-05,
"loss": 0.7037,
"step": 103
},
{
"epoch": 0.1,
"learning_rate": 1.9999909332705403e-05,
"loss": 0.7454,
"step": 104
},
{
"epoch": 0.1,
"learning_rate": 1.999985833247261e-05,
"loss": 0.5024,
"step": 105
},
{
"epoch": 0.1,
"learning_rate": 1.999979599897249e-05,
"loss": 0.6243,
"step": 106
},
{
"epoch": 0.11,
"learning_rate": 1.99997223322757e-05,
"loss": 0.7174,
"step": 107
},
{
"epoch": 0.11,
"learning_rate": 1.999963733246572e-05,
"loss": 0.6342,
"step": 108
},
{
"epoch": 0.11,
"learning_rate": 1.9999540999638882e-05,
"loss": 0.5668,
"step": 109
},
{
"epoch": 0.11,
"learning_rate": 1.999943333390437e-05,
"loss": 0.5933,
"step": 110
},
{
"epoch": 0.11,
"learning_rate": 1.9999314335384205e-05,
"loss": 0.5791,
"step": 111
},
{
"epoch": 0.11,
"learning_rate": 1.9999184004213253e-05,
"loss": 0.5276,
"step": 112
},
{
"epoch": 0.11,
"learning_rate": 1.999904234053922e-05,
"loss": 0.5166,
"step": 113
},
{
"epoch": 0.11,
"learning_rate": 1.9998889344522668e-05,
"loss": 0.8269,
"step": 114
},
{
"epoch": 0.11,
"learning_rate": 1.9998725016336982e-05,
"loss": 0.7464,
"step": 115
},
{
"epoch": 0.11,
"learning_rate": 1.9998549356168415e-05,
"loss": 0.6589,
"step": 116
},
{
"epoch": 0.11,
"learning_rate": 1.999836236421604e-05,
"loss": 0.559,
"step": 117
},
{
"epoch": 0.12,
"learning_rate": 1.9998164040691787e-05,
"loss": 0.7274,
"step": 118
},
{
"epoch": 0.12,
"learning_rate": 1.999795438582043e-05,
"loss": 0.5698,
"step": 119
},
{
"epoch": 0.12,
"learning_rate": 1.999773339983957e-05,
"loss": 0.6225,
"step": 120
},
{
"epoch": 0.12,
"learning_rate": 1.9997501082999663e-05,
"loss": 0.843,
"step": 121
},
{
"epoch": 0.12,
"learning_rate": 1.9997257435564008e-05,
"loss": 0.5086,
"step": 122
},
{
"epoch": 0.12,
"learning_rate": 1.9997002457808735e-05,
"loss": 0.6249,
"step": 123
},
{
"epoch": 0.12,
"learning_rate": 1.9996736150022826e-05,
"loss": 0.6047,
"step": 124
},
{
"epoch": 0.12,
"learning_rate": 1.9996458512508095e-05,
"loss": 0.663,
"step": 125
},
{
"epoch": 0.12,
"learning_rate": 1.9996169545579205e-05,
"loss": 0.6057,
"step": 126
},
{
"epoch": 0.12,
"learning_rate": 1.9995869249563653e-05,
"loss": 0.6479,
"step": 127
},
{
"epoch": 0.13,
"learning_rate": 1.999555762480178e-05,
"loss": 0.6183,
"step": 128
},
{
"epoch": 0.13,
"eval_loss": 0.705041766166687,
"eval_runtime": 92.135,
"eval_samples_per_second": 21.707,
"eval_steps_per_second": 10.854,
"step": 128
},
{
"epoch": 0.13,
"learning_rate": 1.9995234671646753e-05,
"loss": 0.7109,
"step": 129
},
{
"epoch": 0.13,
"learning_rate": 1.9994900390464598e-05,
"loss": 0.6574,
"step": 130
},
{
"epoch": 0.13,
"learning_rate": 1.9994554781634168e-05,
"loss": 0.6746,
"step": 131
},
{
"epoch": 0.13,
"learning_rate": 1.9994197845547158e-05,
"loss": 0.6044,
"step": 132
},
{
"epoch": 0.13,
"learning_rate": 1.9993829582608093e-05,
"loss": 0.7447,
"step": 133
},
{
"epoch": 0.13,
"learning_rate": 1.9993449993234352e-05,
"loss": 0.5898,
"step": 134
},
{
"epoch": 0.13,
"learning_rate": 1.999305907785613e-05,
"loss": 0.5902,
"step": 135
},
{
"epoch": 0.13,
"learning_rate": 1.999265683691647e-05,
"loss": 0.57,
"step": 136
},
{
"epoch": 0.13,
"learning_rate": 1.999224327087125e-05,
"loss": 0.6226,
"step": 137
},
{
"epoch": 0.14,
"learning_rate": 1.9991818380189183e-05,
"loss": 0.6512,
"step": 138
},
{
"epoch": 0.14,
"learning_rate": 1.9991382165351816e-05,
"loss": 0.6892,
"step": 139
},
{
"epoch": 0.14,
"learning_rate": 1.9990934626853527e-05,
"loss": 0.6209,
"step": 140
},
{
"epoch": 0.14,
"learning_rate": 1.9990475765201537e-05,
"loss": 0.5818,
"step": 141
},
{
"epoch": 0.14,
"learning_rate": 1.9990005580915887e-05,
"loss": 0.6222,
"step": 142
},
{
"epoch": 0.14,
"learning_rate": 1.9989524074529455e-05,
"loss": 0.7126,
"step": 143
},
{
"epoch": 0.14,
"learning_rate": 1.9989031246587963e-05,
"loss": 0.7187,
"step": 144
},
{
"epoch": 0.14,
"learning_rate": 1.9988527097649943e-05,
"loss": 0.6048,
"step": 145
},
{
"epoch": 0.14,
"learning_rate": 1.9988011628286776e-05,
"loss": 0.7173,
"step": 146
},
{
"epoch": 0.14,
"learning_rate": 1.9987484839082666e-05,
"loss": 0.7256,
"step": 147
},
{
"epoch": 0.15,
"learning_rate": 1.9986946730634638e-05,
"loss": 0.5946,
"step": 148
},
{
"epoch": 0.15,
"learning_rate": 1.9986397303552557e-05,
"loss": 0.5126,
"step": 149
},
{
"epoch": 0.15,
"learning_rate": 1.9985836558459118e-05,
"loss": 0.6973,
"step": 150
},
{
"epoch": 0.15,
"learning_rate": 1.998526449598983e-05,
"loss": 0.8288,
"step": 151
},
{
"epoch": 0.15,
"learning_rate": 1.998468111679304e-05,
"loss": 0.6636,
"step": 152
},
{
"epoch": 0.15,
"learning_rate": 1.9984086421529913e-05,
"loss": 0.5965,
"step": 153
},
{
"epoch": 0.15,
"learning_rate": 1.9983480410874444e-05,
"loss": 0.5634,
"step": 154
},
{
"epoch": 0.15,
"learning_rate": 1.9982863085513455e-05,
"loss": 0.4541,
"step": 155
},
{
"epoch": 0.15,
"learning_rate": 1.998223444614658e-05,
"loss": 0.5818,
"step": 156
},
{
"epoch": 0.15,
"learning_rate": 1.998159449348629e-05,
"loss": 0.6991,
"step": 157
},
{
"epoch": 0.16,
"learning_rate": 1.9980943228257867e-05,
"loss": 0.6603,
"step": 158
},
{
"epoch": 0.16,
"learning_rate": 1.998028065119942e-05,
"loss": 0.5939,
"step": 159
},
{
"epoch": 0.16,
"learning_rate": 1.9979606763061866e-05,
"loss": 0.611,
"step": 160
},
{
"epoch": 0.16,
"learning_rate": 1.9978921564608968e-05,
"loss": 0.5047,
"step": 161
},
{
"epoch": 0.16,
"learning_rate": 1.9978225056617278e-05,
"loss": 0.6205,
"step": 162
},
{
"epoch": 0.16,
"learning_rate": 1.997751723987618e-05,
"loss": 0.5918,
"step": 163
},
{
"epoch": 0.16,
"learning_rate": 1.997679811518788e-05,
"loss": 0.6244,
"step": 164
},
{
"epoch": 0.16,
"learning_rate": 1.9976067683367388e-05,
"loss": 0.6781,
"step": 165
},
{
"epoch": 0.16,
"learning_rate": 1.997532594524253e-05,
"loss": 0.6196,
"step": 166
},
{
"epoch": 0.16,
"learning_rate": 1.997457290165396e-05,
"loss": 0.7421,
"step": 167
},
{
"epoch": 0.17,
"learning_rate": 1.997380855345512e-05,
"loss": 0.7234,
"step": 168
},
{
"epoch": 0.17,
"learning_rate": 1.997303290151229e-05,
"loss": 0.6198,
"step": 169
},
{
"epoch": 0.17,
"learning_rate": 1.9972245946704545e-05,
"loss": 0.5822,
"step": 170
},
{
"epoch": 0.17,
"learning_rate": 1.9971447689923777e-05,
"loss": 0.4994,
"step": 171
},
{
"epoch": 0.17,
"learning_rate": 1.9970638132074682e-05,
"loss": 0.5832,
"step": 172
},
{
"epoch": 0.17,
"learning_rate": 1.996981727407477e-05,
"loss": 0.6036,
"step": 173
},
{
"epoch": 0.17,
"learning_rate": 1.9968985116854348e-05,
"loss": 0.5373,
"step": 174
},
{
"epoch": 0.17,
"learning_rate": 1.996814166135654e-05,
"loss": 0.6451,
"step": 175
},
{
"epoch": 0.17,
"learning_rate": 1.9967286908537273e-05,
"loss": 0.5477,
"step": 176
},
{
"epoch": 0.17,
"learning_rate": 1.996642085936527e-05,
"loss": 0.9521,
"step": 177
},
{
"epoch": 0.17,
"learning_rate": 1.9965543514822063e-05,
"loss": 0.6307,
"step": 178
},
{
"epoch": 0.18,
"learning_rate": 1.9964654875901985e-05,
"loss": 0.7923,
"step": 179
},
{
"epoch": 0.18,
"learning_rate": 1.9963754943612167e-05,
"loss": 0.5962,
"step": 180
},
{
"epoch": 0.18,
"learning_rate": 1.996284371897254e-05,
"loss": 0.7595,
"step": 181
},
{
"epoch": 0.18,
"learning_rate": 1.9961921203015837e-05,
"loss": 0.5301,
"step": 182
},
{
"epoch": 0.18,
"learning_rate": 1.9960987396787582e-05,
"loss": 0.7748,
"step": 183
},
{
"epoch": 0.18,
"learning_rate": 1.99600423013461e-05,
"loss": 0.5263,
"step": 184
},
{
"epoch": 0.18,
"learning_rate": 1.9959085917762508e-05,
"loss": 0.6277,
"step": 185
},
{
"epoch": 0.18,
"learning_rate": 1.9958118247120714e-05,
"loss": 0.7354,
"step": 186
},
{
"epoch": 0.18,
"learning_rate": 1.9957139290517423e-05,
"loss": 0.6797,
"step": 187
},
{
"epoch": 0.18,
"learning_rate": 1.9956149049062125e-05,
"loss": 0.608,
"step": 188
},
{
"epoch": 0.19,
"learning_rate": 1.995514752387711e-05,
"loss": 0.7044,
"step": 189
},
{
"epoch": 0.19,
"learning_rate": 1.995413471609744e-05,
"loss": 0.5908,
"step": 190
},
{
"epoch": 0.19,
"learning_rate": 1.995311062687098e-05,
"loss": 0.6099,
"step": 191
},
{
"epoch": 0.19,
"learning_rate": 1.995207525735837e-05,
"loss": 0.5801,
"step": 192
},
{
"epoch": 0.19,
"eval_loss": 0.6848942637443542,
"eval_runtime": 92.1287,
"eval_samples_per_second": 21.709,
"eval_steps_per_second": 10.854,
"step": 192
},
{
"epoch": 0.19,
"learning_rate": 1.9951028608733044e-05,
"loss": 0.4869,
"step": 193
},
{
"epoch": 0.19,
"learning_rate": 1.9949970682181208e-05,
"loss": 0.6784,
"step": 194
},
{
"epoch": 0.19,
"learning_rate": 1.9948901478901858e-05,
"loss": 0.5492,
"step": 195
},
{
"epoch": 0.19,
"learning_rate": 1.994782100010677e-05,
"loss": 0.5425,
"step": 196
},
{
"epoch": 0.19,
"learning_rate": 1.9946729247020492e-05,
"loss": 0.7067,
"step": 197
},
{
"epoch": 0.19,
"learning_rate": 1.994562622088036e-05,
"loss": 0.5347,
"step": 198
},
{
"epoch": 0.2,
"learning_rate": 1.9944511922936476e-05,
"loss": 0.5843,
"step": 199
},
{
"epoch": 0.2,
"learning_rate": 1.9943386354451722e-05,
"loss": 0.5791,
"step": 200
},
{
"epoch": 0.2,
"learning_rate": 1.9942249516701757e-05,
"loss": 0.562,
"step": 201
},
{
"epoch": 0.2,
"learning_rate": 1.9941101410975e-05,
"loss": 0.7168,
"step": 202
},
{
"epoch": 0.2,
"learning_rate": 1.9939942038572657e-05,
"loss": 0.6258,
"step": 203
},
{
"epoch": 0.2,
"learning_rate": 1.9938771400808693e-05,
"loss": 0.8022,
"step": 204
},
{
"epoch": 0.2,
"learning_rate": 1.9937589499009834e-05,
"loss": 0.6551,
"step": 205
},
{
"epoch": 0.2,
"learning_rate": 1.993639633451559e-05,
"loss": 0.6644,
"step": 206
},
{
"epoch": 0.2,
"learning_rate": 1.9935191908678224e-05,
"loss": 0.6204,
"step": 207
},
{
"epoch": 0.2,
"learning_rate": 1.9933976222862754e-05,
"loss": 0.6568,
"step": 208
},
{
"epoch": 0.21,
"learning_rate": 1.9932749278446978e-05,
"loss": 0.6738,
"step": 209
},
{
"epoch": 0.21,
"learning_rate": 1.993151107682144e-05,
"loss": 0.6722,
"step": 210
},
{
"epoch": 0.21,
"learning_rate": 1.9930261619389446e-05,
"loss": 0.6123,
"step": 211
},
{
"epoch": 0.21,
"learning_rate": 1.9929000907567067e-05,
"loss": 0.6801,
"step": 212
},
{
"epoch": 0.21,
"learning_rate": 1.9927728942783112e-05,
"loss": 0.6636,
"step": 213
},
{
"epoch": 0.21,
"learning_rate": 1.9926445726479162e-05,
"loss": 0.6399,
"step": 214
},
{
"epoch": 0.21,
"learning_rate": 1.9925151260109533e-05,
"loss": 0.5353,
"step": 215
},
{
"epoch": 0.21,
"learning_rate": 1.9923845545141308e-05,
"loss": 0.7301,
"step": 216
},
{
"epoch": 0.21,
"learning_rate": 1.99225285830543e-05,
"loss": 0.6252,
"step": 217
},
{
"epoch": 0.21,
"learning_rate": 1.9921200375341087e-05,
"loss": 0.5592,
"step": 218
},
{
"epoch": 0.22,
"learning_rate": 1.9919860923506977e-05,
"loss": 0.5899,
"step": 219
},
{
"epoch": 0.22,
"learning_rate": 1.991851022907003e-05,
"loss": 0.6207,
"step": 220
},
{
"epoch": 0.22,
"learning_rate": 1.9917148293561048e-05,
"loss": 0.6192,
"step": 221
},
{
"epoch": 0.22,
"learning_rate": 1.9915775118523567e-05,
"loss": 0.754,
"step": 222
},
{
"epoch": 0.22,
"learning_rate": 1.991439070551387e-05,
"loss": 0.5859,
"step": 223
},
{
"epoch": 0.22,
"learning_rate": 1.9912995056100968e-05,
"loss": 0.5457,
"step": 224
},
{
"epoch": 0.22,
"learning_rate": 1.9911588171866612e-05,
"loss": 0.6023,
"step": 225
},
{
"epoch": 0.22,
"learning_rate": 1.991017005440528e-05,
"loss": 0.5688,
"step": 226
},
{
"epoch": 0.22,
"learning_rate": 1.990874070532419e-05,
"loss": 0.5487,
"step": 227
},
{
"epoch": 0.22,
"learning_rate": 1.9907300126243286e-05,
"loss": 0.6383,
"step": 228
},
{
"epoch": 0.23,
"learning_rate": 1.990584831879523e-05,
"loss": 0.6149,
"step": 229
},
{
"epoch": 0.23,
"learning_rate": 1.9904385284625426e-05,
"loss": 0.5578,
"step": 230
},
{
"epoch": 0.23,
"learning_rate": 1.9902911025391987e-05,
"loss": 0.6359,
"step": 231
},
{
"epoch": 0.23,
"learning_rate": 1.9901425542765757e-05,
"loss": 0.6004,
"step": 232
},
{
"epoch": 0.23,
"learning_rate": 1.9899928838430297e-05,
"loss": 0.5742,
"step": 233
},
{
"epoch": 0.23,
"learning_rate": 1.989842091408188e-05,
"loss": 0.6149,
"step": 234
},
{
"epoch": 0.23,
"learning_rate": 1.9896901771429516e-05,
"loss": 0.6688,
"step": 235
},
{
"epoch": 0.23,
"learning_rate": 1.98953714121949e-05,
"loss": 0.4935,
"step": 236
},
{
"epoch": 0.23,
"learning_rate": 1.989382983811246e-05,
"loss": 0.6845,
"step": 237
},
{
"epoch": 0.23,
"learning_rate": 1.9892277050929326e-05,
"loss": 0.5991,
"step": 238
},
{
"epoch": 0.23,
"learning_rate": 1.989071305240534e-05,
"loss": 0.61,
"step": 239
},
{
"epoch": 0.24,
"learning_rate": 1.9889137844313047e-05,
"loss": 0.6724,
"step": 240
},
{
"epoch": 0.24,
"learning_rate": 1.9887551428437696e-05,
"loss": 0.5567,
"step": 241
},
{
"epoch": 0.24,
"learning_rate": 1.988595380657724e-05,
"loss": 0.5438,
"step": 242
},
{
"epoch": 0.24,
"learning_rate": 1.9884344980542337e-05,
"loss": 0.5627,
"step": 243
},
{
"epoch": 0.24,
"learning_rate": 1.9882724952156337e-05,
"loss": 0.555,
"step": 244
},
{
"epoch": 0.24,
"learning_rate": 1.9881093723255283e-05,
"loss": 0.6202,
"step": 245
},
{
"epoch": 0.24,
"learning_rate": 1.9879451295687927e-05,
"loss": 0.702,
"step": 246
},
{
"epoch": 0.24,
"learning_rate": 1.9877797671315688e-05,
"loss": 0.5675,
"step": 247
},
{
"epoch": 0.24,
"learning_rate": 1.9876132852012697e-05,
"loss": 0.66,
"step": 248
},
{
"epoch": 0.24,
"learning_rate": 1.9874456839665767e-05,
"loss": 0.6814,
"step": 249
},
{
"epoch": 0.25,
"learning_rate": 1.9872769636174384e-05,
"loss": 0.4334,
"step": 250
},
{
"epoch": 0.25,
"learning_rate": 1.9871071243450745e-05,
"loss": 0.5295,
"step": 251
},
{
"epoch": 0.25,
"learning_rate": 1.9869361663419697e-05,
"loss": 0.571,
"step": 252
},
{
"epoch": 0.25,
"learning_rate": 1.9867640898018786e-05,
"loss": 0.6008,
"step": 253
},
{
"epoch": 0.25,
"learning_rate": 1.9865908949198223e-05,
"loss": 0.5558,
"step": 254
},
{
"epoch": 0.25,
"learning_rate": 1.9864165818920913e-05,
"loss": 0.6634,
"step": 255
},
{
"epoch": 0.25,
"learning_rate": 1.9862411509162406e-05,
"loss": 0.6901,
"step": 256
},
{
"epoch": 0.25,
"eval_loss": 0.6748067140579224,
"eval_runtime": 92.1359,
"eval_samples_per_second": 21.707,
"eval_steps_per_second": 10.854,
"step": 256
},
{
"epoch": 0.25,
"learning_rate": 1.9860646021910947e-05,
"loss": 0.5158,
"step": 257
},
{
"epoch": 0.25,
"learning_rate": 1.985886935916743e-05,
"loss": 0.5762,
"step": 258
},
{
"epoch": 0.25,
"learning_rate": 1.9857081522945427e-05,
"loss": 0.736,
"step": 259
},
{
"epoch": 0.26,
"learning_rate": 1.985528251527117e-05,
"loss": 0.6313,
"step": 260
},
{
"epoch": 0.26,
"learning_rate": 1.9853472338183544e-05,
"loss": 0.5199,
"step": 261
},
{
"epoch": 0.26,
"learning_rate": 1.9851650993734112e-05,
"loss": 0.7564,
"step": 262
},
{
"epoch": 0.26,
"learning_rate": 1.9849818483987074e-05,
"loss": 0.5001,
"step": 263
},
{
"epoch": 0.26,
"learning_rate": 1.9847974811019294e-05,
"loss": 0.4724,
"step": 264
},
{
"epoch": 0.26,
"learning_rate": 1.9846119976920284e-05,
"loss": 0.6663,
"step": 265
},
{
"epoch": 0.26,
"learning_rate": 1.984425398379221e-05,
"loss": 0.6231,
"step": 266
},
{
"epoch": 0.26,
"learning_rate": 1.9842376833749878e-05,
"loss": 0.4538,
"step": 267
},
{
"epoch": 0.26,
"learning_rate": 1.9840488528920743e-05,
"loss": 0.5518,
"step": 268
},
{
"epoch": 0.26,
"learning_rate": 1.9838589071444905e-05,
"loss": 0.5957,
"step": 269
},
{
"epoch": 0.27,
"learning_rate": 1.9836678463475096e-05,
"loss": 0.7355,
"step": 270
},
{
"epoch": 0.27,
"learning_rate": 1.983475670717669e-05,
"loss": 0.604,
"step": 271
},
{
"epoch": 0.27,
"learning_rate": 1.98328238047277e-05,
"loss": 0.5412,
"step": 272
},
{
"epoch": 0.27,
"learning_rate": 1.9830879758318765e-05,
"loss": 0.6476,
"step": 273
},
{
"epoch": 0.27,
"learning_rate": 1.9828924570153155e-05,
"loss": 0.5646,
"step": 274
},
{
"epoch": 0.27,
"learning_rate": 1.982695824244677e-05,
"loss": 0.5436,
"step": 275
},
{
"epoch": 0.27,
"learning_rate": 1.9824980777428133e-05,
"loss": 0.5466,
"step": 276
},
{
"epoch": 0.27,
"learning_rate": 1.9822992177338383e-05,
"loss": 0.6041,
"step": 277
},
{
"epoch": 0.27,
"learning_rate": 1.9820992444431296e-05,
"loss": 0.5578,
"step": 278
},
{
"epoch": 0.27,
"learning_rate": 1.9818981580973254e-05,
"loss": 0.6698,
"step": 279
},
{
"epoch": 0.28,
"learning_rate": 1.981695958924325e-05,
"loss": 0.5525,
"step": 280
},
{
"epoch": 0.28,
"learning_rate": 1.9814926471532888e-05,
"loss": 0.729,
"step": 281
},
{
"epoch": 0.28,
"learning_rate": 1.98128822301464e-05,
"loss": 0.6863,
"step": 282
},
{
"epoch": 0.28,
"learning_rate": 1.9810826867400605e-05,
"loss": 0.5483,
"step": 283
},
{
"epoch": 0.28,
"learning_rate": 1.9808760385624932e-05,
"loss": 0.6107,
"step": 284
},
{
"epoch": 0.28,
"learning_rate": 1.9806682787161418e-05,
"loss": 0.5194,
"step": 285
},
{
"epoch": 0.28,
"learning_rate": 1.9804594074364692e-05,
"loss": 0.6639,
"step": 286
},
{
"epoch": 0.28,
"learning_rate": 1.9802494249601984e-05,
"loss": 0.5012,
"step": 287
},
{
"epoch": 0.28,
"learning_rate": 1.9800383315253115e-05,
"loss": 0.5466,
"step": 288
},
{
"epoch": 0.28,
"learning_rate": 1.979826127371049e-05,
"loss": 0.5478,
"step": 289
},
{
"epoch": 0.28,
"learning_rate": 1.9796128127379117e-05,
"loss": 0.48,
"step": 290
},
{
"epoch": 0.29,
"learning_rate": 1.9793983878676578e-05,
"loss": 0.6836,
"step": 291
},
{
"epoch": 0.29,
"learning_rate": 1.9791828530033048e-05,
"loss": 0.5615,
"step": 292
},
{
"epoch": 0.29,
"learning_rate": 1.978966208389127e-05,
"loss": 0.5809,
"step": 293
},
{
"epoch": 0.29,
"learning_rate": 1.978748454270657e-05,
"loss": 0.5844,
"step": 294
},
{
"epoch": 0.29,
"learning_rate": 1.978529590894685e-05,
"loss": 0.6289,
"step": 295
},
{
"epoch": 0.29,
"learning_rate": 1.9783096185092582e-05,
"loss": 0.4815,
"step": 296
},
{
"epoch": 0.29,
"learning_rate": 1.978088537363681e-05,
"loss": 0.5463,
"step": 297
},
{
"epoch": 0.29,
"learning_rate": 1.9778663477085137e-05,
"loss": 0.5372,
"step": 298
},
{
"epoch": 0.29,
"learning_rate": 1.9776430497955736e-05,
"loss": 0.5588,
"step": 299
},
{
"epoch": 0.29,
"learning_rate": 1.9774186438779336e-05,
"loss": 0.4526,
"step": 300
},
{
"epoch": 0.3,
"learning_rate": 1.9771931302099228e-05,
"loss": 0.5449,
"step": 301
},
{
"epoch": 0.3,
"learning_rate": 1.9769665090471253e-05,
"loss": 0.7155,
"step": 302
},
{
"epoch": 0.3,
"learning_rate": 1.9767387806463807e-05,
"loss": 0.6767,
"step": 303
},
{
"epoch": 0.3,
"learning_rate": 1.976509945265783e-05,
"loss": 0.611,
"step": 304
},
{
"epoch": 0.3,
"learning_rate": 1.9762800031646814e-05,
"loss": 0.8605,
"step": 305
},
{
"epoch": 0.3,
"learning_rate": 1.9760489546036793e-05,
"loss": 0.6723,
"step": 306
},
{
"epoch": 0.3,
"learning_rate": 1.9758167998446334e-05,
"loss": 0.6633,
"step": 307
},
{
"epoch": 0.3,
"learning_rate": 1.975583539150655e-05,
"loss": 0.5117,
"step": 308
},
{
"epoch": 0.3,
"learning_rate": 1.9753491727861085e-05,
"loss": 0.6069,
"step": 309
},
{
"epoch": 0.3,
"learning_rate": 1.975113701016611e-05,
"loss": 0.5028,
"step": 310
},
{
"epoch": 0.31,
"learning_rate": 1.974877124109033e-05,
"loss": 0.5138,
"step": 311
},
{
"epoch": 0.31,
"learning_rate": 1.9746394423314973e-05,
"loss": 0.4409,
"step": 312
},
{
"epoch": 0.31,
"learning_rate": 1.9744006559533782e-05,
"loss": 0.5342,
"step": 313
},
{
"epoch": 0.31,
"learning_rate": 1.9741607652453033e-05,
"loss": 0.4869,
"step": 314
},
{
"epoch": 0.31,
"learning_rate": 1.9739197704791508e-05,
"loss": 0.586,
"step": 315
},
{
"epoch": 0.31,
"learning_rate": 1.9736776719280502e-05,
"loss": 0.6161,
"step": 316
},
{
"epoch": 0.31,
"learning_rate": 1.9734344698663823e-05,
"loss": 0.5257,
"step": 317
},
{
"epoch": 0.31,
"learning_rate": 1.973190164569778e-05,
"loss": 0.5142,
"step": 318
},
{
"epoch": 0.31,
"learning_rate": 1.9729447563151193e-05,
"loss": 0.6155,
"step": 319
},
{
"epoch": 0.31,
"learning_rate": 1.9726982453805383e-05,
"loss": 0.5016,
"step": 320
},
{
"epoch": 0.31,
"eval_loss": 0.6677874326705933,
"eval_runtime": 92.1385,
"eval_samples_per_second": 21.706,
"eval_steps_per_second": 10.853,
"step": 320
},
{
"epoch": 0.32,
"learning_rate": 1.9724506320454153e-05,
"loss": 0.5549,
"step": 321
},
{
"epoch": 0.32,
"learning_rate": 1.972201916590382e-05,
"loss": 0.5889,
"step": 322
},
{
"epoch": 0.32,
"learning_rate": 1.971952099297318e-05,
"loss": 0.6956,
"step": 323
},
{
"epoch": 0.32,
"learning_rate": 1.971701180449352e-05,
"loss": 0.5185,
"step": 324
},
{
"epoch": 0.32,
"learning_rate": 1.971449160330861e-05,
"loss": 0.6535,
"step": 325
},
{
"epoch": 0.32,
"learning_rate": 1.9711960392274698e-05,
"loss": 0.5459,
"step": 326
},
{
"epoch": 0.32,
"learning_rate": 1.9709418174260523e-05,
"loss": 0.53,
"step": 327
},
{
"epoch": 0.32,
"learning_rate": 1.970686495214728e-05,
"loss": 0.5827,
"step": 328
},
{
"epoch": 0.32,
"learning_rate": 1.970430072882865e-05,
"loss": 0.5848,
"step": 329
},
{
"epoch": 0.32,
"learning_rate": 1.9701725507210776e-05,
"loss": 0.5544,
"step": 330
},
{
"epoch": 0.33,
"learning_rate": 1.9699139290212267e-05,
"loss": 0.5165,
"step": 331
},
{
"epoch": 0.33,
"learning_rate": 1.969654208076419e-05,
"loss": 0.6333,
"step": 332
},
{
"epoch": 0.33,
"learning_rate": 1.969393388181008e-05,
"loss": 0.7029,
"step": 333
},
{
"epoch": 0.33,
"learning_rate": 1.9691314696305915e-05,
"loss": 0.6081,
"step": 334
},
{
"epoch": 0.33,
"learning_rate": 1.9688684527220133e-05,
"loss": 0.7165,
"step": 335
},
{
"epoch": 0.33,
"learning_rate": 1.9686043377533615e-05,
"loss": 0.524,
"step": 336
},
{
"epoch": 0.33,
"learning_rate": 1.9683391250239693e-05,
"loss": 0.6743,
"step": 337
},
{
"epoch": 0.33,
"learning_rate": 1.9680728148344132e-05,
"loss": 0.64,
"step": 338
},
{
"epoch": 0.33,
"learning_rate": 1.9678054074865137e-05,
"loss": 0.6171,
"step": 339
},
{
"epoch": 0.33,
"learning_rate": 1.967536903283336e-05,
"loss": 0.6021,
"step": 340
},
{
"epoch": 0.34,
"learning_rate": 1.9672673025291863e-05,
"loss": 0.5922,
"step": 341
},
{
"epoch": 0.34,
"learning_rate": 1.9669966055296154e-05,
"loss": 0.4512,
"step": 342
},
{
"epoch": 0.34,
"learning_rate": 1.9667248125914153e-05,
"loss": 0.5496,
"step": 343
},
{
"epoch": 0.34,
"learning_rate": 1.966451924022621e-05,
"loss": 0.7078,
"step": 344
},
{
"epoch": 0.34,
"learning_rate": 1.9661779401325086e-05,
"loss": 0.5699,
"step": 345
},
{
"epoch": 0.34,
"learning_rate": 1.965902861231596e-05,
"loss": 0.5894,
"step": 346
},
{
"epoch": 0.34,
"learning_rate": 1.965626687631641e-05,
"loss": 0.5899,
"step": 347
},
{
"epoch": 0.34,
"learning_rate": 1.9653494196456442e-05,
"loss": 0.5675,
"step": 348
},
{
"epoch": 0.34,
"learning_rate": 1.9650710575878445e-05,
"loss": 0.5252,
"step": 349
},
{
"epoch": 0.34,
"learning_rate": 1.9647916017737218e-05,
"loss": 0.5635,
"step": 350
},
{
"epoch": 0.34,
"learning_rate": 1.964511052519995e-05,
"loss": 0.5287,
"step": 351
},
{
"epoch": 0.35,
"learning_rate": 1.964229410144623e-05,
"loss": 0.6825,
"step": 352
},
{
"epoch": 0.35,
"learning_rate": 1.963946674966803e-05,
"loss": 0.5502,
"step": 353
},
{
"epoch": 0.35,
"learning_rate": 1.9636628473069704e-05,
"loss": 0.5904,
"step": 354
},
{
"epoch": 0.35,
"learning_rate": 1.9633779274868003e-05,
"loss": 0.5705,
"step": 355
},
{
"epoch": 0.35,
"learning_rate": 1.9630919158292037e-05,
"loss": 0.5459,
"step": 356
},
{
"epoch": 0.35,
"learning_rate": 1.9628048126583298e-05,
"loss": 0.5555,
"step": 357
},
{
"epoch": 0.35,
"learning_rate": 1.9625166182995654e-05,
"loss": 0.4807,
"step": 358
},
{
"epoch": 0.35,
"learning_rate": 1.962227333079533e-05,
"loss": 0.5867,
"step": 359
},
{
"epoch": 0.35,
"learning_rate": 1.9619369573260924e-05,
"loss": 0.6056,
"step": 360
},
{
"epoch": 0.35,
"learning_rate": 1.9616454913683383e-05,
"loss": 0.5912,
"step": 361
},
{
"epoch": 0.36,
"learning_rate": 1.9613529355366026e-05,
"loss": 0.4929,
"step": 362
},
{
"epoch": 0.36,
"learning_rate": 1.96105929016245e-05,
"loss": 0.6125,
"step": 363
},
{
"epoch": 0.36,
"learning_rate": 1.9607645555786823e-05,
"loss": 0.6415,
"step": 364
},
{
"epoch": 0.36,
"learning_rate": 1.9604687321193342e-05,
"loss": 0.5401,
"step": 365
},
{
"epoch": 0.36,
"learning_rate": 1.9601718201196757e-05,
"loss": 0.4589,
"step": 366
},
{
"epoch": 0.36,
"learning_rate": 1.9598738199162094e-05,
"loss": 0.6138,
"step": 367
},
{
"epoch": 0.36,
"learning_rate": 1.959574731846672e-05,
"loss": 0.5734,
"step": 368
},
{
"epoch": 0.36,
"learning_rate": 1.9592745562500326e-05,
"loss": 0.4655,
"step": 369
},
{
"epoch": 0.36,
"learning_rate": 1.958973293466493e-05,
"loss": 0.4814,
"step": 370
},
{
"epoch": 0.36,
"learning_rate": 1.9586709438374873e-05,
"loss": 0.4206,
"step": 371
},
{
"epoch": 0.37,
"learning_rate": 1.958367507705681e-05,
"loss": 0.6551,
"step": 372
},
{
"epoch": 0.37,
"learning_rate": 1.958062985414972e-05,
"loss": 0.5372,
"step": 373
},
{
"epoch": 0.37,
"learning_rate": 1.9577573773104877e-05,
"loss": 0.6906,
"step": 374
},
{
"epoch": 0.37,
"learning_rate": 1.9574506837385872e-05,
"loss": 0.6007,
"step": 375
},
{
"epoch": 0.37,
"learning_rate": 1.9571429050468594e-05,
"loss": 0.636,
"step": 376
},
{
"epoch": 0.37,
"learning_rate": 1.956834041584123e-05,
"loss": 0.6088,
"step": 377
},
{
"epoch": 0.37,
"learning_rate": 1.956524093700426e-05,
"loss": 0.6225,
"step": 378
},
{
"epoch": 0.37,
"learning_rate": 1.9562130617470463e-05,
"loss": 0.6323,
"step": 379
},
{
"epoch": 0.37,
"learning_rate": 1.9559009460764885e-05,
"loss": 0.5683,
"step": 380
},
{
"epoch": 0.37,
"learning_rate": 1.955587747042488e-05,
"loss": 0.6235,
"step": 381
},
{
"epoch": 0.38,
"learning_rate": 1.955273465000006e-05,
"loss": 0.5892,
"step": 382
},
{
"epoch": 0.38,
"learning_rate": 1.9549581003052315e-05,
"loss": 0.5734,
"step": 383
},
{
"epoch": 0.38,
"learning_rate": 1.954641653315581e-05,
"loss": 0.5113,
"step": 384
},
{
"epoch": 0.38,
"eval_loss": 0.6619812846183777,
"eval_runtime": 92.1362,
"eval_samples_per_second": 21.707,
"eval_steps_per_second": 10.854,
"step": 384
},
{
"epoch": 0.38,
"learning_rate": 1.9543241243896976e-05,
"loss": 0.6799,
"step": 385
},
{
"epoch": 0.38,
"learning_rate": 1.9540055138874504e-05,
"loss": 0.5934,
"step": 386
},
{
"epoch": 0.38,
"learning_rate": 1.9536858221699342e-05,
"loss": 0.4988,
"step": 387
},
{
"epoch": 0.38,
"learning_rate": 1.9533650495994697e-05,
"loss": 0.5526,
"step": 388
},
{
"epoch": 0.38,
"learning_rate": 1.9530431965396013e-05,
"loss": 0.5664,
"step": 389
},
{
"epoch": 0.38,
"learning_rate": 1.9527202633551e-05,
"loss": 0.6442,
"step": 390
},
{
"epoch": 0.38,
"learning_rate": 1.9523962504119588e-05,
"loss": 0.4919,
"step": 391
},
{
"epoch": 0.39,
"learning_rate": 1.952071158077396e-05,
"loss": 0.5236,
"step": 392
},
{
"epoch": 0.39,
"learning_rate": 1.9517449867198523e-05,
"loss": 0.5732,
"step": 393
},
{
"epoch": 0.39,
"learning_rate": 1.9514177367089918e-05,
"loss": 0.6263,
"step": 394
},
{
"epoch": 0.39,
"learning_rate": 1.951089408415701e-05,
"loss": 0.5807,
"step": 395
},
{
"epoch": 0.39,
"learning_rate": 1.950760002212088e-05,
"loss": 0.5942,
"step": 396
},
{
"epoch": 0.39,
"learning_rate": 1.9504295184714838e-05,
"loss": 0.4897,
"step": 397
},
{
"epoch": 0.39,
"learning_rate": 1.9500979575684392e-05,
"loss": 0.5562,
"step": 398
},
{
"epoch": 0.39,
"learning_rate": 1.9497653198787265e-05,
"loss": 0.6829,
"step": 399
},
{
"epoch": 0.39,
"learning_rate": 1.949431605779338e-05,
"loss": 0.7462,
"step": 400
},
{
"epoch": 0.39,
"learning_rate": 1.9490968156484867e-05,
"loss": 0.4942,
"step": 401
},
{
"epoch": 0.39,
"learning_rate": 1.948760949865604e-05,
"loss": 0.6106,
"step": 402
},
{
"epoch": 0.4,
"learning_rate": 1.9484240088113407e-05,
"loss": 0.7027,
"step": 403
},
{
"epoch": 0.4,
"learning_rate": 1.9480859928675674e-05,
"loss": 0.5575,
"step": 404
},
{
"epoch": 0.4,
"learning_rate": 1.9477469024173717e-05,
"loss": 0.5348,
"step": 405
},
{
"epoch": 0.4,
"learning_rate": 1.947406737845059e-05,
"loss": 0.5284,
"step": 406
},
{
"epoch": 0.4,
"learning_rate": 1.9470654995361526e-05,
"loss": 0.838,
"step": 407
},
{
"epoch": 0.4,
"learning_rate": 1.9467231878773925e-05,
"loss": 0.692,
"step": 408
},
{
"epoch": 0.4,
"learning_rate": 1.9463798032567352e-05,
"loss": 0.7596,
"step": 409
},
{
"epoch": 0.4,
"learning_rate": 1.946035346063353e-05,
"loss": 0.6378,
"step": 410
},
{
"epoch": 0.4,
"learning_rate": 1.9456898166876344e-05,
"loss": 0.4766,
"step": 411
},
{
"epoch": 0.4,
"learning_rate": 1.945343215521182e-05,
"loss": 0.8978,
"step": 412
},
{
"epoch": 0.41,
"learning_rate": 1.944995542956814e-05,
"loss": 0.6245,
"step": 413
},
{
"epoch": 0.41,
"learning_rate": 1.944646799388563e-05,
"loss": 0.6317,
"step": 414
},
{
"epoch": 0.41,
"learning_rate": 1.9442969852116743e-05,
"loss": 0.5779,
"step": 415
},
{
"epoch": 0.41,
"learning_rate": 1.9439461008226078e-05,
"loss": 0.6473,
"step": 416
},
{
"epoch": 0.41,
"learning_rate": 1.9435941466190353e-05,
"loss": 0.7423,
"step": 417
},
{
"epoch": 0.41,
"learning_rate": 1.943241122999842e-05,
"loss": 0.5844,
"step": 418
},
{
"epoch": 0.41,
"learning_rate": 1.9428870303651246e-05,
"loss": 0.6334,
"step": 419
},
{
"epoch": 0.41,
"learning_rate": 1.9425318691161915e-05,
"loss": 0.463,
"step": 420
},
{
"epoch": 0.41,
"learning_rate": 1.942175639655562e-05,
"loss": 0.7012,
"step": 421
},
{
"epoch": 0.41,
"learning_rate": 1.941818342386966e-05,
"loss": 0.4855,
"step": 422
},
{
"epoch": 0.42,
"learning_rate": 1.9414599777153443e-05,
"loss": 0.5386,
"step": 423
},
{
"epoch": 0.42,
"learning_rate": 1.941100546046846e-05,
"loss": 0.5807,
"step": 424
},
{
"epoch": 0.42,
"learning_rate": 1.9407400477888315e-05,
"loss": 0.6452,
"step": 425
},
{
"epoch": 0.42,
"learning_rate": 1.9403784833498684e-05,
"loss": 0.6562,
"step": 426
},
{
"epoch": 0.42,
"learning_rate": 1.940015853139733e-05,
"loss": 0.5725,
"step": 427
},
{
"epoch": 0.42,
"learning_rate": 1.93965215756941e-05,
"loss": 0.5738,
"step": 428
},
{
"epoch": 0.42,
"learning_rate": 1.9392873970510905e-05,
"loss": 0.6161,
"step": 429
},
{
"epoch": 0.42,
"learning_rate": 1.938921571998174e-05,
"loss": 0.586,
"step": 430
},
{
"epoch": 0.42,
"learning_rate": 1.9385546828252653e-05,
"loss": 0.6672,
"step": 431
},
{
"epoch": 0.42,
"learning_rate": 1.9381867299481754e-05,
"loss": 0.5885,
"step": 432
},
{
"epoch": 0.43,
"learning_rate": 1.9378177137839214e-05,
"loss": 0.6214,
"step": 433
},
{
"epoch": 0.43,
"learning_rate": 1.9374476347507247e-05,
"loss": 0.623,
"step": 434
},
{
"epoch": 0.43,
"learning_rate": 1.937076493268012e-05,
"loss": 0.6748,
"step": 435
},
{
"epoch": 0.43,
"learning_rate": 1.9367042897564142e-05,
"loss": 0.5884,
"step": 436
},
{
"epoch": 0.43,
"learning_rate": 1.9363310246377648e-05,
"loss": 0.6778,
"step": 437
},
{
"epoch": 0.43,
"learning_rate": 1.9359566983351015e-05,
"loss": 0.475,
"step": 438
},
{
"epoch": 0.43,
"learning_rate": 1.935581311272664e-05,
"loss": 0.5686,
"step": 439
},
{
"epoch": 0.43,
"learning_rate": 1.9352048638758948e-05,
"loss": 0.4168,
"step": 440
},
{
"epoch": 0.43,
"learning_rate": 1.9348273565714378e-05,
"loss": 0.8648,
"step": 441
},
{
"epoch": 0.43,
"learning_rate": 1.934448789787138e-05,
"loss": 0.6103,
"step": 442
},
{
"epoch": 0.44,
"learning_rate": 1.9340691639520414e-05,
"loss": 0.6311,
"step": 443
},
{
"epoch": 0.44,
"learning_rate": 1.9336884794963946e-05,
"loss": 0.6184,
"step": 444
},
{
"epoch": 0.44,
"learning_rate": 1.9333067368516428e-05,
"loss": 0.6603,
"step": 445
},
{
"epoch": 0.44,
"learning_rate": 1.9329239364504323e-05,
"loss": 0.5903,
"step": 446
},
{
"epoch": 0.44,
"learning_rate": 1.9325400787266065e-05,
"loss": 0.477,
"step": 447
},
{
"epoch": 0.44,
"learning_rate": 1.9321551641152076e-05,
"loss": 0.4994,
"step": 448
},
{
"epoch": 0.44,
"eval_loss": 0.6565234065055847,
"eval_runtime": 92.1185,
"eval_samples_per_second": 21.711,
"eval_steps_per_second": 10.856,
"step": 448
},
{
"epoch": 0.44,
"learning_rate": 1.9317691930524763e-05,
"loss": 0.6525,
"step": 449
},
{
"epoch": 0.44,
"learning_rate": 1.9313821659758498e-05,
"loss": 0.4883,
"step": 450
},
{
"epoch": 0.44,
"learning_rate": 1.9309940833239628e-05,
"loss": 0.616,
"step": 451
},
{
"epoch": 0.44,
"learning_rate": 1.9306049455366453e-05,
"loss": 0.8203,
"step": 452
},
{
"epoch": 0.45,
"learning_rate": 1.9302147530549245e-05,
"loss": 0.6362,
"step": 453
},
{
"epoch": 0.45,
"learning_rate": 1.929823506321022e-05,
"loss": 0.5773,
"step": 454
},
{
"epoch": 0.45,
"learning_rate": 1.9294312057783543e-05,
"loss": 0.5675,
"step": 455
},
{
"epoch": 0.45,
"learning_rate": 1.9290378518715327e-05,
"loss": 0.4942,
"step": 456
},
{
"epoch": 0.45,
"learning_rate": 1.928643445046362e-05,
"loss": 0.5928,
"step": 457
},
{
"epoch": 0.45,
"learning_rate": 1.9282479857498395e-05,
"loss": 0.6095,
"step": 458
},
{
"epoch": 0.45,
"learning_rate": 1.9278514744301573e-05,
"loss": 0.5911,
"step": 459
},
{
"epoch": 0.45,
"learning_rate": 1.927453911536698e-05,
"loss": 0.6702,
"step": 460
},
{
"epoch": 0.45,
"learning_rate": 1.927055297520037e-05,
"loss": 0.5072,
"step": 461
},
{
"epoch": 0.45,
"learning_rate": 1.9266556328319402e-05,
"loss": 0.5075,
"step": 462
},
{
"epoch": 0.45,
"learning_rate": 1.926254917925365e-05,
"loss": 0.6498,
"step": 463
},
{
"epoch": 0.46,
"learning_rate": 1.9258531532544586e-05,
"loss": 0.6032,
"step": 464
},
{
"epoch": 0.46,
"learning_rate": 1.9254503392745584e-05,
"loss": 0.5094,
"step": 465
},
{
"epoch": 0.46,
"learning_rate": 1.9250464764421905e-05,
"loss": 0.6339,
"step": 466
},
{
"epoch": 0.46,
"learning_rate": 1.9246415652150694e-05,
"loss": 0.6805,
"step": 467
},
{
"epoch": 0.46,
"learning_rate": 1.9242356060520992e-05,
"loss": 0.5546,
"step": 468
},
{
"epoch": 0.46,
"learning_rate": 1.92382859941337e-05,
"loss": 0.497,
"step": 469
},
{
"epoch": 0.46,
"learning_rate": 1.9234205457601608e-05,
"loss": 0.6051,
"step": 470
},
{
"epoch": 0.46,
"learning_rate": 1.9230114455549355e-05,
"loss": 0.4472,
"step": 471
},
{
"epoch": 0.46,
"learning_rate": 1.922601299261345e-05,
"loss": 0.5803,
"step": 472
},
{
"epoch": 0.46,
"learning_rate": 1.922190107344226e-05,
"loss": 0.5564,
"step": 473
},
{
"epoch": 0.47,
"learning_rate": 1.921777870269599e-05,
"loss": 0.5021,
"step": 474
},
{
"epoch": 0.47,
"learning_rate": 1.921364588504671e-05,
"loss": 0.4868,
"step": 475
},
{
"epoch": 0.47,
"learning_rate": 1.920950262517831e-05,
"loss": 0.6012,
"step": 476
},
{
"epoch": 0.47,
"learning_rate": 1.9205348927786533e-05,
"loss": 0.4786,
"step": 477
},
{
"epoch": 0.47,
"learning_rate": 1.9201184797578937e-05,
"loss": 0.4347,
"step": 478
},
{
"epoch": 0.47,
"learning_rate": 1.919701023927491e-05,
"loss": 0.5688,
"step": 479
},
{
"epoch": 0.47,
"learning_rate": 1.919282525760565e-05,
"loss": 0.5875,
"step": 480
},
{
"epoch": 0.47,
"learning_rate": 1.9188629857314186e-05,
"loss": 0.6125,
"step": 481
},
{
"epoch": 0.47,
"learning_rate": 1.918442404315534e-05,
"loss": 0.6252,
"step": 482
},
{
"epoch": 0.47,
"learning_rate": 1.9180207819895745e-05,
"loss": 0.5012,
"step": 483
},
{
"epoch": 0.48,
"learning_rate": 1.9175981192313822e-05,
"loss": 0.6249,
"step": 484
},
{
"epoch": 0.48,
"learning_rate": 1.9171744165199792e-05,
"loss": 0.4791,
"step": 485
},
{
"epoch": 0.48,
"learning_rate": 1.916749674335566e-05,
"loss": 0.5655,
"step": 486
},
{
"epoch": 0.48,
"learning_rate": 1.9163238931595205e-05,
"loss": 0.6597,
"step": 487
},
{
"epoch": 0.48,
"learning_rate": 1.9158970734743994e-05,
"loss": 0.7171,
"step": 488
},
{
"epoch": 0.48,
"learning_rate": 1.9154692157639357e-05,
"loss": 0.7145,
"step": 489
},
{
"epoch": 0.48,
"learning_rate": 1.9150403205130384e-05,
"loss": 0.49,
"step": 490
},
{
"epoch": 0.48,
"learning_rate": 1.914610388207793e-05,
"loss": 0.6374,
"step": 491
},
{
"epoch": 0.48,
"learning_rate": 1.91417941933546e-05,
"loss": 0.6496,
"step": 492
},
{
"epoch": 0.48,
"learning_rate": 1.9137474143844758e-05,
"loss": 0.6032,
"step": 493
},
{
"epoch": 0.49,
"learning_rate": 1.9133143738444485e-05,
"loss": 0.5627,
"step": 494
},
{
"epoch": 0.49,
"learning_rate": 1.9128802982061628e-05,
"loss": 0.4698,
"step": 495
},
{
"epoch": 0.49,
"learning_rate": 1.912445187961575e-05,
"loss": 0.5617,
"step": 496
},
{
"epoch": 0.49,
"learning_rate": 1.9120090436038137e-05,
"loss": 0.406,
"step": 497
},
{
"epoch": 0.49,
"learning_rate": 1.9115718656271803e-05,
"loss": 0.6347,
"step": 498
},
{
"epoch": 0.49,
"learning_rate": 1.911133654527147e-05,
"loss": 0.6834,
"step": 499
},
{
"epoch": 0.49,
"learning_rate": 1.9106944108003574e-05,
"loss": 0.6969,
"step": 500
},
{
"epoch": 0.49,
"learning_rate": 1.9102541349446252e-05,
"loss": 0.5373,
"step": 501
},
{
"epoch": 0.49,
"learning_rate": 1.909812827458934e-05,
"loss": 0.5486,
"step": 502
},
{
"epoch": 0.49,
"learning_rate": 1.909370488843436e-05,
"loss": 0.6086,
"step": 503
},
{
"epoch": 0.5,
"learning_rate": 1.908927119599453e-05,
"loss": 0.7068,
"step": 504
},
{
"epoch": 0.5,
"learning_rate": 1.9084827202294742e-05,
"loss": 0.6374,
"step": 505
},
{
"epoch": 0.5,
"learning_rate": 1.9080372912371562e-05,
"loss": 0.7382,
"step": 506
},
{
"epoch": 0.5,
"learning_rate": 1.907590833127323e-05,
"loss": 0.6204,
"step": 507
},
{
"epoch": 0.5,
"learning_rate": 1.9071433464059647e-05,
"loss": 0.477,
"step": 508
},
{
"epoch": 0.5,
"learning_rate": 1.9066948315802363e-05,
"loss": 0.5462,
"step": 509
},
{
"epoch": 0.5,
"learning_rate": 1.90624528915846e-05,
"loss": 0.8172,
"step": 510
},
{
"epoch": 0.5,
"learning_rate": 1.9057947196501213e-05,
"loss": 0.6394,
"step": 511
},
{
"epoch": 0.5,
"learning_rate": 1.9053431235658695e-05,
"loss": 0.5942,
"step": 512
},
{
"epoch": 0.5,
"eval_loss": 0.6541461944580078,
"eval_runtime": 92.1391,
"eval_samples_per_second": 21.706,
"eval_steps_per_second": 10.853,
"step": 512
},
{
"epoch": 0.5,
"learning_rate": 1.9048905014175178e-05,
"loss": 0.5821,
"step": 513
},
{
"epoch": 0.51,
"learning_rate": 1.9044368537180424e-05,
"loss": 0.5485,
"step": 514
},
{
"epoch": 0.51,
"learning_rate": 1.903982180981581e-05,
"loss": 0.6743,
"step": 515
},
{
"epoch": 0.51,
"learning_rate": 1.9035264837234347e-05,
"loss": 0.5285,
"step": 516
},
{
"epoch": 0.51,
"learning_rate": 1.9030697624600644e-05,
"loss": 0.5084,
"step": 517
},
{
"epoch": 0.51,
"learning_rate": 1.9026120177090915e-05,
"loss": 0.547,
"step": 518
},
{
"epoch": 0.51,
"learning_rate": 1.9021532499892982e-05,
"loss": 0.5065,
"step": 519
},
{
"epoch": 0.51,
"learning_rate": 1.901693459820625e-05,
"loss": 0.6824,
"step": 520
},
{
"epoch": 0.51,
"learning_rate": 1.901232647724172e-05,
"loss": 0.6373,
"step": 521
},
{
"epoch": 0.51,
"learning_rate": 1.9007708142221975e-05,
"loss": 0.5872,
"step": 522
},
{
"epoch": 0.51,
"learning_rate": 1.9003079598381167e-05,
"loss": 0.6842,
"step": 523
},
{
"epoch": 0.51,
"learning_rate": 1.8998440850965027e-05,
"loss": 0.485,
"step": 524
},
{
"epoch": 0.52,
"learning_rate": 1.8993791905230846e-05,
"loss": 0.7171,
"step": 525
},
{
"epoch": 0.52,
"learning_rate": 1.8989132766447474e-05,
"loss": 0.7202,
"step": 526
},
{
"epoch": 0.52,
"learning_rate": 1.8984463439895305e-05,
"loss": 0.6693,
"step": 527
},
{
"epoch": 0.52,
"learning_rate": 1.89797839308663e-05,
"loss": 0.6171,
"step": 528
},
{
"epoch": 0.52,
"learning_rate": 1.897509424466393e-05,
"loss": 0.6535,
"step": 529
},
{
"epoch": 0.52,
"learning_rate": 1.897039438660323e-05,
"loss": 0.6767,
"step": 530
},
{
"epoch": 0.52,
"learning_rate": 1.8965684362010745e-05,
"loss": 0.4948,
"step": 531
},
{
"epoch": 0.52,
"learning_rate": 1.8960964176224546e-05,
"loss": 0.6155,
"step": 532
},
{
"epoch": 0.52,
"learning_rate": 1.8956233834594225e-05,
"loss": 0.5414,
"step": 533
},
{
"epoch": 0.52,
"learning_rate": 1.895149334248088e-05,
"loss": 0.4703,
"step": 534
},
{
"epoch": 0.53,
"learning_rate": 1.8946742705257112e-05,
"loss": 0.4943,
"step": 535
},
{
"epoch": 0.53,
"learning_rate": 1.8941981928307023e-05,
"loss": 0.6737,
"step": 536
},
{
"epoch": 0.53,
"learning_rate": 1.8937211017026205e-05,
"loss": 0.4268,
"step": 537
},
{
"epoch": 0.53,
"learning_rate": 1.8932429976821733e-05,
"loss": 0.5434,
"step": 538
},
{
"epoch": 0.53,
"learning_rate": 1.892763881311217e-05,
"loss": 0.5222,
"step": 539
},
{
"epoch": 0.53,
"learning_rate": 1.892283753132754e-05,
"loss": 0.7323,
"step": 540
},
{
"epoch": 0.53,
"learning_rate": 1.891802613690935e-05,
"loss": 0.4247,
"step": 541
},
{
"epoch": 0.53,
"learning_rate": 1.8913204635310548e-05,
"loss": 0.5733,
"step": 542
},
{
"epoch": 0.53,
"learning_rate": 1.8908373031995558e-05,
"loss": 0.6486,
"step": 543
},
{
"epoch": 0.53,
"learning_rate": 1.8903531332440236e-05,
"loss": 0.6881,
"step": 544
},
{
"epoch": 0.54,
"learning_rate": 1.8898679542131896e-05,
"loss": 0.535,
"step": 545
},
{
"epoch": 0.54,
"learning_rate": 1.8893817666569266e-05,
"loss": 0.5699,
"step": 546
},
{
"epoch": 0.54,
"learning_rate": 1.8888945711262532e-05,
"loss": 0.4792,
"step": 547
},
{
"epoch": 0.54,
"learning_rate": 1.8884063681733278e-05,
"loss": 0.588,
"step": 548
},
{
"epoch": 0.54,
"learning_rate": 1.8879171583514524e-05,
"loss": 0.7845,
"step": 549
},
{
"epoch": 0.54,
"learning_rate": 1.887426942215069e-05,
"loss": 0.6052,
"step": 550
},
{
"epoch": 0.54,
"learning_rate": 1.886935720319761e-05,
"loss": 0.5702,
"step": 551
},
{
"epoch": 0.54,
"learning_rate": 1.88644349322225e-05,
"loss": 0.5422,
"step": 552
},
{
"epoch": 0.54,
"learning_rate": 1.8859502614804e-05,
"loss": 0.4487,
"step": 553
},
{
"epoch": 0.54,
"learning_rate": 1.8854560256532098e-05,
"loss": 0.5661,
"step": 554
},
{
"epoch": 0.55,
"learning_rate": 1.884960786300819e-05,
"loss": 0.6781,
"step": 555
},
{
"epoch": 0.55,
"learning_rate": 1.884464543984504e-05,
"loss": 0.6465,
"step": 556
},
{
"epoch": 0.55,
"learning_rate": 1.8839672992666763e-05,
"loss": 0.6027,
"step": 557
},
{
"epoch": 0.55,
"learning_rate": 1.8834690527108847e-05,
"loss": 0.5763,
"step": 558
},
{
"epoch": 0.55,
"learning_rate": 1.8829698048818142e-05,
"loss": 0.5832,
"step": 559
},
{
"epoch": 0.55,
"learning_rate": 1.882469556345283e-05,
"loss": 0.519,
"step": 560
},
{
"epoch": 0.55,
"learning_rate": 1.8819683076682444e-05,
"loss": 0.5767,
"step": 561
},
{
"epoch": 0.55,
"learning_rate": 1.881466059418785e-05,
"loss": 0.6031,
"step": 562
},
{
"epoch": 0.55,
"learning_rate": 1.8809628121661247e-05,
"loss": 0.5468,
"step": 563
},
{
"epoch": 0.55,
"learning_rate": 1.8804585664806143e-05,
"loss": 0.7676,
"step": 564
},
{
"epoch": 0.56,
"learning_rate": 1.879953322933737e-05,
"loss": 0.5865,
"step": 565
},
{
"epoch": 0.56,
"learning_rate": 1.8794470820981083e-05,
"loss": 0.4952,
"step": 566
},
{
"epoch": 0.56,
"learning_rate": 1.878939844547471e-05,
"loss": 0.4852,
"step": 567
},
{
"epoch": 0.56,
"learning_rate": 1.8784316108566994e-05,
"loss": 0.6168,
"step": 568
},
{
"epoch": 0.56,
"learning_rate": 1.8779223816017973e-05,
"loss": 0.6529,
"step": 569
},
{
"epoch": 0.56,
"learning_rate": 1.8774121573598956e-05,
"loss": 0.6118,
"step": 570
},
{
"epoch": 0.56,
"learning_rate": 1.8769009387092533e-05,
"loss": 0.6778,
"step": 571
},
{
"epoch": 0.56,
"learning_rate": 1.8763887262292557e-05,
"loss": 0.646,
"step": 572
},
{
"epoch": 0.56,
"learning_rate": 1.875875520500416e-05,
"loss": 0.7043,
"step": 573
},
{
"epoch": 0.56,
"learning_rate": 1.8753613221043722e-05,
"loss": 0.5042,
"step": 574
},
{
"epoch": 0.56,
"learning_rate": 1.8748461316238865e-05,
"loss": 0.5699,
"step": 575
},
{
"epoch": 0.57,
"learning_rate": 1.874329949642847e-05,
"loss": 0.6755,
"step": 576
},
{
"epoch": 0.57,
"eval_loss": 0.6506475210189819,
"eval_runtime": 92.1181,
"eval_samples_per_second": 21.711,
"eval_steps_per_second": 10.856,
"step": 576
},
{
"epoch": 0.57,
"learning_rate": 1.873812776746265e-05,
"loss": 0.5427,
"step": 577
},
{
"epoch": 0.57,
"learning_rate": 1.873294613520274e-05,
"loss": 0.5481,
"step": 578
},
{
"epoch": 0.57,
"learning_rate": 1.8727754605521307e-05,
"loss": 0.4806,
"step": 579
},
{
"epoch": 0.57,
"learning_rate": 1.872255318430214e-05,
"loss": 0.4741,
"step": 580
},
{
"epoch": 0.57,
"learning_rate": 1.8717341877440227e-05,
"loss": 0.645,
"step": 581
},
{
"epoch": 0.57,
"learning_rate": 1.8712120690841767e-05,
"loss": 0.5871,
"step": 582
},
{
"epoch": 0.57,
"learning_rate": 1.870688963042415e-05,
"loss": 0.5273,
"step": 583
},
{
"epoch": 0.57,
"learning_rate": 1.8701648702115966e-05,
"loss": 0.7077,
"step": 584
},
{
"epoch": 0.57,
"learning_rate": 1.8696397911856983e-05,
"loss": 0.4775,
"step": 585
},
{
"epoch": 0.58,
"learning_rate": 1.8691137265598144e-05,
"loss": 0.6678,
"step": 586
},
{
"epoch": 0.58,
"learning_rate": 1.868586676930156e-05,
"loss": 0.5864,
"step": 587
},
{
"epoch": 0.58,
"learning_rate": 1.868058642894052e-05,
"loss": 0.593,
"step": 588
},
{
"epoch": 0.58,
"learning_rate": 1.8675296250499457e-05,
"loss": 0.5687,
"step": 589
},
{
"epoch": 0.58,
"learning_rate": 1.8669996239973946e-05,
"loss": 0.5601,
"step": 590
},
{
"epoch": 0.58,
"learning_rate": 1.866468640337073e-05,
"loss": 0.4729,
"step": 591
},
{
"epoch": 0.58,
"learning_rate": 1.8659366746707665e-05,
"loss": 0.7099,
"step": 592
},
{
"epoch": 0.58,
"learning_rate": 1.865403727601375e-05,
"loss": 0.5509,
"step": 593
},
{
"epoch": 0.58,
"learning_rate": 1.86486979973291e-05,
"loss": 0.5258,
"step": 594
},
{
"epoch": 0.58,
"learning_rate": 1.8643348916704947e-05,
"loss": 0.5296,
"step": 595
},
{
"epoch": 0.59,
"learning_rate": 1.863799004020364e-05,
"loss": 0.4981,
"step": 596
},
{
"epoch": 0.59,
"learning_rate": 1.863262137389861e-05,
"loss": 0.5171,
"step": 597
},
{
"epoch": 0.59,
"learning_rate": 1.862724292387441e-05,
"loss": 0.5145,
"step": 598
},
{
"epoch": 0.59,
"learning_rate": 1.862185469622666e-05,
"loss": 0.6257,
"step": 599
},
{
"epoch": 0.59,
"learning_rate": 1.8616456697062068e-05,
"loss": 0.6129,
"step": 600
},
{
"epoch": 0.59,
"learning_rate": 1.861104893249842e-05,
"loss": 0.5564,
"step": 601
},
{
"epoch": 0.59,
"learning_rate": 1.8605631408664566e-05,
"loss": 0.6742,
"step": 602
},
{
"epoch": 0.59,
"learning_rate": 1.860020413170042e-05,
"loss": 0.4616,
"step": 603
},
{
"epoch": 0.59,
"learning_rate": 1.8594767107756943e-05,
"loss": 0.5639,
"step": 604
},
{
"epoch": 0.59,
"learning_rate": 1.8589320342996153e-05,
"loss": 0.5221,
"step": 605
},
{
"epoch": 0.6,
"learning_rate": 1.8583863843591095e-05,
"loss": 0.5318,
"step": 606
},
{
"epoch": 0.6,
"learning_rate": 1.8578397615725857e-05,
"loss": 0.6984,
"step": 607
},
{
"epoch": 0.6,
"learning_rate": 1.857292166559555e-05,
"loss": 0.4811,
"step": 608
},
{
"epoch": 0.6,
"learning_rate": 1.8567435999406297e-05,
"loss": 0.6425,
"step": 609
},
{
"epoch": 0.6,
"learning_rate": 1.8561940623375245e-05,
"loss": 0.5415,
"step": 610
},
{
"epoch": 0.6,
"learning_rate": 1.8556435543730537e-05,
"loss": 0.564,
"step": 611
},
{
"epoch": 0.6,
"learning_rate": 1.855092076671131e-05,
"loss": 0.5067,
"step": 612
},
{
"epoch": 0.6,
"learning_rate": 1.85453962985677e-05,
"loss": 0.5384,
"step": 613
},
{
"epoch": 0.6,
"learning_rate": 1.8539862145560828e-05,
"loss": 0.5515,
"step": 614
},
{
"epoch": 0.6,
"learning_rate": 1.853431831396278e-05,
"loss": 0.4757,
"step": 615
},
{
"epoch": 0.61,
"learning_rate": 1.8528764810056618e-05,
"loss": 0.4996,
"step": 616
},
{
"epoch": 0.61,
"learning_rate": 1.8523201640136366e-05,
"loss": 0.4874,
"step": 617
},
{
"epoch": 0.61,
"learning_rate": 1.851762881050701e-05,
"loss": 0.5611,
"step": 618
},
{
"epoch": 0.61,
"learning_rate": 1.8512046327484466e-05,
"loss": 0.5846,
"step": 619
},
{
"epoch": 0.61,
"learning_rate": 1.8506454197395608e-05,
"loss": 0.5565,
"step": 620
},
{
"epoch": 0.61,
"learning_rate": 1.8500852426578233e-05,
"loss": 0.7008,
"step": 621
},
{
"epoch": 0.61,
"learning_rate": 1.8495241021381064e-05,
"loss": 0.6467,
"step": 622
},
{
"epoch": 0.61,
"learning_rate": 1.8489619988163756e-05,
"loss": 0.6444,
"step": 623
},
{
"epoch": 0.61,
"learning_rate": 1.8483989333296858e-05,
"loss": 0.5281,
"step": 624
},
{
"epoch": 0.61,
"learning_rate": 1.8478349063161834e-05,
"loss": 0.6119,
"step": 625
},
{
"epoch": 0.62,
"learning_rate": 1.8472699184151045e-05,
"loss": 0.4825,
"step": 626
},
{
"epoch": 0.62,
"learning_rate": 1.846703970266774e-05,
"loss": 0.5628,
"step": 627
},
{
"epoch": 0.62,
"learning_rate": 1.8461370625126053e-05,
"loss": 0.6054,
"step": 628
},
{
"epoch": 0.62,
"learning_rate": 1.8455691957950992e-05,
"loss": 0.4738,
"step": 629
},
{
"epoch": 0.62,
"learning_rate": 1.845000370757843e-05,
"loss": 0.545,
"step": 630
},
{
"epoch": 0.62,
"learning_rate": 1.8444305880455108e-05,
"loss": 0.648,
"step": 631
},
{
"epoch": 0.62,
"learning_rate": 1.8438598483038615e-05,
"loss": 0.517,
"step": 632
},
{
"epoch": 0.62,
"learning_rate": 1.843288152179739e-05,
"loss": 0.4683,
"step": 633
},
{
"epoch": 0.62,
"learning_rate": 1.842715500321071e-05,
"loss": 0.548,
"step": 634
},
{
"epoch": 0.62,
"learning_rate": 1.8421418933768683e-05,
"loss": 0.5073,
"step": 635
},
{
"epoch": 0.62,
"learning_rate": 1.8415673319972246e-05,
"loss": 0.6487,
"step": 636
},
{
"epoch": 0.63,
"learning_rate": 1.840991816833314e-05,
"loss": 0.4228,
"step": 637
},
{
"epoch": 0.63,
"learning_rate": 1.840415348537393e-05,
"loss": 0.5822,
"step": 638
},
{
"epoch": 0.63,
"learning_rate": 1.839837927762798e-05,
"loss": 0.765,
"step": 639
},
{
"epoch": 0.63,
"learning_rate": 1.8392595551639443e-05,
"loss": 0.543,
"step": 640
},
{
"epoch": 0.63,
"eval_loss": 0.647984504699707,
"eval_runtime": 92.14,
"eval_samples_per_second": 21.706,
"eval_steps_per_second": 10.853,
"step": 640
},
{
"epoch": 0.63,
"learning_rate": 1.8386802313963262e-05,
"loss": 0.5537,
"step": 641
},
{
"epoch": 0.63,
"learning_rate": 1.838099957116517e-05,
"loss": 0.4953,
"step": 642
},
{
"epoch": 0.63,
"learning_rate": 1.837518732982165e-05,
"loss": 0.6852,
"step": 643
},
{
"epoch": 0.63,
"learning_rate": 1.8369365596519973e-05,
"loss": 0.7302,
"step": 644
},
{
"epoch": 0.63,
"learning_rate": 1.836353437785816e-05,
"loss": 0.9249,
"step": 645
},
{
"epoch": 0.63,
"learning_rate": 1.8357693680444978e-05,
"loss": 0.718,
"step": 646
},
{
"epoch": 0.64,
"learning_rate": 1.8351843510899933e-05,
"loss": 0.5188,
"step": 647
},
{
"epoch": 0.64,
"learning_rate": 1.834598387585328e-05,
"loss": 0.587,
"step": 648
},
{
"epoch": 0.64,
"learning_rate": 1.8340114781945993e-05,
"loss": 0.4678,
"step": 649
},
{
"epoch": 0.64,
"learning_rate": 1.8334236235829764e-05,
"loss": 0.5868,
"step": 650
},
{
"epoch": 0.64,
"learning_rate": 1.8328348244167005e-05,
"loss": 0.4718,
"step": 651
},
{
"epoch": 0.64,
"learning_rate": 1.8322450813630826e-05,
"loss": 0.7199,
"step": 652
},
{
"epoch": 0.64,
"learning_rate": 1.831654395090504e-05,
"loss": 0.5938,
"step": 653
},
{
"epoch": 0.64,
"learning_rate": 1.8310627662684145e-05,
"loss": 0.6977,
"step": 654
},
{
"epoch": 0.64,
"learning_rate": 1.8304701955673322e-05,
"loss": 0.5145,
"step": 655
},
{
"epoch": 0.64,
"learning_rate": 1.829876683658843e-05,
"loss": 0.4831,
"step": 656
},
{
"epoch": 0.65,
"learning_rate": 1.8292822312155997e-05,
"loss": 0.5874,
"step": 657
},
{
"epoch": 0.65,
"learning_rate": 1.8286868389113202e-05,
"loss": 0.5856,
"step": 658
},
{
"epoch": 0.65,
"learning_rate": 1.8280905074207886e-05,
"loss": 0.604,
"step": 659
},
{
"epoch": 0.65,
"learning_rate": 1.827493237419852e-05,
"loss": 0.7056,
"step": 660
},
{
"epoch": 0.65,
"learning_rate": 1.826895029585423e-05,
"loss": 0.6135,
"step": 661
},
{
"epoch": 0.65,
"learning_rate": 1.8262958845954755e-05,
"loss": 0.5842,
"step": 662
},
{
"epoch": 0.65,
"learning_rate": 1.8256958031290464e-05,
"loss": 0.7325,
"step": 663
},
{
"epoch": 0.65,
"learning_rate": 1.8250947858662337e-05,
"loss": 0.5161,
"step": 664
},
{
"epoch": 0.65,
"learning_rate": 1.8244928334881962e-05,
"loss": 0.6334,
"step": 665
},
{
"epoch": 0.65,
"learning_rate": 1.823889946677152e-05,
"loss": 0.7439,
"step": 666
},
{
"epoch": 0.66,
"learning_rate": 1.8232861261163784e-05,
"loss": 0.5713,
"step": 667
},
{
"epoch": 0.66,
"learning_rate": 1.822681372490211e-05,
"loss": 0.5948,
"step": 668
},
{
"epoch": 0.66,
"learning_rate": 1.8220756864840436e-05,
"loss": 0.5961,
"step": 669
},
{
"epoch": 0.66,
"learning_rate": 1.8214690687843255e-05,
"loss": 0.6035,
"step": 670
},
{
"epoch": 0.66,
"learning_rate": 1.8208615200785628e-05,
"loss": 0.6535,
"step": 671
},
{
"epoch": 0.66,
"learning_rate": 1.8202530410553162e-05,
"loss": 0.6137,
"step": 672
},
{
"epoch": 0.66,
"learning_rate": 1.819643632404201e-05,
"loss": 0.6333,
"step": 673
},
{
"epoch": 0.66,
"learning_rate": 1.8190332948158868e-05,
"loss": 0.5746,
"step": 674
},
{
"epoch": 0.66,
"learning_rate": 1.818422028982094e-05,
"loss": 0.7497,
"step": 675
},
{
"epoch": 0.66,
"learning_rate": 1.8178098355955976e-05,
"loss": 0.5311,
"step": 676
},
{
"epoch": 0.67,
"learning_rate": 1.817196715350222e-05,
"loss": 0.6479,
"step": 677
},
{
"epoch": 0.67,
"learning_rate": 1.8165826689408423e-05,
"loss": 0.9289,
"step": 678
},
{
"epoch": 0.67,
"learning_rate": 1.815967697063384e-05,
"loss": 0.5473,
"step": 679
},
{
"epoch": 0.67,
"learning_rate": 1.8153518004148213e-05,
"loss": 0.888,
"step": 680
},
{
"epoch": 0.67,
"learning_rate": 1.8147349796931754e-05,
"loss": 0.5876,
"step": 681
},
{
"epoch": 0.67,
"learning_rate": 1.8141172355975163e-05,
"loss": 0.6277,
"step": 682
},
{
"epoch": 0.67,
"learning_rate": 1.8134985688279597e-05,
"loss": 0.6282,
"step": 683
},
{
"epoch": 0.67,
"learning_rate": 1.8128789800856666e-05,
"loss": 0.6552,
"step": 684
},
{
"epoch": 0.67,
"learning_rate": 1.8122584700728444e-05,
"loss": 0.6045,
"step": 685
},
{
"epoch": 0.67,
"learning_rate": 1.8116370394927424e-05,
"loss": 0.4967,
"step": 686
},
{
"epoch": 0.68,
"learning_rate": 1.8110146890496556e-05,
"loss": 0.7058,
"step": 687
},
{
"epoch": 0.68,
"learning_rate": 1.81039141944892e-05,
"loss": 0.5844,
"step": 688
},
{
"epoch": 0.68,
"learning_rate": 1.8097672313969135e-05,
"loss": 0.5261,
"step": 689
},
{
"epoch": 0.68,
"learning_rate": 1.8091421256010553e-05,
"loss": 0.5321,
"step": 690
},
{
"epoch": 0.68,
"learning_rate": 1.8085161027698046e-05,
"loss": 0.6195,
"step": 691
},
{
"epoch": 0.68,
"learning_rate": 1.8078891636126598e-05,
"loss": 0.7518,
"step": 692
},
{
"epoch": 0.68,
"learning_rate": 1.8072613088401575e-05,
"loss": 0.5663,
"step": 693
},
{
"epoch": 0.68,
"learning_rate": 1.8066325391638733e-05,
"loss": 0.7279,
"step": 694
},
{
"epoch": 0.68,
"learning_rate": 1.806002855296418e-05,
"loss": 0.5241,
"step": 695
},
{
"epoch": 0.68,
"learning_rate": 1.8053722579514396e-05,
"loss": 0.4786,
"step": 696
},
{
"epoch": 0.68,
"learning_rate": 1.8047407478436208e-05,
"loss": 0.6003,
"step": 697
},
{
"epoch": 0.69,
"learning_rate": 1.804108325688679e-05,
"loss": 0.6762,
"step": 698
},
{
"epoch": 0.69,
"learning_rate": 1.8034749922033655e-05,
"loss": 0.4717,
"step": 699
},
{
"epoch": 0.69,
"learning_rate": 1.8028407481054643e-05,
"loss": 0.6024,
"step": 700
},
{
"epoch": 0.69,
"learning_rate": 1.8022055941137916e-05,
"loss": 0.5751,
"step": 701
},
{
"epoch": 0.69,
"learning_rate": 1.8015695309481936e-05,
"loss": 0.4996,
"step": 702
},
{
"epoch": 0.69,
"learning_rate": 1.800932559329549e-05,
"loss": 0.5605,
"step": 703
},
{
"epoch": 0.69,
"learning_rate": 1.8002946799797646e-05,
"loss": 0.6652,
"step": 704
},
{
"epoch": 0.69,
"eval_loss": 0.64524245262146,
"eval_runtime": 92.1271,
"eval_samples_per_second": 21.709,
"eval_steps_per_second": 10.855,
"step": 704
},
{
"epoch": 0.69,
"learning_rate": 1.799655893621776e-05,
"loss": 0.5642,
"step": 705
},
{
"epoch": 0.69,
"learning_rate": 1.7990162009795477e-05,
"loss": 0.6293,
"step": 706
},
{
"epoch": 0.69,
"learning_rate": 1.7983756027780704e-05,
"loss": 0.5189,
"step": 707
},
{
"epoch": 0.7,
"learning_rate": 1.7977340997433616e-05,
"loss": 0.5823,
"step": 708
},
{
"epoch": 0.7,
"learning_rate": 1.797091692602464e-05,
"loss": 0.565,
"step": 709
},
{
"epoch": 0.7,
"learning_rate": 1.796448382083445e-05,
"loss": 0.5803,
"step": 710
},
{
"epoch": 0.7,
"learning_rate": 1.7958041689153963e-05,
"loss": 0.7027,
"step": 711
},
{
"epoch": 0.7,
"learning_rate": 1.795159053828432e-05,
"loss": 0.6501,
"step": 712
},
{
"epoch": 0.7,
"learning_rate": 1.7945130375536886e-05,
"loss": 0.5503,
"step": 713
},
{
"epoch": 0.7,
"learning_rate": 1.793866120823324e-05,
"loss": 0.7471,
"step": 714
},
{
"epoch": 0.7,
"learning_rate": 1.793218304370517e-05,
"loss": 0.5216,
"step": 715
},
{
"epoch": 0.7,
"learning_rate": 1.792569588929465e-05,
"loss": 0.6097,
"step": 716
},
{
"epoch": 0.7,
"learning_rate": 1.7919199752353854e-05,
"loss": 0.7207,
"step": 717
},
{
"epoch": 0.71,
"learning_rate": 1.7912694640245133e-05,
"loss": 0.6575,
"step": 718
},
{
"epoch": 0.71,
"learning_rate": 1.7906180560341006e-05,
"loss": 0.7072,
"step": 719
},
{
"epoch": 0.71,
"learning_rate": 1.789965752002416e-05,
"loss": 0.5954,
"step": 720
},
{
"epoch": 0.71,
"learning_rate": 1.789312552668744e-05,
"loss": 0.5912,
"step": 721
},
{
"epoch": 0.71,
"learning_rate": 1.7886584587733823e-05,
"loss": 0.4987,
"step": 722
},
{
"epoch": 0.71,
"learning_rate": 1.7880034710576442e-05,
"loss": 0.5835,
"step": 723
},
{
"epoch": 0.71,
"learning_rate": 1.7873475902638552e-05,
"loss": 0.7508,
"step": 724
},
{
"epoch": 0.71,
"learning_rate": 1.7866908171353534e-05,
"loss": 0.5608,
"step": 725
},
{
"epoch": 0.71,
"learning_rate": 1.7860331524164873e-05,
"loss": 0.7412,
"step": 726
},
{
"epoch": 0.71,
"learning_rate": 1.7853745968526167e-05,
"loss": 0.5486,
"step": 727
},
{
"epoch": 0.72,
"learning_rate": 1.784715151190111e-05,
"loss": 0.6936,
"step": 728
},
{
"epoch": 0.72,
"learning_rate": 1.7840548161763477e-05,
"loss": 0.4809,
"step": 729
},
{
"epoch": 0.72,
"learning_rate": 1.783393592559713e-05,
"loss": 0.7534,
"step": 730
},
{
"epoch": 0.72,
"learning_rate": 1.7827314810896004e-05,
"loss": 0.6164,
"step": 731
},
{
"epoch": 0.72,
"learning_rate": 1.7820684825164084e-05,
"loss": 0.6506,
"step": 732
},
{
"epoch": 0.72,
"learning_rate": 1.7814045975915423e-05,
"loss": 0.7288,
"step": 733
},
{
"epoch": 0.72,
"learning_rate": 1.7807398270674108e-05,
"loss": 0.7347,
"step": 734
},
{
"epoch": 0.72,
"learning_rate": 1.7800741716974266e-05,
"loss": 0.5629,
"step": 735
},
{
"epoch": 0.72,
"learning_rate": 1.7794076322360063e-05,
"loss": 0.5343,
"step": 736
},
{
"epoch": 0.72,
"learning_rate": 1.7787402094385665e-05,
"loss": 0.5308,
"step": 737
},
{
"epoch": 0.73,
"learning_rate": 1.778071904061527e-05,
"loss": 0.5779,
"step": 738
},
{
"epoch": 0.73,
"learning_rate": 1.7774027168623064e-05,
"loss": 0.4822,
"step": 739
},
{
"epoch": 0.73,
"learning_rate": 1.7767326485993227e-05,
"loss": 0.6662,
"step": 740
},
{
"epoch": 0.73,
"learning_rate": 1.776061700031994e-05,
"loss": 0.4451,
"step": 741
},
{
"epoch": 0.73,
"learning_rate": 1.775389871920734e-05,
"loss": 0.5796,
"step": 742
},
{
"epoch": 0.73,
"learning_rate": 1.774717165026955e-05,
"loss": 0.4812,
"step": 743
},
{
"epoch": 0.73,
"learning_rate": 1.7740435801130646e-05,
"loss": 0.5097,
"step": 744
},
{
"epoch": 0.73,
"learning_rate": 1.7733691179424646e-05,
"loss": 0.6361,
"step": 745
},
{
"epoch": 0.73,
"learning_rate": 1.7726937792795523e-05,
"loss": 0.4894,
"step": 746
},
{
"epoch": 0.73,
"learning_rate": 1.7720175648897177e-05,
"loss": 0.6488,
"step": 747
},
{
"epoch": 0.73,
"learning_rate": 1.771340475539344e-05,
"loss": 0.6022,
"step": 748
},
{
"epoch": 0.74,
"learning_rate": 1.7706625119958052e-05,
"loss": 0.5357,
"step": 749
},
{
"epoch": 0.74,
"learning_rate": 1.769983675027466e-05,
"loss": 0.6011,
"step": 750
},
{
"epoch": 0.74,
"learning_rate": 1.7693039654036824e-05,
"loss": 0.6854,
"step": 751
},
{
"epoch": 0.74,
"learning_rate": 1.7686233838947974e-05,
"loss": 0.6822,
"step": 752
},
{
"epoch": 0.74,
"learning_rate": 1.7679419312721434e-05,
"loss": 0.4995,
"step": 753
},
{
"epoch": 0.74,
"learning_rate": 1.76725960830804e-05,
"loss": 0.4755,
"step": 754
},
{
"epoch": 0.74,
"learning_rate": 1.766576415775793e-05,
"loss": 0.5371,
"step": 755
},
{
"epoch": 0.74,
"learning_rate": 1.7658923544496937e-05,
"loss": 0.5643,
"step": 756
},
{
"epoch": 0.74,
"learning_rate": 1.7652074251050183e-05,
"loss": 0.63,
"step": 757
},
{
"epoch": 0.74,
"learning_rate": 1.764521628518026e-05,
"loss": 0.5933,
"step": 758
},
{
"epoch": 0.75,
"learning_rate": 1.7638349654659596e-05,
"loss": 0.5993,
"step": 759
},
{
"epoch": 0.75,
"learning_rate": 1.763147436727044e-05,
"loss": 0.5606,
"step": 760
},
{
"epoch": 0.75,
"learning_rate": 1.7624590430804843e-05,
"loss": 0.5107,
"step": 761
},
{
"epoch": 0.75,
"learning_rate": 1.7617697853064677e-05,
"loss": 0.5984,
"step": 762
},
{
"epoch": 0.75,
"learning_rate": 1.7610796641861584e-05,
"loss": 0.5364,
"step": 763
},
{
"epoch": 0.75,
"learning_rate": 1.7603886805017004e-05,
"loss": 0.6252,
"step": 764
},
{
"epoch": 0.75,
"learning_rate": 1.7596968350362155e-05,
"loss": 0.4487,
"step": 765
},
{
"epoch": 0.75,
"learning_rate": 1.759004128573801e-05,
"loss": 0.5498,
"step": 766
},
{
"epoch": 0.75,
"learning_rate": 1.7583105618995318e-05,
"loss": 0.5785,
"step": 767
},
{
"epoch": 0.75,
"learning_rate": 1.7576161357994558e-05,
"loss": 0.5662,
"step": 768
},
{
"epoch": 0.75,
"eval_loss": 0.6423307657241821,
"eval_runtime": 92.1064,
"eval_samples_per_second": 21.714,
"eval_steps_per_second": 10.857,
"step": 768
},
{
"epoch": 0.76,
"learning_rate": 1.7569208510605965e-05,
"loss": 0.5083,
"step": 769
},
{
"epoch": 0.76,
"learning_rate": 1.7562247084709493e-05,
"loss": 0.6088,
"step": 770
},
{
"epoch": 0.76,
"learning_rate": 1.7555277088194827e-05,
"loss": 0.4787,
"step": 771
},
{
"epoch": 0.76,
"learning_rate": 1.754829852896136e-05,
"loss": 0.5777,
"step": 772
},
{
"epoch": 0.76,
"learning_rate": 1.7541311414918192e-05,
"loss": 0.5769,
"step": 773
},
{
"epoch": 0.76,
"learning_rate": 1.7534315753984125e-05,
"loss": 0.506,
"step": 774
},
{
"epoch": 0.76,
"learning_rate": 1.752731155408763e-05,
"loss": 0.5512,
"step": 775
},
{
"epoch": 0.76,
"learning_rate": 1.7520298823166873e-05,
"loss": 0.4389,
"step": 776
},
{
"epoch": 0.76,
"learning_rate": 1.751327756916968e-05,
"loss": 0.5408,
"step": 777
},
{
"epoch": 0.76,
"learning_rate": 1.750624780005354e-05,
"loss": 0.5699,
"step": 778
},
{
"epoch": 0.77,
"learning_rate": 1.7499209523785593e-05,
"loss": 0.5606,
"step": 779
},
{
"epoch": 0.77,
"learning_rate": 1.749216274834261e-05,
"loss": 0.5035,
"step": 780
},
{
"epoch": 0.77,
"learning_rate": 1.7485107481711014e-05,
"loss": 0.6086,
"step": 781
},
{
"epoch": 0.77,
"learning_rate": 1.747804373188683e-05,
"loss": 0.4745,
"step": 782
},
{
"epoch": 0.77,
"learning_rate": 1.747097150687572e-05,
"loss": 0.7503,
"step": 783
},
{
"epoch": 0.77,
"learning_rate": 1.746389081469293e-05,
"loss": 0.5023,
"step": 784
},
{
"epoch": 0.77,
"learning_rate": 1.7456801663363317e-05,
"loss": 0.5885,
"step": 785
},
{
"epoch": 0.77,
"learning_rate": 1.7449704060921314e-05,
"loss": 0.5762,
"step": 786
},
{
"epoch": 0.77,
"learning_rate": 1.744259801541094e-05,
"loss": 0.5614,
"step": 787
},
{
"epoch": 0.77,
"learning_rate": 1.743548353488578e-05,
"loss": 0.5225,
"step": 788
},
{
"epoch": 0.78,
"learning_rate": 1.742836062740898e-05,
"loss": 0.5162,
"step": 789
},
{
"epoch": 0.78,
"learning_rate": 1.742122930105324e-05,
"loss": 0.5628,
"step": 790
},
{
"epoch": 0.78,
"learning_rate": 1.741408956390079e-05,
"loss": 0.5347,
"step": 791
},
{
"epoch": 0.78,
"learning_rate": 1.7406941424043402e-05,
"loss": 0.5678,
"step": 792
},
{
"epoch": 0.78,
"learning_rate": 1.739978488958237e-05,
"loss": 0.6086,
"step": 793
},
{
"epoch": 0.78,
"learning_rate": 1.73926199686285e-05,
"loss": 0.7297,
"step": 794
},
{
"epoch": 0.78,
"learning_rate": 1.7385446669302105e-05,
"loss": 0.4721,
"step": 795
},
{
"epoch": 0.78,
"learning_rate": 1.737826499973299e-05,
"loss": 0.5605,
"step": 796
},
{
"epoch": 0.78,
"learning_rate": 1.737107496806045e-05,
"loss": 0.6494,
"step": 797
},
{
"epoch": 0.78,
"learning_rate": 1.7363876582433254e-05,
"loss": 0.5687,
"step": 798
},
{
"epoch": 0.79,
"learning_rate": 1.7356669851009636e-05,
"loss": 0.5405,
"step": 799
},
{
"epoch": 0.79,
"learning_rate": 1.7349454781957305e-05,
"loss": 0.4653,
"step": 800
},
{
"epoch": 0.79,
"learning_rate": 1.7342231383453397e-05,
"loss": 0.6261,
"step": 801
},
{
"epoch": 0.79,
"learning_rate": 1.7334999663684504e-05,
"loss": 0.6735,
"step": 802
},
{
"epoch": 0.79,
"learning_rate": 1.7327759630846644e-05,
"loss": 0.4555,
"step": 803
},
{
"epoch": 0.79,
"learning_rate": 1.7320511293145246e-05,
"loss": 0.5476,
"step": 804
},
{
"epoch": 0.79,
"learning_rate": 1.731325465879518e-05,
"loss": 0.5048,
"step": 805
},
{
"epoch": 0.79,
"learning_rate": 1.730598973602068e-05,
"loss": 0.5811,
"step": 806
},
{
"epoch": 0.79,
"learning_rate": 1.7298716533055406e-05,
"loss": 0.5615,
"step": 807
},
{
"epoch": 0.79,
"learning_rate": 1.729143505814239e-05,
"loss": 0.4507,
"step": 808
},
{
"epoch": 0.79,
"learning_rate": 1.728414531953403e-05,
"loss": 0.6074,
"step": 809
},
{
"epoch": 0.8,
"learning_rate": 1.727684732549211e-05,
"loss": 0.4515,
"step": 810
},
{
"epoch": 0.8,
"learning_rate": 1.726954108428775e-05,
"loss": 0.5392,
"step": 811
},
{
"epoch": 0.8,
"learning_rate": 1.7262226604201432e-05,
"loss": 0.5854,
"step": 812
},
{
"epoch": 0.8,
"learning_rate": 1.725490389352297e-05,
"loss": 0.6544,
"step": 813
},
{
"epoch": 0.8,
"learning_rate": 1.7247572960551497e-05,
"loss": 0.5857,
"step": 814
},
{
"epoch": 0.8,
"learning_rate": 1.724023381359548e-05,
"loss": 0.6065,
"step": 815
},
{
"epoch": 0.8,
"learning_rate": 1.7232886460972685e-05,
"loss": 0.7026,
"step": 816
},
{
"epoch": 0.8,
"learning_rate": 1.7225530911010184e-05,
"loss": 1.4322,
"step": 817
},
{
"epoch": 0.8,
"learning_rate": 1.721816717204433e-05,
"loss": 0.4124,
"step": 818
},
{
"epoch": 0.8,
"learning_rate": 1.7210795252420776e-05,
"loss": 0.6122,
"step": 819
},
{
"epoch": 0.81,
"learning_rate": 1.7203415160494427e-05,
"loss": 0.5791,
"step": 820
},
{
"epoch": 0.81,
"learning_rate": 1.7196026904629453e-05,
"loss": 0.5399,
"step": 821
},
{
"epoch": 0.81,
"learning_rate": 1.7188630493199284e-05,
"loss": 0.5382,
"step": 822
},
{
"epoch": 0.81,
"learning_rate": 1.7181225934586588e-05,
"loss": 0.5084,
"step": 823
},
{
"epoch": 0.81,
"learning_rate": 1.717381323718327e-05,
"loss": 0.4271,
"step": 824
},
{
"epoch": 0.81,
"learning_rate": 1.716639240939046e-05,
"loss": 0.5819,
"step": 825
},
{
"epoch": 0.81,
"learning_rate": 1.7158963459618493e-05,
"loss": 0.5319,
"step": 826
},
{
"epoch": 0.81,
"learning_rate": 1.715152639628692e-05,
"loss": 0.5007,
"step": 827
},
{
"epoch": 0.81,
"learning_rate": 1.7144081227824482e-05,
"loss": 0.5845,
"step": 828
},
{
"epoch": 0.81,
"learning_rate": 1.7136627962669104e-05,
"loss": 0.617,
"step": 829
},
{
"epoch": 0.82,
"learning_rate": 1.71291666092679e-05,
"loss": 0.6463,
"step": 830
},
{
"epoch": 0.82,
"learning_rate": 1.712169717607713e-05,
"loss": 0.5372,
"step": 831
},
{
"epoch": 0.82,
"learning_rate": 1.711421967156223e-05,
"loss": 0.5517,
"step": 832
},
{
"epoch": 0.82,
"eval_loss": 0.6399876475334167,
"eval_runtime": 92.1336,
"eval_samples_per_second": 21.708,
"eval_steps_per_second": 10.854,
"step": 832
},
{
"epoch": 0.82,
"learning_rate": 1.7106734104197768e-05,
"loss": 0.4906,
"step": 833
},
{
"epoch": 0.82,
"learning_rate": 1.7099240482467463e-05,
"loss": 0.6046,
"step": 834
},
{
"epoch": 0.82,
"learning_rate": 1.709173881486416e-05,
"loss": 0.5195,
"step": 835
},
{
"epoch": 0.82,
"learning_rate": 1.7084229109889813e-05,
"loss": 0.4765,
"step": 836
},
{
"epoch": 0.82,
"learning_rate": 1.70767113760555e-05,
"loss": 0.5676,
"step": 837
},
{
"epoch": 0.82,
"learning_rate": 1.706918562188138e-05,
"loss": 0.5957,
"step": 838
},
{
"epoch": 0.82,
"learning_rate": 1.706165185589672e-05,
"loss": 0.6872,
"step": 839
},
{
"epoch": 0.83,
"learning_rate": 1.705411008663986e-05,
"loss": 0.666,
"step": 840
},
{
"epoch": 0.83,
"learning_rate": 1.70465603226582e-05,
"loss": 0.5761,
"step": 841
},
{
"epoch": 0.83,
"learning_rate": 1.7039002572508227e-05,
"loss": 0.7386,
"step": 842
},
{
"epoch": 0.83,
"learning_rate": 1.7031436844755448e-05,
"loss": 0.5125,
"step": 843
},
{
"epoch": 0.83,
"learning_rate": 1.702386314797443e-05,
"loss": 0.6297,
"step": 844
},
{
"epoch": 0.83,
"learning_rate": 1.7016281490748768e-05,
"loss": 0.4903,
"step": 845
},
{
"epoch": 0.83,
"learning_rate": 1.7008691881671083e-05,
"loss": 0.5961,
"step": 846
},
{
"epoch": 0.83,
"learning_rate": 1.7001094329343e-05,
"loss": 0.6881,
"step": 847
},
{
"epoch": 0.83,
"learning_rate": 1.699348884237515e-05,
"loss": 0.4957,
"step": 848
},
{
"epoch": 0.83,
"learning_rate": 1.6985875429387155e-05,
"loss": 0.6217,
"step": 849
},
{
"epoch": 0.84,
"learning_rate": 1.6978254099007625e-05,
"loss": 0.8178,
"step": 850
},
{
"epoch": 0.84,
"learning_rate": 1.6970624859874138e-05,
"loss": 0.7296,
"step": 851
},
{
"epoch": 0.84,
"learning_rate": 1.696298772063324e-05,
"loss": 0.6073,
"step": 852
},
{
"epoch": 0.84,
"learning_rate": 1.6955342689940423e-05,
"loss": 0.4353,
"step": 853
},
{
"epoch": 0.84,
"learning_rate": 1.694768977646013e-05,
"loss": 0.5238,
"step": 854
},
{
"epoch": 0.84,
"learning_rate": 1.6940028988865735e-05,
"loss": 0.6831,
"step": 855
},
{
"epoch": 0.84,
"learning_rate": 1.693236033583954e-05,
"loss": 0.5718,
"step": 856
},
{
"epoch": 0.84,
"learning_rate": 1.6924683826072752e-05,
"loss": 0.5932,
"step": 857
},
{
"epoch": 0.84,
"learning_rate": 1.6916999468265487e-05,
"loss": 0.4794,
"step": 858
},
{
"epoch": 0.84,
"learning_rate": 1.6909307271126763e-05,
"loss": 0.4706,
"step": 859
},
{
"epoch": 0.85,
"learning_rate": 1.690160724337447e-05,
"loss": 0.809,
"step": 860
},
{
"epoch": 0.85,
"learning_rate": 1.6893899393735383e-05,
"loss": 0.5915,
"step": 861
},
{
"epoch": 0.85,
"learning_rate": 1.6886183730945138e-05,
"loss": 0.4905,
"step": 862
},
{
"epoch": 0.85,
"learning_rate": 1.6878460263748223e-05,
"loss": 0.5525,
"step": 863
},
{
"epoch": 0.85,
"learning_rate": 1.6870729000897977e-05,
"loss": 0.5855,
"step": 864
},
{
"epoch": 0.85,
"learning_rate": 1.6862989951156567e-05,
"loss": 0.5472,
"step": 865
},
{
"epoch": 0.85,
"learning_rate": 1.6855243123294992e-05,
"loss": 0.5132,
"step": 866
},
{
"epoch": 0.85,
"learning_rate": 1.684748852609306e-05,
"loss": 0.5063,
"step": 867
},
{
"epoch": 0.85,
"learning_rate": 1.6839726168339394e-05,
"loss": 0.5982,
"step": 868
},
{
"epoch": 0.85,
"learning_rate": 1.6831956058831402e-05,
"loss": 0.5756,
"step": 869
},
{
"epoch": 0.85,
"learning_rate": 1.6824178206375282e-05,
"loss": 0.5691,
"step": 870
},
{
"epoch": 0.86,
"learning_rate": 1.6816392619786007e-05,
"loss": 0.6367,
"step": 871
},
{
"epoch": 0.86,
"learning_rate": 1.6808599307887316e-05,
"loss": 0.4613,
"step": 872
},
{
"epoch": 0.86,
"learning_rate": 1.6800798279511702e-05,
"loss": 0.7304,
"step": 873
},
{
"epoch": 0.86,
"learning_rate": 1.6792989543500405e-05,
"loss": 0.5408,
"step": 874
},
{
"epoch": 0.86,
"learning_rate": 1.67851731087034e-05,
"loss": 0.7371,
"step": 875
},
{
"epoch": 0.86,
"learning_rate": 1.6777348983979385e-05,
"loss": 0.4902,
"step": 876
},
{
"epoch": 0.86,
"learning_rate": 1.676951717819578e-05,
"loss": 0.5557,
"step": 877
},
{
"epoch": 0.86,
"learning_rate": 1.67616777002287e-05,
"loss": 0.489,
"step": 878
},
{
"epoch": 0.86,
"learning_rate": 1.6753830558962962e-05,
"loss": 0.5915,
"step": 879
},
{
"epoch": 0.86,
"learning_rate": 1.6745975763292072e-05,
"loss": 0.5993,
"step": 880
},
{
"epoch": 0.87,
"learning_rate": 1.6738113322118197e-05,
"loss": 0.5586,
"step": 881
},
{
"epoch": 0.87,
"learning_rate": 1.6730243244352185e-05,
"loss": 0.6386,
"step": 882
},
{
"epoch": 0.87,
"learning_rate": 1.672236553891353e-05,
"loss": 0.6062,
"step": 883
},
{
"epoch": 0.87,
"learning_rate": 1.671448021473038e-05,
"loss": 0.4943,
"step": 884
},
{
"epoch": 0.87,
"learning_rate": 1.6706587280739494e-05,
"loss": 0.5276,
"step": 885
},
{
"epoch": 0.87,
"learning_rate": 1.6698686745886285e-05,
"loss": 0.4385,
"step": 886
},
{
"epoch": 0.87,
"learning_rate": 1.6690778619124763e-05,
"loss": 0.4777,
"step": 887
},
{
"epoch": 0.87,
"learning_rate": 1.6682862909417542e-05,
"loss": 0.5673,
"step": 888
},
{
"epoch": 0.87,
"learning_rate": 1.6674939625735844e-05,
"loss": 0.7413,
"step": 889
},
{
"epoch": 0.87,
"learning_rate": 1.666700877705946e-05,
"loss": 0.568,
"step": 890
},
{
"epoch": 0.88,
"learning_rate": 1.665907037237676e-05,
"loss": 0.5401,
"step": 891
},
{
"epoch": 0.88,
"learning_rate": 1.6651124420684676e-05,
"loss": 0.6113,
"step": 892
},
{
"epoch": 0.88,
"learning_rate": 1.66431709309887e-05,
"loss": 0.5278,
"step": 893
},
{
"epoch": 0.88,
"learning_rate": 1.6635209912302857e-05,
"loss": 0.4876,
"step": 894
},
{
"epoch": 0.88,
"learning_rate": 1.662724137364971e-05,
"loss": 0.7981,
"step": 895
},
{
"epoch": 0.88,
"learning_rate": 1.661926532406035e-05,
"loss": 0.449,
"step": 896
},
{
"epoch": 0.88,
"eval_loss": 0.6382502317428589,
"eval_runtime": 92.1364,
"eval_samples_per_second": 21.707,
"eval_steps_per_second": 10.853,
"step": 896
},
{
"epoch": 0.88,
"learning_rate": 1.6611281772574376e-05,
"loss": 0.5559,
"step": 897
},
{
"epoch": 0.88,
"learning_rate": 1.6603290728239883e-05,
"loss": 0.5803,
"step": 898
},
{
"epoch": 0.88,
"learning_rate": 1.6595292200113467e-05,
"loss": 0.8397,
"step": 899
},
{
"epoch": 0.88,
"learning_rate": 1.65872861972602e-05,
"loss": 0.5793,
"step": 900
},
{
"epoch": 0.89,
"learning_rate": 1.6579272728753628e-05,
"loss": 0.5363,
"step": 901
},
{
"epoch": 0.89,
"learning_rate": 1.6571251803675758e-05,
"loss": 0.5237,
"step": 902
},
{
"epoch": 0.89,
"learning_rate": 1.6563223431117046e-05,
"loss": 0.5121,
"step": 903
},
{
"epoch": 0.89,
"learning_rate": 1.6555187620176394e-05,
"loss": 0.4492,
"step": 904
},
{
"epoch": 0.89,
"learning_rate": 1.6547144379961128e-05,
"loss": 0.4857,
"step": 905
},
{
"epoch": 0.89,
"learning_rate": 1.6539093719586998e-05,
"loss": 0.6915,
"step": 906
},
{
"epoch": 0.89,
"learning_rate": 1.6531035648178157e-05,
"loss": 0.5871,
"step": 907
},
{
"epoch": 0.89,
"learning_rate": 1.6522970174867166e-05,
"loss": 0.4624,
"step": 908
},
{
"epoch": 0.89,
"learning_rate": 1.6514897308794973e-05,
"loss": 0.5587,
"step": 909
},
{
"epoch": 0.89,
"learning_rate": 1.6506817059110898e-05,
"loss": 0.6931,
"step": 910
},
{
"epoch": 0.9,
"learning_rate": 1.6498729434972636e-05,
"loss": 0.5383,
"step": 911
},
{
"epoch": 0.9,
"learning_rate": 1.649063444554624e-05,
"loss": 0.458,
"step": 912
},
{
"epoch": 0.9,
"learning_rate": 1.64825321000061e-05,
"loss": 0.538,
"step": 913
},
{
"epoch": 0.9,
"learning_rate": 1.6474422407534964e-05,
"loss": 0.6022,
"step": 914
},
{
"epoch": 0.9,
"learning_rate": 1.6466305377323876e-05,
"loss": 0.7523,
"step": 915
},
{
"epoch": 0.9,
"learning_rate": 1.645818101857223e-05,
"loss": 0.7106,
"step": 916
},
{
"epoch": 0.9,
"learning_rate": 1.64500493404877e-05,
"loss": 0.5367,
"step": 917
},
{
"epoch": 0.9,
"learning_rate": 1.6441910352286264e-05,
"loss": 0.6779,
"step": 918
},
{
"epoch": 0.9,
"learning_rate": 1.6433764063192195e-05,
"loss": 0.3973,
"step": 919
},
{
"epoch": 0.9,
"learning_rate": 1.642561048243802e-05,
"loss": 0.5079,
"step": 920
},
{
"epoch": 0.9,
"learning_rate": 1.641744961926455e-05,
"loss": 0.5427,
"step": 921
},
{
"epoch": 0.91,
"learning_rate": 1.6409281482920833e-05,
"loss": 0.6709,
"step": 922
},
{
"epoch": 0.91,
"learning_rate": 1.6401106082664172e-05,
"loss": 0.5958,
"step": 923
},
{
"epoch": 0.91,
"learning_rate": 1.63929234277601e-05,
"loss": 0.6822,
"step": 924
},
{
"epoch": 0.91,
"learning_rate": 1.638473352748236e-05,
"loss": 0.4728,
"step": 925
},
{
"epoch": 0.91,
"learning_rate": 1.6376536391112927e-05,
"loss": 0.5049,
"step": 926
},
{
"epoch": 0.91,
"learning_rate": 1.636833202794196e-05,
"loss": 0.556,
"step": 927
},
{
"epoch": 0.91,
"learning_rate": 1.636012044726782e-05,
"loss": 0.5341,
"step": 928
},
{
"epoch": 0.91,
"learning_rate": 1.6351901658397037e-05,
"loss": 0.6881,
"step": 929
},
{
"epoch": 0.91,
"learning_rate": 1.6343675670644322e-05,
"loss": 0.5809,
"step": 930
},
{
"epoch": 0.91,
"learning_rate": 1.6335442493332535e-05,
"loss": 0.5832,
"step": 931
},
{
"epoch": 0.92,
"learning_rate": 1.6327202135792687e-05,
"loss": 0.498,
"step": 932
},
{
"epoch": 0.92,
"learning_rate": 1.631895460736393e-05,
"loss": 0.5114,
"step": 933
},
{
"epoch": 0.92,
"learning_rate": 1.6310699917393538e-05,
"loss": 0.6849,
"step": 934
},
{
"epoch": 0.92,
"learning_rate": 1.630243807523691e-05,
"loss": 0.5395,
"step": 935
},
{
"epoch": 0.92,
"learning_rate": 1.6294169090257543e-05,
"loss": 0.5941,
"step": 936
},
{
"epoch": 0.92,
"learning_rate": 1.6285892971827034e-05,
"loss": 0.5236,
"step": 937
},
{
"epoch": 0.92,
"learning_rate": 1.6277609729325054e-05,
"loss": 0.4999,
"step": 938
},
{
"epoch": 0.92,
"learning_rate": 1.6269319372139357e-05,
"loss": 0.6664,
"step": 939
},
{
"epoch": 0.92,
"learning_rate": 1.6261021909665772e-05,
"loss": 0.6276,
"step": 940
},
{
"epoch": 0.92,
"learning_rate": 1.6252717351308156e-05,
"loss": 0.5642,
"step": 941
},
{
"epoch": 0.93,
"learning_rate": 1.6244405706478425e-05,
"loss": 0.8156,
"step": 942
},
{
"epoch": 0.93,
"learning_rate": 1.6236086984596516e-05,
"loss": 0.6022,
"step": 943
},
{
"epoch": 0.93,
"learning_rate": 1.6227761195090404e-05,
"loss": 0.6605,
"step": 944
},
{
"epoch": 0.93,
"learning_rate": 1.6219428347396055e-05,
"loss": 0.5739,
"step": 945
},
{
"epoch": 0.93,
"learning_rate": 1.6211088450957436e-05,
"loss": 0.4745,
"step": 946
},
{
"epoch": 0.93,
"learning_rate": 1.6202741515226522e-05,
"loss": 0.6358,
"step": 947
},
{
"epoch": 0.93,
"learning_rate": 1.619438754966324e-05,
"loss": 0.4981,
"step": 948
},
{
"epoch": 0.93,
"learning_rate": 1.618602656373551e-05,
"loss": 0.5242,
"step": 949
},
{
"epoch": 0.93,
"learning_rate": 1.617765856691918e-05,
"loss": 0.6705,
"step": 950
},
{
"epoch": 0.93,
"learning_rate": 1.6169283568698068e-05,
"loss": 0.5556,
"step": 951
},
{
"epoch": 0.94,
"learning_rate": 1.6160901578563916e-05,
"loss": 0.5363,
"step": 952
},
{
"epoch": 0.94,
"learning_rate": 1.6152512606016394e-05,
"loss": 0.5554,
"step": 953
},
{
"epoch": 0.94,
"learning_rate": 1.6144116660563076e-05,
"loss": 0.5712,
"step": 954
},
{
"epoch": 0.94,
"learning_rate": 1.6135713751719454e-05,
"loss": 0.524,
"step": 955
},
{
"epoch": 0.94,
"learning_rate": 1.6127303889008907e-05,
"loss": 0.5764,
"step": 956
},
{
"epoch": 0.94,
"learning_rate": 1.6118887081962683e-05,
"loss": 0.5153,
"step": 957
},
{
"epoch": 0.94,
"learning_rate": 1.6110463340119917e-05,
"loss": 0.5185,
"step": 958
},
{
"epoch": 0.94,
"learning_rate": 1.6102032673027586e-05,
"loss": 0.5831,
"step": 959
},
{
"epoch": 0.94,
"learning_rate": 1.6093595090240536e-05,
"loss": 0.595,
"step": 960
},
{
"epoch": 0.94,
"eval_loss": 0.6362167596817017,
"eval_runtime": 92.1251,
"eval_samples_per_second": 21.71,
"eval_steps_per_second": 10.855,
"step": 960
},
{
"epoch": 0.94,
"learning_rate": 1.608515060132144e-05,
"loss": 0.6489,
"step": 961
},
{
"epoch": 0.95,
"learning_rate": 1.607669921584079e-05,
"loss": 0.5969,
"step": 962
},
{
"epoch": 0.95,
"learning_rate": 1.606824094337691e-05,
"loss": 0.5507,
"step": 963
},
{
"epoch": 0.95,
"learning_rate": 1.6059775793515925e-05,
"loss": 0.5265,
"step": 964
},
{
"epoch": 0.95,
"learning_rate": 1.6051303775851742e-05,
"loss": 0.4696,
"step": 965
},
{
"epoch": 0.95,
"learning_rate": 1.6042824899986066e-05,
"loss": 0.452,
"step": 966
},
{
"epoch": 0.95,
"learning_rate": 1.6034339175528374e-05,
"loss": 0.6304,
"step": 967
},
{
"epoch": 0.95,
"learning_rate": 1.6025846612095895e-05,
"loss": 0.6278,
"step": 968
},
{
"epoch": 0.95,
"learning_rate": 1.6017347219313613e-05,
"loss": 0.5339,
"step": 969
},
{
"epoch": 0.95,
"learning_rate": 1.6008841006814265e-05,
"loss": 0.6104,
"step": 970
},
{
"epoch": 0.95,
"learning_rate": 1.6000327984238292e-05,
"loss": 0.6284,
"step": 971
},
{
"epoch": 0.96,
"learning_rate": 1.5991808161233874e-05,
"loss": 0.6261,
"step": 972
},
{
"epoch": 0.96,
"learning_rate": 1.5983281547456884e-05,
"loss": 0.4593,
"step": 973
},
{
"epoch": 0.96,
"learning_rate": 1.5974748152570908e-05,
"loss": 0.6288,
"step": 974
},
{
"epoch": 0.96,
"learning_rate": 1.59662079862472e-05,
"loss": 0.5832,
"step": 975
},
{
"epoch": 0.96,
"learning_rate": 1.5957661058164697e-05,
"loss": 0.5963,
"step": 976
},
{
"epoch": 0.96,
"learning_rate": 1.5949107378010003e-05,
"loss": 0.4953,
"step": 977
},
{
"epoch": 0.96,
"learning_rate": 1.5940546955477366e-05,
"loss": 0.5905,
"step": 978
},
{
"epoch": 0.96,
"learning_rate": 1.5931979800268684e-05,
"loss": 0.5401,
"step": 979
},
{
"epoch": 0.96,
"learning_rate": 1.592340592209347e-05,
"loss": 0.7311,
"step": 980
},
{
"epoch": 0.96,
"learning_rate": 1.5914825330668876e-05,
"loss": 0.716,
"step": 981
},
{
"epoch": 0.96,
"learning_rate": 1.590623803571965e-05,
"loss": 0.5851,
"step": 982
},
{
"epoch": 0.97,
"learning_rate": 1.5897644046978143e-05,
"loss": 0.4605,
"step": 983
},
{
"epoch": 0.97,
"learning_rate": 1.5889043374184286e-05,
"loss": 0.5157,
"step": 984
},
{
"epoch": 0.97,
"learning_rate": 1.5880436027085596e-05,
"loss": 0.7261,
"step": 985
},
{
"epoch": 0.97,
"learning_rate": 1.5871822015437145e-05,
"loss": 0.3944,
"step": 986
},
{
"epoch": 0.97,
"learning_rate": 1.5863201349001556e-05,
"loss": 0.4487,
"step": 987
},
{
"epoch": 0.97,
"learning_rate": 1.5854574037549006e-05,
"loss": 0.3894,
"step": 988
},
{
"epoch": 0.97,
"learning_rate": 1.5845940090857192e-05,
"loss": 0.4336,
"step": 989
},
{
"epoch": 0.97,
"learning_rate": 1.5837299518711334e-05,
"loss": 0.6209,
"step": 990
},
{
"epoch": 0.97,
"learning_rate": 1.582865233090417e-05,
"loss": 0.5264,
"step": 991
},
{
"epoch": 0.97,
"learning_rate": 1.5819998537235918e-05,
"loss": 0.436,
"step": 992
},
{
"epoch": 0.98,
"learning_rate": 1.58113381475143e-05,
"loss": 0.5235,
"step": 993
},
{
"epoch": 0.98,
"learning_rate": 1.58026711715545e-05,
"loss": 0.5615,
"step": 994
},
{
"epoch": 0.98,
"learning_rate": 1.5793997619179184e-05,
"loss": 0.6318,
"step": 995
},
{
"epoch": 0.98,
"learning_rate": 1.5785317500218444e-05,
"loss": 0.5864,
"step": 996
},
{
"epoch": 0.98,
"learning_rate": 1.5776630824509843e-05,
"loss": 0.555,
"step": 997
},
{
"epoch": 0.98,
"learning_rate": 1.5767937601898356e-05,
"loss": 0.4748,
"step": 998
},
{
"epoch": 0.98,
"learning_rate": 1.575923784223638e-05,
"loss": 0.7556,
"step": 999
},
{
"epoch": 0.98,
"learning_rate": 1.575053155538374e-05,
"loss": 0.4632,
"step": 1000
},
{
"epoch": 0.98,
"learning_rate": 1.574181875120763e-05,
"loss": 0.6794,
"step": 1001
},
{
"epoch": 0.98,
"learning_rate": 1.573309943958265e-05,
"loss": 0.6157,
"step": 1002
},
{
"epoch": 0.99,
"learning_rate": 1.5724373630390767e-05,
"loss": 0.6646,
"step": 1003
},
{
"epoch": 0.99,
"learning_rate": 1.571564133352131e-05,
"loss": 0.7129,
"step": 1004
},
{
"epoch": 0.99,
"learning_rate": 1.5706902558870972e-05,
"loss": 0.5768,
"step": 1005
},
{
"epoch": 0.99,
"learning_rate": 1.5698157316343774e-05,
"loss": 0.693,
"step": 1006
},
{
"epoch": 0.99,
"learning_rate": 1.568940561585108e-05,
"loss": 0.5689,
"step": 1007
},
{
"epoch": 0.99,
"learning_rate": 1.568064746731156e-05,
"loss": 0.5122,
"step": 1008
},
{
"epoch": 0.99,
"learning_rate": 1.5671882880651203e-05,
"loss": 0.6655,
"step": 1009
},
{
"epoch": 0.99,
"learning_rate": 1.5663111865803285e-05,
"loss": 0.5886,
"step": 1010
},
{
"epoch": 0.99,
"learning_rate": 1.565433443270838e-05,
"loss": 0.5732,
"step": 1011
},
{
"epoch": 0.99,
"learning_rate": 1.5645550591314322e-05,
"loss": 0.6283,
"step": 1012
},
{
"epoch": 1.0,
"learning_rate": 1.5636760351576217e-05,
"loss": 0.4339,
"step": 1013
},
{
"epoch": 1.0,
"learning_rate": 1.562796372345642e-05,
"loss": 0.5992,
"step": 1014
},
{
"epoch": 1.0,
"learning_rate": 1.5619160716924528e-05,
"loss": 0.7873,
"step": 1015
},
{
"epoch": 1.0,
"learning_rate": 1.561035134195736e-05,
"loss": 0.5134,
"step": 1016
},
{
"epoch": 1.0,
"learning_rate": 1.5601535608538958e-05,
"loss": 0.4752,
"step": 1017
},
{
"epoch": 1.0,
"learning_rate": 1.5592713526660573e-05,
"loss": 0.6139,
"step": 1018
},
{
"epoch": 1.0,
"learning_rate": 1.558388510632065e-05,
"loss": 0.4426,
"step": 1019
},
{
"epoch": 1.0,
"learning_rate": 1.5575050357524807e-05,
"loss": 0.4197,
"step": 1020
},
{
"epoch": 1.0,
"learning_rate": 1.5566209290285853e-05,
"loss": 0.4283,
"step": 1021
},
{
"epoch": 1.0,
"learning_rate": 1.555736191462374e-05,
"loss": 0.5645,
"step": 1022
},
{
"epoch": 1.01,
"learning_rate": 1.5548508240565584e-05,
"loss": 0.5181,
"step": 1023
},
{
"epoch": 1.01,
"learning_rate": 1.5539648278145624e-05,
"loss": 0.4402,
"step": 1024
},
{
"epoch": 1.01,
"eval_loss": 0.6378227472305298,
"eval_runtime": 92.1443,
"eval_samples_per_second": 21.705,
"eval_steps_per_second": 10.853,
"step": 1024
},
{
"epoch": 1.01,
"learning_rate": 1.5530782037405244e-05,
"loss": 0.4189,
"step": 1025
},
{
"epoch": 1.01,
"learning_rate": 1.5521909528392928e-05,
"loss": 0.5989,
"step": 1026
},
{
"epoch": 1.01,
"learning_rate": 1.551303076116427e-05,
"loss": 0.4853,
"step": 1027
},
{
"epoch": 1.01,
"learning_rate": 1.5504145745781962e-05,
"loss": 0.5463,
"step": 1028
},
{
"epoch": 1.01,
"learning_rate": 1.5495254492315764e-05,
"loss": 0.4867,
"step": 1029
},
{
"epoch": 1.01,
"learning_rate": 1.548635701084252e-05,
"loss": 0.5638,
"step": 1030
},
{
"epoch": 1.01,
"learning_rate": 1.5477453311446127e-05,
"loss": 0.7157,
"step": 1031
},
{
"epoch": 1.01,
"learning_rate": 1.5468543404217526e-05,
"loss": 0.3872,
"step": 1032
},
{
"epoch": 1.01,
"learning_rate": 1.5459627299254695e-05,
"loss": 0.452,
"step": 1033
},
{
"epoch": 1.02,
"learning_rate": 1.545070500666264e-05,
"loss": 0.7096,
"step": 1034
},
{
"epoch": 1.02,
"learning_rate": 1.5441776536553376e-05,
"loss": 0.4872,
"step": 1035
},
{
"epoch": 1.02,
"learning_rate": 1.543284189904592e-05,
"loss": 0.4081,
"step": 1036
},
{
"epoch": 1.02,
"learning_rate": 1.5423901104266275e-05,
"loss": 0.3912,
"step": 1037
},
{
"epoch": 1.02,
"learning_rate": 1.5414954162347435e-05,
"loss": 0.454,
"step": 1038
},
{
"epoch": 1.02,
"learning_rate": 1.5406001083429348e-05,
"loss": 0.5008,
"step": 1039
},
{
"epoch": 1.02,
"learning_rate": 1.539704187765892e-05,
"loss": 0.4822,
"step": 1040
},
{
"epoch": 1.02,
"learning_rate": 1.5388076555190002e-05,
"loss": 0.4635,
"step": 1041
},
{
"epoch": 1.02,
"learning_rate": 1.537910512618338e-05,
"loss": 0.482,
"step": 1042
},
{
"epoch": 1.02,
"learning_rate": 1.5370127600806752e-05,
"loss": 0.5151,
"step": 1043
},
{
"epoch": 1.03,
"learning_rate": 1.5361143989234745e-05,
"loss": 0.4532,
"step": 1044
},
{
"epoch": 1.03,
"learning_rate": 1.5352154301648855e-05,
"loss": 0.6225,
"step": 1045
},
{
"epoch": 1.03,
"learning_rate": 1.534315854823749e-05,
"loss": 0.4333,
"step": 1046
},
{
"epoch": 1.03,
"learning_rate": 1.5334156739195915e-05,
"loss": 0.3975,
"step": 1047
},
{
"epoch": 1.03,
"learning_rate": 1.5325148884726274e-05,
"loss": 0.4248,
"step": 1048
},
{
"epoch": 1.03,
"learning_rate": 1.5316134995037545e-05,
"loss": 0.414,
"step": 1049
},
{
"epoch": 1.03,
"learning_rate": 1.5307115080345563e-05,
"loss": 0.422,
"step": 1050
},
{
"epoch": 1.03,
"learning_rate": 1.529808915087298e-05,
"loss": 0.6175,
"step": 1051
},
{
"epoch": 1.03,
"learning_rate": 1.5289057216849262e-05,
"loss": 0.5117,
"step": 1052
},
{
"epoch": 1.03,
"learning_rate": 1.5280019288510696e-05,
"loss": 0.4267,
"step": 1053
},
{
"epoch": 1.04,
"learning_rate": 1.5270975376100343e-05,
"loss": 0.5055,
"step": 1054
},
{
"epoch": 1.04,
"learning_rate": 1.5261925489868066e-05,
"loss": 0.4266,
"step": 1055
},
{
"epoch": 1.04,
"learning_rate": 1.5252869640070485e-05,
"loss": 0.4732,
"step": 1056
},
{
"epoch": 1.04,
"learning_rate": 1.5243807836970979e-05,
"loss": 0.4444,
"step": 1057
},
{
"epoch": 1.04,
"learning_rate": 1.5234740090839677e-05,
"loss": 0.3987,
"step": 1058
},
{
"epoch": 1.04,
"learning_rate": 1.5225666411953448e-05,
"loss": 0.4704,
"step": 1059
},
{
"epoch": 1.04,
"learning_rate": 1.521658681059588e-05,
"loss": 0.5186,
"step": 1060
},
{
"epoch": 1.04,
"learning_rate": 1.5207501297057268e-05,
"loss": 0.3647,
"step": 1061
},
{
"epoch": 1.04,
"learning_rate": 1.5198409881634617e-05,
"loss": 0.481,
"step": 1062
},
{
"epoch": 1.04,
"learning_rate": 1.5189312574631619e-05,
"loss": 0.5223,
"step": 1063
},
{
"epoch": 1.05,
"learning_rate": 1.5180209386358641e-05,
"loss": 0.3982,
"step": 1064
},
{
"epoch": 1.05,
"learning_rate": 1.5171100327132711e-05,
"loss": 0.446,
"step": 1065
},
{
"epoch": 1.05,
"learning_rate": 1.5161985407277523e-05,
"loss": 0.4345,
"step": 1066
},
{
"epoch": 1.05,
"learning_rate": 1.5152864637123397e-05,
"loss": 0.5752,
"step": 1067
},
{
"epoch": 1.05,
"learning_rate": 1.5143738027007298e-05,
"loss": 0.4616,
"step": 1068
},
{
"epoch": 1.05,
"learning_rate": 1.5134605587272804e-05,
"loss": 0.4701,
"step": 1069
},
{
"epoch": 1.05,
"learning_rate": 1.5125467328270098e-05,
"loss": 0.5689,
"step": 1070
},
{
"epoch": 1.05,
"learning_rate": 1.5116323260355957e-05,
"loss": 0.5106,
"step": 1071
},
{
"epoch": 1.05,
"learning_rate": 1.510717339389375e-05,
"loss": 0.4945,
"step": 1072
},
{
"epoch": 1.05,
"learning_rate": 1.5098017739253407e-05,
"loss": 0.5133,
"step": 1073
},
{
"epoch": 1.06,
"learning_rate": 1.5088856306811432e-05,
"loss": 0.4423,
"step": 1074
},
{
"epoch": 1.06,
"learning_rate": 1.5079689106950855e-05,
"loss": 0.6219,
"step": 1075
},
{
"epoch": 1.06,
"learning_rate": 1.5070516150061268e-05,
"loss": 0.5647,
"step": 1076
},
{
"epoch": 1.06,
"learning_rate": 1.5061337446538767e-05,
"loss": 0.4028,
"step": 1077
},
{
"epoch": 1.06,
"learning_rate": 1.5052153006785977e-05,
"loss": 0.4511,
"step": 1078
},
{
"epoch": 1.06,
"learning_rate": 1.5042962841212007e-05,
"loss": 0.4372,
"step": 1079
},
{
"epoch": 1.06,
"learning_rate": 1.5033766960232474e-05,
"loss": 0.4829,
"step": 1080
},
{
"epoch": 1.06,
"learning_rate": 1.5024565374269462e-05,
"loss": 0.6102,
"step": 1081
},
{
"epoch": 1.06,
"learning_rate": 1.5015358093751514e-05,
"loss": 0.4247,
"step": 1082
},
{
"epoch": 1.06,
"learning_rate": 1.5006145129113645e-05,
"loss": 0.6118,
"step": 1083
},
{
"epoch": 1.07,
"learning_rate": 1.4996926490797297e-05,
"loss": 0.4613,
"step": 1084
},
{
"epoch": 1.07,
"learning_rate": 1.498770218925035e-05,
"loss": 0.439,
"step": 1085
},
{
"epoch": 1.07,
"learning_rate": 1.4978472234927094e-05,
"loss": 0.423,
"step": 1086
},
{
"epoch": 1.07,
"learning_rate": 1.4969236638288238e-05,
"loss": 0.3737,
"step": 1087
},
{
"epoch": 1.07,
"learning_rate": 1.4959995409800874e-05,
"loss": 0.5562,
"step": 1088
},
{
"epoch": 1.07,
"eval_loss": 0.6433264017105103,
"eval_runtime": 92.1623,
"eval_samples_per_second": 21.701,
"eval_steps_per_second": 10.85,
"step": 1088
},
{
"epoch": 1.07,
"learning_rate": 1.4950748559938484e-05,
"loss": 0.4299,
"step": 1089
},
{
"epoch": 1.07,
"learning_rate": 1.4941496099180919e-05,
"loss": 0.5709,
"step": 1090
},
{
"epoch": 1.07,
"learning_rate": 1.4932238038014388e-05,
"loss": 0.5344,
"step": 1091
},
{
"epoch": 1.07,
"learning_rate": 1.4922974386931445e-05,
"loss": 0.5739,
"step": 1092
},
{
"epoch": 1.07,
"learning_rate": 1.4913705156430986e-05,
"loss": 0.4344,
"step": 1093
},
{
"epoch": 1.07,
"learning_rate": 1.4904430357018225e-05,
"loss": 0.443,
"step": 1094
},
{
"epoch": 1.08,
"learning_rate": 1.4895149999204693e-05,
"loss": 0.459,
"step": 1095
},
{
"epoch": 1.08,
"learning_rate": 1.4885864093508208e-05,
"loss": 0.4837,
"step": 1096
},
{
"epoch": 1.08,
"learning_rate": 1.487657265045289e-05,
"loss": 0.4837,
"step": 1097
},
{
"epoch": 1.08,
"learning_rate": 1.4867275680569129e-05,
"loss": 0.5251,
"step": 1098
},
{
"epoch": 1.08,
"learning_rate": 1.485797319439358e-05,
"loss": 0.5383,
"step": 1099
},
{
"epoch": 1.08,
"learning_rate": 1.4848665202469143e-05,
"loss": 0.4655,
"step": 1100
},
{
"epoch": 1.08,
"learning_rate": 1.4839351715344967e-05,
"loss": 0.3662,
"step": 1101
},
{
"epoch": 1.08,
"learning_rate": 1.4830032743576427e-05,
"loss": 0.5284,
"step": 1102
},
{
"epoch": 1.08,
"learning_rate": 1.482070829772511e-05,
"loss": 0.4343,
"step": 1103
},
{
"epoch": 1.08,
"learning_rate": 1.4811378388358814e-05,
"loss": 0.4714,
"step": 1104
},
{
"epoch": 1.09,
"learning_rate": 1.4802043026051516e-05,
"loss": 0.4371,
"step": 1105
},
{
"epoch": 1.09,
"learning_rate": 1.4792702221383391e-05,
"loss": 0.5693,
"step": 1106
},
{
"epoch": 1.09,
"learning_rate": 1.4783355984940767e-05,
"loss": 0.4272,
"step": 1107
},
{
"epoch": 1.09,
"learning_rate": 1.4774004327316132e-05,
"loss": 0.4351,
"step": 1108
},
{
"epoch": 1.09,
"learning_rate": 1.4764647259108122e-05,
"loss": 0.4312,
"step": 1109
},
{
"epoch": 1.09,
"learning_rate": 1.4755284790921504e-05,
"loss": 0.6222,
"step": 1110
},
{
"epoch": 1.09,
"learning_rate": 1.4745916933367166e-05,
"loss": 0.4985,
"step": 1111
},
{
"epoch": 1.09,
"learning_rate": 1.4736543697062096e-05,
"loss": 0.4285,
"step": 1112
},
{
"epoch": 1.09,
"learning_rate": 1.4727165092629388e-05,
"loss": 0.4628,
"step": 1113
},
{
"epoch": 1.09,
"learning_rate": 1.4717781130698212e-05,
"loss": 0.583,
"step": 1114
},
{
"epoch": 1.1,
"learning_rate": 1.4708391821903818e-05,
"loss": 0.4176,
"step": 1115
},
{
"epoch": 1.1,
"learning_rate": 1.4698997176887511e-05,
"loss": 0.5004,
"step": 1116
},
{
"epoch": 1.1,
"learning_rate": 1.468959720629664e-05,
"loss": 0.4816,
"step": 1117
},
{
"epoch": 1.1,
"learning_rate": 1.4680191920784595e-05,
"loss": 0.4627,
"step": 1118
},
{
"epoch": 1.1,
"learning_rate": 1.467078133101079e-05,
"loss": 0.3442,
"step": 1119
},
{
"epoch": 1.1,
"learning_rate": 1.4661365447640652e-05,
"loss": 0.358,
"step": 1120
},
{
"epoch": 1.1,
"learning_rate": 1.4651944281345598e-05,
"loss": 0.4381,
"step": 1121
},
{
"epoch": 1.1,
"learning_rate": 1.4642517842803043e-05,
"loss": 0.5172,
"step": 1122
},
{
"epoch": 1.1,
"learning_rate": 1.4633086142696373e-05,
"loss": 0.7537,
"step": 1123
},
{
"epoch": 1.1,
"learning_rate": 1.4623649191714938e-05,
"loss": 0.5916,
"step": 1124
},
{
"epoch": 1.11,
"learning_rate": 1.4614207000554036e-05,
"loss": 0.402,
"step": 1125
},
{
"epoch": 1.11,
"learning_rate": 1.4604759579914906e-05,
"loss": 0.4113,
"step": 1126
},
{
"epoch": 1.11,
"learning_rate": 1.4595306940504717e-05,
"loss": 0.3432,
"step": 1127
},
{
"epoch": 1.11,
"learning_rate": 1.4585849093036546e-05,
"loss": 0.5175,
"step": 1128
},
{
"epoch": 1.11,
"learning_rate": 1.4576386048229383e-05,
"loss": 0.3498,
"step": 1129
},
{
"epoch": 1.11,
"learning_rate": 1.4566917816808092e-05,
"loss": 0.497,
"step": 1130
},
{
"epoch": 1.11,
"learning_rate": 1.4557444409503427e-05,
"loss": 0.4621,
"step": 1131
},
{
"epoch": 1.11,
"learning_rate": 1.4547965837052015e-05,
"loss": 0.5582,
"step": 1132
},
{
"epoch": 1.11,
"learning_rate": 1.4538482110196319e-05,
"loss": 0.5334,
"step": 1133
},
{
"epoch": 1.11,
"learning_rate": 1.4528993239684654e-05,
"loss": 0.3817,
"step": 1134
},
{
"epoch": 1.12,
"learning_rate": 1.4519499236271165e-05,
"loss": 0.3702,
"step": 1135
},
{
"epoch": 1.12,
"learning_rate": 1.4510000110715809e-05,
"loss": 0.5757,
"step": 1136
},
{
"epoch": 1.12,
"learning_rate": 1.4500495873784354e-05,
"loss": 0.4307,
"step": 1137
},
{
"epoch": 1.12,
"learning_rate": 1.4490986536248359e-05,
"loss": 0.4587,
"step": 1138
},
{
"epoch": 1.12,
"learning_rate": 1.4481472108885159e-05,
"loss": 0.5539,
"step": 1139
},
{
"epoch": 1.12,
"learning_rate": 1.4471952602477866e-05,
"loss": 0.4755,
"step": 1140
},
{
"epoch": 1.12,
"learning_rate": 1.4462428027815345e-05,
"loss": 0.6503,
"step": 1141
},
{
"epoch": 1.12,
"learning_rate": 1.4452898395692198e-05,
"loss": 0.4157,
"step": 1142
},
{
"epoch": 1.12,
"learning_rate": 1.444336371690877e-05,
"loss": 0.4848,
"step": 1143
},
{
"epoch": 1.12,
"learning_rate": 1.4433824002271117e-05,
"loss": 0.5808,
"step": 1144
},
{
"epoch": 1.13,
"learning_rate": 1.4424279262591008e-05,
"loss": 0.4866,
"step": 1145
},
{
"epoch": 1.13,
"learning_rate": 1.4414729508685905e-05,
"loss": 0.6204,
"step": 1146
},
{
"epoch": 1.13,
"learning_rate": 1.4405174751378953e-05,
"loss": 0.5109,
"step": 1147
},
{
"epoch": 1.13,
"learning_rate": 1.4395615001498963e-05,
"loss": 0.3963,
"step": 1148
},
{
"epoch": 1.13,
"learning_rate": 1.4386050269880414e-05,
"loss": 0.4637,
"step": 1149
},
{
"epoch": 1.13,
"learning_rate": 1.4376480567363426e-05,
"loss": 0.7669,
"step": 1150
},
{
"epoch": 1.13,
"learning_rate": 1.4366905904793747e-05,
"loss": 0.4432,
"step": 1151
},
{
"epoch": 1.13,
"learning_rate": 1.4357326293022756e-05,
"loss": 0.4143,
"step": 1152
},
{
"epoch": 1.13,
"eval_loss": 0.6418061256408691,
"eval_runtime": 92.1506,
"eval_samples_per_second": 21.704,
"eval_steps_per_second": 10.852,
"step": 1152
},
{
"epoch": 1.13,
"learning_rate": 1.4347741742907433e-05,
"loss": 0.6537,
"step": 1153
},
{
"epoch": 1.13,
"learning_rate": 1.4338152265310362e-05,
"loss": 0.3619,
"step": 1154
},
{
"epoch": 1.13,
"learning_rate": 1.432855787109971e-05,
"loss": 0.4613,
"step": 1155
},
{
"epoch": 1.14,
"learning_rate": 1.4318958571149208e-05,
"loss": 0.4304,
"step": 1156
},
{
"epoch": 1.14,
"learning_rate": 1.4309354376338163e-05,
"loss": 0.3444,
"step": 1157
},
{
"epoch": 1.14,
"learning_rate": 1.4299745297551408e-05,
"loss": 0.6261,
"step": 1158
},
{
"epoch": 1.14,
"learning_rate": 1.4290131345679337e-05,
"loss": 0.3739,
"step": 1159
},
{
"epoch": 1.14,
"learning_rate": 1.428051253161784e-05,
"loss": 0.4964,
"step": 1160
},
{
"epoch": 1.14,
"learning_rate": 1.4270888866268335e-05,
"loss": 0.6293,
"step": 1161
},
{
"epoch": 1.14,
"learning_rate": 1.4261260360537738e-05,
"loss": 0.4481,
"step": 1162
},
{
"epoch": 1.14,
"learning_rate": 1.4251627025338443e-05,
"loss": 0.4528,
"step": 1163
},
{
"epoch": 1.14,
"learning_rate": 1.4241988871588321e-05,
"loss": 0.6874,
"step": 1164
},
{
"epoch": 1.14,
"learning_rate": 1.4232345910210703e-05,
"loss": 0.4717,
"step": 1165
},
{
"epoch": 1.15,
"learning_rate": 1.4222698152134373e-05,
"loss": 0.3865,
"step": 1166
},
{
"epoch": 1.15,
"learning_rate": 1.4213045608293546e-05,
"loss": 0.4564,
"step": 1167
},
{
"epoch": 1.15,
"learning_rate": 1.4203388289627862e-05,
"loss": 0.5061,
"step": 1168
},
{
"epoch": 1.15,
"learning_rate": 1.4193726207082375e-05,
"loss": 0.3957,
"step": 1169
},
{
"epoch": 1.15,
"learning_rate": 1.4184059371607535e-05,
"loss": 0.4778,
"step": 1170
},
{
"epoch": 1.15,
"learning_rate": 1.4174387794159183e-05,
"loss": 0.4591,
"step": 1171
},
{
"epoch": 1.15,
"learning_rate": 1.4164711485698528e-05,
"loss": 0.5613,
"step": 1172
},
{
"epoch": 1.15,
"learning_rate": 1.4155030457192147e-05,
"loss": 0.3868,
"step": 1173
},
{
"epoch": 1.15,
"learning_rate": 1.4145344719611962e-05,
"loss": 0.4173,
"step": 1174
},
{
"epoch": 1.15,
"learning_rate": 1.4135654283935236e-05,
"loss": 0.4794,
"step": 1175
},
{
"epoch": 1.16,
"learning_rate": 1.4125959161144555e-05,
"loss": 0.5332,
"step": 1176
},
{
"epoch": 1.16,
"learning_rate": 1.4116259362227816e-05,
"loss": 0.4001,
"step": 1177
},
{
"epoch": 1.16,
"learning_rate": 1.410655489817821e-05,
"loss": 0.4357,
"step": 1178
},
{
"epoch": 1.16,
"learning_rate": 1.409684577999423e-05,
"loss": 0.6384,
"step": 1179
},
{
"epoch": 1.16,
"learning_rate": 1.4087132018679633e-05,
"loss": 0.5056,
"step": 1180
},
{
"epoch": 1.16,
"learning_rate": 1.4077413625243434e-05,
"loss": 0.4574,
"step": 1181
},
{
"epoch": 1.16,
"learning_rate": 1.406769061069991e-05,
"loss": 0.4067,
"step": 1182
},
{
"epoch": 1.16,
"learning_rate": 1.405796298606857e-05,
"loss": 0.4461,
"step": 1183
},
{
"epoch": 1.16,
"learning_rate": 1.4048230762374145e-05,
"loss": 0.4754,
"step": 1184
},
{
"epoch": 1.16,
"learning_rate": 1.4038493950646582e-05,
"loss": 0.4431,
"step": 1185
},
{
"epoch": 1.17,
"learning_rate": 1.4028752561921023e-05,
"loss": 0.4883,
"step": 1186
},
{
"epoch": 1.17,
"learning_rate": 1.4019006607237804e-05,
"loss": 0.4642,
"step": 1187
},
{
"epoch": 1.17,
"learning_rate": 1.4009256097642432e-05,
"loss": 0.4424,
"step": 1188
},
{
"epoch": 1.17,
"learning_rate": 1.3999501044185577e-05,
"loss": 0.5227,
"step": 1189
},
{
"epoch": 1.17,
"learning_rate": 1.3989741457923053e-05,
"loss": 0.452,
"step": 1190
},
{
"epoch": 1.17,
"learning_rate": 1.3979977349915825e-05,
"loss": 0.4788,
"step": 1191
},
{
"epoch": 1.17,
"learning_rate": 1.3970208731229975e-05,
"loss": 0.48,
"step": 1192
},
{
"epoch": 1.17,
"learning_rate": 1.3960435612936687e-05,
"loss": 0.5141,
"step": 1193
},
{
"epoch": 1.17,
"learning_rate": 1.3950658006112261e-05,
"loss": 0.5066,
"step": 1194
},
{
"epoch": 1.17,
"learning_rate": 1.3940875921838073e-05,
"loss": 0.4132,
"step": 1195
},
{
"epoch": 1.18,
"learning_rate": 1.3931089371200586e-05,
"loss": 0.6134,
"step": 1196
},
{
"epoch": 1.18,
"learning_rate": 1.3921298365291306e-05,
"loss": 0.4294,
"step": 1197
},
{
"epoch": 1.18,
"learning_rate": 1.3911502915206805e-05,
"loss": 0.3907,
"step": 1198
},
{
"epoch": 1.18,
"learning_rate": 1.3901703032048683e-05,
"loss": 0.3252,
"step": 1199
},
{
"epoch": 1.18,
"learning_rate": 1.3891898726923571e-05,
"loss": 0.522,
"step": 1200
},
{
"epoch": 1.18,
"learning_rate": 1.3882090010943108e-05,
"loss": 0.4624,
"step": 1201
},
{
"epoch": 1.18,
"learning_rate": 1.3872276895223923e-05,
"loss": 0.4088,
"step": 1202
},
{
"epoch": 1.18,
"learning_rate": 1.3862459390887647e-05,
"loss": 0.5829,
"step": 1203
},
{
"epoch": 1.18,
"learning_rate": 1.3852637509060875e-05,
"loss": 0.3834,
"step": 1204
},
{
"epoch": 1.18,
"learning_rate": 1.384281126087517e-05,
"loss": 0.4125,
"step": 1205
},
{
"epoch": 1.18,
"learning_rate": 1.3832980657467036e-05,
"loss": 0.4006,
"step": 1206
},
{
"epoch": 1.19,
"learning_rate": 1.3823145709977913e-05,
"loss": 0.5298,
"step": 1207
},
{
"epoch": 1.19,
"learning_rate": 1.3813306429554177e-05,
"loss": 0.4584,
"step": 1208
},
{
"epoch": 1.19,
"learning_rate": 1.3803462827347099e-05,
"loss": 0.4194,
"step": 1209
},
{
"epoch": 1.19,
"learning_rate": 1.3793614914512855e-05,
"loss": 0.4819,
"step": 1210
},
{
"epoch": 1.19,
"learning_rate": 1.3783762702212507e-05,
"loss": 0.4614,
"step": 1211
},
{
"epoch": 1.19,
"learning_rate": 1.3773906201611987e-05,
"loss": 0.4775,
"step": 1212
},
{
"epoch": 1.19,
"learning_rate": 1.3764045423882092e-05,
"loss": 0.5111,
"step": 1213
},
{
"epoch": 1.19,
"learning_rate": 1.3754180380198463e-05,
"loss": 0.3936,
"step": 1214
},
{
"epoch": 1.19,
"learning_rate": 1.3744311081741576e-05,
"loss": 0.5261,
"step": 1215
},
{
"epoch": 1.19,
"learning_rate": 1.3734437539696724e-05,
"loss": 0.5809,
"step": 1216
},
{
"epoch": 1.19,
"eval_loss": 0.643155038356781,
"eval_runtime": 92.1457,
"eval_samples_per_second": 21.705,
"eval_steps_per_second": 10.852,
"step": 1216
},
{
"epoch": 1.2,
"learning_rate": 1.3724559765254024e-05,
"loss": 0.4809,
"step": 1217
},
{
"epoch": 1.2,
"learning_rate": 1.371467776960837e-05,
"loss": 0.3917,
"step": 1218
},
{
"epoch": 1.2,
"learning_rate": 1.3704791563959461e-05,
"loss": 0.4373,
"step": 1219
},
{
"epoch": 1.2,
"learning_rate": 1.3694901159511746e-05,
"loss": 0.4099,
"step": 1220
},
{
"epoch": 1.2,
"learning_rate": 1.3685006567474453e-05,
"loss": 0.4016,
"step": 1221
},
{
"epoch": 1.2,
"learning_rate": 1.3675107799061544e-05,
"loss": 0.3381,
"step": 1222
},
{
"epoch": 1.2,
"learning_rate": 1.3665204865491713e-05,
"loss": 0.4284,
"step": 1223
},
{
"epoch": 1.2,
"learning_rate": 1.3655297777988381e-05,
"loss": 0.4067,
"step": 1224
},
{
"epoch": 1.2,
"learning_rate": 1.3645386547779675e-05,
"loss": 0.4327,
"step": 1225
},
{
"epoch": 1.2,
"learning_rate": 1.3635471186098415e-05,
"loss": 0.5682,
"step": 1226
},
{
"epoch": 1.21,
"learning_rate": 1.3625551704182108e-05,
"loss": 0.442,
"step": 1227
},
{
"epoch": 1.21,
"learning_rate": 1.3615628113272919e-05,
"loss": 0.5041,
"step": 1228
},
{
"epoch": 1.21,
"learning_rate": 1.3605700424617685e-05,
"loss": 0.4087,
"step": 1229
},
{
"epoch": 1.21,
"learning_rate": 1.359576864946788e-05,
"loss": 0.4118,
"step": 1230
},
{
"epoch": 1.21,
"learning_rate": 1.358583279907961e-05,
"loss": 0.5586,
"step": 1231
},
{
"epoch": 1.21,
"learning_rate": 1.3575892884713597e-05,
"loss": 0.5202,
"step": 1232
},
{
"epoch": 1.21,
"learning_rate": 1.3565948917635169e-05,
"loss": 0.6437,
"step": 1233
},
{
"epoch": 1.21,
"learning_rate": 1.3556000909114256e-05,
"loss": 0.3742,
"step": 1234
},
{
"epoch": 1.21,
"learning_rate": 1.3546048870425356e-05,
"loss": 0.4073,
"step": 1235
},
{
"epoch": 1.21,
"learning_rate": 1.3536092812847548e-05,
"loss": 0.5483,
"step": 1236
},
{
"epoch": 1.22,
"learning_rate": 1.3526132747664446e-05,
"loss": 0.4923,
"step": 1237
},
{
"epoch": 1.22,
"learning_rate": 1.3516168686164228e-05,
"loss": 0.497,
"step": 1238
},
{
"epoch": 1.22,
"learning_rate": 1.3506200639639586e-05,
"loss": 0.3738,
"step": 1239
},
{
"epoch": 1.22,
"learning_rate": 1.349622861938774e-05,
"loss": 0.4221,
"step": 1240
},
{
"epoch": 1.22,
"learning_rate": 1.3486252636710398e-05,
"loss": 0.5519,
"step": 1241
},
{
"epoch": 1.22,
"learning_rate": 1.3476272702913771e-05,
"loss": 0.3895,
"step": 1242
},
{
"epoch": 1.22,
"learning_rate": 1.3466288829308551e-05,
"loss": 0.5378,
"step": 1243
},
{
"epoch": 1.22,
"learning_rate": 1.3456301027209884e-05,
"loss": 0.3972,
"step": 1244
},
{
"epoch": 1.22,
"learning_rate": 1.3446309307937378e-05,
"loss": 0.5007,
"step": 1245
},
{
"epoch": 1.22,
"learning_rate": 1.3436313682815066e-05,
"loss": 0.4063,
"step": 1246
},
{
"epoch": 1.23,
"learning_rate": 1.3426314163171428e-05,
"loss": 0.4292,
"step": 1247
},
{
"epoch": 1.23,
"learning_rate": 1.3416310760339342e-05,
"loss": 0.4789,
"step": 1248
},
{
"epoch": 1.23,
"learning_rate": 1.3406303485656094e-05,
"loss": 0.3955,
"step": 1249
},
{
"epoch": 1.23,
"learning_rate": 1.3396292350463355e-05,
"loss": 0.3498,
"step": 1250
},
{
"epoch": 1.23,
"learning_rate": 1.3386277366107177e-05,
"loss": 0.4949,
"step": 1251
},
{
"epoch": 1.23,
"learning_rate": 1.3376258543937968e-05,
"loss": 0.402,
"step": 1252
},
{
"epoch": 1.23,
"learning_rate": 1.3366235895310486e-05,
"loss": 0.4553,
"step": 1253
},
{
"epoch": 1.23,
"learning_rate": 1.3356209431583831e-05,
"loss": 0.4398,
"step": 1254
},
{
"epoch": 1.23,
"learning_rate": 1.3346179164121418e-05,
"loss": 0.4255,
"step": 1255
},
{
"epoch": 1.23,
"learning_rate": 1.3336145104290985e-05,
"loss": 0.4198,
"step": 1256
},
{
"epoch": 1.24,
"learning_rate": 1.3326107263464559e-05,
"loss": 0.5645,
"step": 1257
},
{
"epoch": 1.24,
"learning_rate": 1.331606565301845e-05,
"loss": 0.5843,
"step": 1258
},
{
"epoch": 1.24,
"learning_rate": 1.330602028433325e-05,
"loss": 0.3931,
"step": 1259
},
{
"epoch": 1.24,
"learning_rate": 1.3295971168793802e-05,
"loss": 0.6684,
"step": 1260
},
{
"epoch": 1.24,
"learning_rate": 1.3285918317789203e-05,
"loss": 0.4594,
"step": 1261
},
{
"epoch": 1.24,
"learning_rate": 1.3275861742712777e-05,
"loss": 0.4198,
"step": 1262
},
{
"epoch": 1.24,
"learning_rate": 1.3265801454962066e-05,
"loss": 0.499,
"step": 1263
},
{
"epoch": 1.24,
"learning_rate": 1.3255737465938832e-05,
"loss": 0.5017,
"step": 1264
},
{
"epoch": 1.24,
"learning_rate": 1.3245669787049021e-05,
"loss": 0.5483,
"step": 1265
},
{
"epoch": 1.24,
"learning_rate": 1.3235598429702762e-05,
"loss": 0.5766,
"step": 1266
},
{
"epoch": 1.24,
"learning_rate": 1.322552340531436e-05,
"loss": 0.6579,
"step": 1267
},
{
"epoch": 1.25,
"learning_rate": 1.3215444725302269e-05,
"loss": 0.5201,
"step": 1268
},
{
"epoch": 1.25,
"learning_rate": 1.3205362401089086e-05,
"loss": 0.499,
"step": 1269
},
{
"epoch": 1.25,
"learning_rate": 1.3195276444101546e-05,
"loss": 0.4311,
"step": 1270
},
{
"epoch": 1.25,
"learning_rate": 1.3185186865770489e-05,
"loss": 0.4559,
"step": 1271
},
{
"epoch": 1.25,
"learning_rate": 1.3175093677530868e-05,
"loss": 0.391,
"step": 1272
},
{
"epoch": 1.25,
"learning_rate": 1.316499689082173e-05,
"loss": 0.432,
"step": 1273
},
{
"epoch": 1.25,
"learning_rate": 1.3154896517086188e-05,
"loss": 0.3953,
"step": 1274
},
{
"epoch": 1.25,
"learning_rate": 1.3144792567771436e-05,
"loss": 0.403,
"step": 1275
},
{
"epoch": 1.25,
"learning_rate": 1.3134685054328702e-05,
"loss": 0.4392,
"step": 1276
},
{
"epoch": 1.25,
"learning_rate": 1.3124573988213272e-05,
"loss": 0.3883,
"step": 1277
},
{
"epoch": 1.26,
"learning_rate": 1.3114459380884446e-05,
"loss": 0.3968,
"step": 1278
},
{
"epoch": 1.26,
"learning_rate": 1.310434124380554e-05,
"loss": 0.4253,
"step": 1279
},
{
"epoch": 1.26,
"learning_rate": 1.3094219588443874e-05,
"loss": 0.4208,
"step": 1280
},
{
"epoch": 1.26,
"eval_loss": 0.642217755317688,
"eval_runtime": 92.1323,
"eval_samples_per_second": 21.708,
"eval_steps_per_second": 10.854,
"step": 1280
},
{
"epoch": 1.26,
"learning_rate": 1.3084094426270755e-05,
"loss": 0.4697,
"step": 1281
},
{
"epoch": 1.26,
"learning_rate": 1.3073965768761461e-05,
"loss": 0.4322,
"step": 1282
},
{
"epoch": 1.26,
"learning_rate": 1.3063833627395231e-05,
"loss": 0.563,
"step": 1283
},
{
"epoch": 1.26,
"learning_rate": 1.3053698013655253e-05,
"loss": 0.4812,
"step": 1284
},
{
"epoch": 1.26,
"learning_rate": 1.3043558939028657e-05,
"loss": 0.421,
"step": 1285
},
{
"epoch": 1.26,
"learning_rate": 1.3033416415006486e-05,
"loss": 0.528,
"step": 1286
},
{
"epoch": 1.26,
"learning_rate": 1.3023270453083701e-05,
"loss": 0.4808,
"step": 1287
},
{
"epoch": 1.27,
"learning_rate": 1.3013121064759148e-05,
"loss": 0.5954,
"step": 1288
},
{
"epoch": 1.27,
"learning_rate": 1.3002968261535566e-05,
"loss": 0.5036,
"step": 1289
},
{
"epoch": 1.27,
"learning_rate": 1.2992812054919566e-05,
"loss": 0.5814,
"step": 1290
},
{
"epoch": 1.27,
"learning_rate": 1.2982652456421607e-05,
"loss": 0.4946,
"step": 1291
},
{
"epoch": 1.27,
"learning_rate": 1.2972489477555995e-05,
"loss": 0.4362,
"step": 1292
},
{
"epoch": 1.27,
"learning_rate": 1.296232312984087e-05,
"loss": 0.6515,
"step": 1293
},
{
"epoch": 1.27,
"learning_rate": 1.2952153424798193e-05,
"loss": 0.4783,
"step": 1294
},
{
"epoch": 1.27,
"learning_rate": 1.2941980373953719e-05,
"loss": 0.3793,
"step": 1295
},
{
"epoch": 1.27,
"learning_rate": 1.293180398883701e-05,
"loss": 0.6208,
"step": 1296
},
{
"epoch": 1.27,
"learning_rate": 1.292162428098139e-05,
"loss": 0.4737,
"step": 1297
},
{
"epoch": 1.28,
"learning_rate": 1.2911441261923965e-05,
"loss": 0.5852,
"step": 1298
},
{
"epoch": 1.28,
"learning_rate": 1.2901254943205582e-05,
"loss": 0.4963,
"step": 1299
},
{
"epoch": 1.28,
"learning_rate": 1.289106533637083e-05,
"loss": 0.431,
"step": 1300
},
{
"epoch": 1.28,
"learning_rate": 1.2880872452968034e-05,
"loss": 0.5248,
"step": 1301
},
{
"epoch": 1.28,
"learning_rate": 1.2870676304549217e-05,
"loss": 0.622,
"step": 1302
},
{
"epoch": 1.28,
"learning_rate": 1.2860476902670116e-05,
"loss": 0.4883,
"step": 1303
},
{
"epoch": 1.28,
"learning_rate": 1.2850274258890144e-05,
"loss": 0.4131,
"step": 1304
},
{
"epoch": 1.28,
"learning_rate": 1.2840068384772399e-05,
"loss": 0.5054,
"step": 1305
},
{
"epoch": 1.28,
"learning_rate": 1.2829859291883629e-05,
"loss": 0.3523,
"step": 1306
},
{
"epoch": 1.28,
"learning_rate": 1.2819646991794242e-05,
"loss": 0.3954,
"step": 1307
},
{
"epoch": 1.29,
"learning_rate": 1.280943149607827e-05,
"loss": 0.449,
"step": 1308
},
{
"epoch": 1.29,
"learning_rate": 1.2799212816313375e-05,
"loss": 0.5491,
"step": 1309
},
{
"epoch": 1.29,
"learning_rate": 1.2788990964080824e-05,
"loss": 0.5913,
"step": 1310
},
{
"epoch": 1.29,
"learning_rate": 1.2778765950965473e-05,
"loss": 0.382,
"step": 1311
},
{
"epoch": 1.29,
"learning_rate": 1.2768537788555777e-05,
"loss": 0.4703,
"step": 1312
},
{
"epoch": 1.29,
"learning_rate": 1.2758306488443744e-05,
"loss": 0.4116,
"step": 1313
},
{
"epoch": 1.29,
"learning_rate": 1.274807206222494e-05,
"loss": 0.3523,
"step": 1314
},
{
"epoch": 1.29,
"learning_rate": 1.2737834521498489e-05,
"loss": 0.4168,
"step": 1315
},
{
"epoch": 1.29,
"learning_rate": 1.2727593877867024e-05,
"loss": 0.4017,
"step": 1316
},
{
"epoch": 1.29,
"learning_rate": 1.2717350142936713e-05,
"loss": 0.4728,
"step": 1317
},
{
"epoch": 1.3,
"learning_rate": 1.2707103328317211e-05,
"loss": 0.4775,
"step": 1318
},
{
"epoch": 1.3,
"learning_rate": 1.2696853445621677e-05,
"loss": 0.428,
"step": 1319
},
{
"epoch": 1.3,
"learning_rate": 1.268660050646674e-05,
"loss": 0.4741,
"step": 1320
},
{
"epoch": 1.3,
"learning_rate": 1.2676344522472497e-05,
"loss": 0.5829,
"step": 1321
},
{
"epoch": 1.3,
"learning_rate": 1.2666085505262486e-05,
"loss": 0.3966,
"step": 1322
},
{
"epoch": 1.3,
"learning_rate": 1.2655823466463697e-05,
"loss": 0.469,
"step": 1323
},
{
"epoch": 1.3,
"learning_rate": 1.2645558417706539e-05,
"loss": 0.5967,
"step": 1324
},
{
"epoch": 1.3,
"learning_rate": 1.2635290370624823e-05,
"loss": 0.4337,
"step": 1325
},
{
"epoch": 1.3,
"learning_rate": 1.2625019336855774e-05,
"loss": 0.429,
"step": 1326
},
{
"epoch": 1.3,
"learning_rate": 1.261474532803999e-05,
"loss": 0.5048,
"step": 1327
},
{
"epoch": 1.3,
"learning_rate": 1.2604468355821446e-05,
"loss": 0.4131,
"step": 1328
},
{
"epoch": 1.31,
"learning_rate": 1.2594188431847476e-05,
"loss": 0.342,
"step": 1329
},
{
"epoch": 1.31,
"learning_rate": 1.2583905567768753e-05,
"loss": 0.3977,
"step": 1330
},
{
"epoch": 1.31,
"learning_rate": 1.2573619775239295e-05,
"loss": 0.4516,
"step": 1331
},
{
"epoch": 1.31,
"learning_rate": 1.2563331065916418e-05,
"loss": 0.347,
"step": 1332
},
{
"epoch": 1.31,
"learning_rate": 1.2553039451460768e-05,
"loss": 0.3824,
"step": 1333
},
{
"epoch": 1.31,
"learning_rate": 1.2542744943536266e-05,
"loss": 0.4852,
"step": 1334
},
{
"epoch": 1.31,
"learning_rate": 1.2532447553810125e-05,
"loss": 0.4888,
"step": 1335
},
{
"epoch": 1.31,
"learning_rate": 1.2522147293952806e-05,
"loss": 0.5005,
"step": 1336
},
{
"epoch": 1.31,
"learning_rate": 1.2511844175638046e-05,
"loss": 0.4055,
"step": 1337
},
{
"epoch": 1.31,
"learning_rate": 1.2501538210542805e-05,
"loss": 0.4423,
"step": 1338
},
{
"epoch": 1.32,
"learning_rate": 1.2491229410347272e-05,
"loss": 0.3097,
"step": 1339
},
{
"epoch": 1.32,
"learning_rate": 1.2480917786734855e-05,
"loss": 0.5855,
"step": 1340
},
{
"epoch": 1.32,
"learning_rate": 1.2470603351392154e-05,
"loss": 0.8108,
"step": 1341
},
{
"epoch": 1.32,
"learning_rate": 1.2460286116008963e-05,
"loss": 0.4486,
"step": 1342
},
{
"epoch": 1.32,
"learning_rate": 1.2449966092278247e-05,
"loss": 0.3948,
"step": 1343
},
{
"epoch": 1.32,
"learning_rate": 1.243964329189613e-05,
"loss": 0.5083,
"step": 1344
},
{
"epoch": 1.32,
"eval_loss": 0.6403606534004211,
"eval_runtime": 92.1495,
"eval_samples_per_second": 21.704,
"eval_steps_per_second": 10.852,
"step": 1344
},
{
"epoch": 1.32,
"learning_rate": 1.242931772656188e-05,
"loss": 0.4648,
"step": 1345
},
{
"epoch": 1.32,
"learning_rate": 1.2418989407977906e-05,
"loss": 0.5427,
"step": 1346
},
{
"epoch": 1.32,
"learning_rate": 1.2408658347849735e-05,
"loss": 0.5903,
"step": 1347
},
{
"epoch": 1.32,
"learning_rate": 1.2398324557885994e-05,
"loss": 0.526,
"step": 1348
},
{
"epoch": 1.33,
"learning_rate": 1.2387988049798412e-05,
"loss": 0.5298,
"step": 1349
},
{
"epoch": 1.33,
"learning_rate": 1.2377648835301795e-05,
"loss": 0.4412,
"step": 1350
},
{
"epoch": 1.33,
"learning_rate": 1.236730692611402e-05,
"loss": 0.459,
"step": 1351
},
{
"epoch": 1.33,
"learning_rate": 1.235696233395601e-05,
"loss": 0.4664,
"step": 1352
},
{
"epoch": 1.33,
"learning_rate": 1.234661507055174e-05,
"loss": 0.5334,
"step": 1353
},
{
"epoch": 1.33,
"learning_rate": 1.2336265147628202e-05,
"loss": 0.4123,
"step": 1354
},
{
"epoch": 1.33,
"learning_rate": 1.2325912576915407e-05,
"loss": 0.5095,
"step": 1355
},
{
"epoch": 1.33,
"learning_rate": 1.2315557370146371e-05,
"loss": 0.4195,
"step": 1356
},
{
"epoch": 1.33,
"learning_rate": 1.2305199539057086e-05,
"loss": 0.3927,
"step": 1357
},
{
"epoch": 1.33,
"learning_rate": 1.2294839095386528e-05,
"loss": 0.4188,
"step": 1358
},
{
"epoch": 1.34,
"learning_rate": 1.2284476050876633e-05,
"loss": 0.5133,
"step": 1359
},
{
"epoch": 1.34,
"learning_rate": 1.227411041727228e-05,
"loss": 0.505,
"step": 1360
},
{
"epoch": 1.34,
"learning_rate": 1.2263742206321287e-05,
"loss": 0.6633,
"step": 1361
},
{
"epoch": 1.34,
"learning_rate": 1.225337142977439e-05,
"loss": 0.4736,
"step": 1362
},
{
"epoch": 1.34,
"learning_rate": 1.2242998099385234e-05,
"loss": 0.5027,
"step": 1363
},
{
"epoch": 1.34,
"learning_rate": 1.2232622226910361e-05,
"loss": 0.3838,
"step": 1364
},
{
"epoch": 1.34,
"learning_rate": 1.2222243824109189e-05,
"loss": 0.489,
"step": 1365
},
{
"epoch": 1.34,
"learning_rate": 1.2211862902743998e-05,
"loss": 0.4725,
"step": 1366
},
{
"epoch": 1.34,
"learning_rate": 1.2201479474579946e-05,
"loss": 0.5076,
"step": 1367
},
{
"epoch": 1.34,
"learning_rate": 1.2191093551385004e-05,
"loss": 0.4788,
"step": 1368
},
{
"epoch": 1.35,
"learning_rate": 1.2180705144929989e-05,
"loss": 0.5037,
"step": 1369
},
{
"epoch": 1.35,
"learning_rate": 1.2170314266988525e-05,
"loss": 0.5288,
"step": 1370
},
{
"epoch": 1.35,
"learning_rate": 1.215992092933704e-05,
"loss": 0.4623,
"step": 1371
},
{
"epoch": 1.35,
"learning_rate": 1.2149525143754748e-05,
"loss": 0.5142,
"step": 1372
},
{
"epoch": 1.35,
"learning_rate": 1.2139126922023633e-05,
"loss": 0.4796,
"step": 1373
},
{
"epoch": 1.35,
"learning_rate": 1.212872627592845e-05,
"loss": 0.4865,
"step": 1374
},
{
"epoch": 1.35,
"learning_rate": 1.2118323217256694e-05,
"loss": 0.4385,
"step": 1375
},
{
"epoch": 1.35,
"learning_rate": 1.2107917757798595e-05,
"loss": 0.4761,
"step": 1376
},
{
"epoch": 1.35,
"learning_rate": 1.2097509909347112e-05,
"loss": 0.5267,
"step": 1377
},
{
"epoch": 1.35,
"learning_rate": 1.2087099683697899e-05,
"loss": 0.4389,
"step": 1378
},
{
"epoch": 1.35,
"learning_rate": 1.207668709264931e-05,
"loss": 0.5114,
"step": 1379
},
{
"epoch": 1.36,
"learning_rate": 1.206627214800238e-05,
"loss": 0.4283,
"step": 1380
},
{
"epoch": 1.36,
"learning_rate": 1.2055854861560814e-05,
"loss": 0.7428,
"step": 1381
},
{
"epoch": 1.36,
"learning_rate": 1.204543524513097e-05,
"loss": 0.4743,
"step": 1382
},
{
"epoch": 1.36,
"learning_rate": 1.203501331052184e-05,
"loss": 0.4846,
"step": 1383
},
{
"epoch": 1.36,
"learning_rate": 1.2024589069545049e-05,
"loss": 0.5233,
"step": 1384
},
{
"epoch": 1.36,
"learning_rate": 1.2014162534014839e-05,
"loss": 0.4953,
"step": 1385
},
{
"epoch": 1.36,
"learning_rate": 1.2003733715748052e-05,
"loss": 0.4959,
"step": 1386
},
{
"epoch": 1.36,
"learning_rate": 1.1993302626564103e-05,
"loss": 0.4487,
"step": 1387
},
{
"epoch": 1.36,
"learning_rate": 1.1982869278284996e-05,
"loss": 0.5788,
"step": 1388
},
{
"epoch": 1.36,
"learning_rate": 1.1972433682735299e-05,
"loss": 0.5554,
"step": 1389
},
{
"epoch": 1.37,
"learning_rate": 1.196199585174211e-05,
"loss": 0.4623,
"step": 1390
},
{
"epoch": 1.37,
"learning_rate": 1.1951555797135073e-05,
"loss": 0.581,
"step": 1391
},
{
"epoch": 1.37,
"learning_rate": 1.1941113530746344e-05,
"loss": 0.5634,
"step": 1392
},
{
"epoch": 1.37,
"learning_rate": 1.1930669064410599e-05,
"loss": 0.4151,
"step": 1393
},
{
"epoch": 1.37,
"learning_rate": 1.1920222409964992e-05,
"loss": 0.4672,
"step": 1394
},
{
"epoch": 1.37,
"learning_rate": 1.1909773579249166e-05,
"loss": 0.3719,
"step": 1395
},
{
"epoch": 1.37,
"learning_rate": 1.1899322584105225e-05,
"loss": 0.4242,
"step": 1396
},
{
"epoch": 1.37,
"learning_rate": 1.188886943637773e-05,
"loss": 0.5637,
"step": 1397
},
{
"epoch": 1.37,
"learning_rate": 1.1878414147913685e-05,
"loss": 0.3944,
"step": 1398
},
{
"epoch": 1.37,
"learning_rate": 1.186795673056251e-05,
"loss": 0.4626,
"step": 1399
},
{
"epoch": 1.38,
"learning_rate": 1.1857497196176049e-05,
"loss": 0.4978,
"step": 1400
},
{
"epoch": 1.38,
"learning_rate": 1.1847035556608532e-05,
"loss": 0.3292,
"step": 1401
},
{
"epoch": 1.38,
"learning_rate": 1.1836571823716594e-05,
"loss": 0.4592,
"step": 1402
},
{
"epoch": 1.38,
"learning_rate": 1.1826106009359221e-05,
"loss": 0.4512,
"step": 1403
},
{
"epoch": 1.38,
"learning_rate": 1.1815638125397773e-05,
"loss": 0.6305,
"step": 1404
},
{
"epoch": 1.38,
"learning_rate": 1.1805168183695948e-05,
"loss": 0.4476,
"step": 1405
},
{
"epoch": 1.38,
"learning_rate": 1.179469619611978e-05,
"loss": 0.3988,
"step": 1406
},
{
"epoch": 1.38,
"learning_rate": 1.1784222174537627e-05,
"loss": 0.4043,
"step": 1407
},
{
"epoch": 1.38,
"learning_rate": 1.1773746130820137e-05,
"loss": 0.4425,
"step": 1408
},
{
"epoch": 1.38,
"eval_loss": 0.6399658918380737,
"eval_runtime": 92.1659,
"eval_samples_per_second": 21.7,
"eval_steps_per_second": 10.85,
"step": 1408
},
{
"epoch": 1.38,
"learning_rate": 1.176326807684026e-05,
"loss": 0.5018,
"step": 1409
},
{
"epoch": 1.39,
"learning_rate": 1.1752788024473227e-05,
"loss": 0.7034,
"step": 1410
},
{
"epoch": 1.39,
"learning_rate": 1.1742305985596526e-05,
"loss": 0.4332,
"step": 1411
},
{
"epoch": 1.39,
"learning_rate": 1.1731821972089902e-05,
"loss": 0.4375,
"step": 1412
},
{
"epoch": 1.39,
"learning_rate": 1.1721335995835336e-05,
"loss": 0.467,
"step": 1413
},
{
"epoch": 1.39,
"learning_rate": 1.1710848068717033e-05,
"loss": 0.3435,
"step": 1414
},
{
"epoch": 1.39,
"learning_rate": 1.1700358202621412e-05,
"loss": 0.4285,
"step": 1415
},
{
"epoch": 1.39,
"learning_rate": 1.1689866409437084e-05,
"loss": 0.507,
"step": 1416
},
{
"epoch": 1.39,
"learning_rate": 1.1679372701054846e-05,
"loss": 0.4239,
"step": 1417
},
{
"epoch": 1.39,
"learning_rate": 1.1668877089367668e-05,
"loss": 0.4888,
"step": 1418
},
{
"epoch": 1.39,
"learning_rate": 1.1658379586270679e-05,
"loss": 0.5367,
"step": 1419
},
{
"epoch": 1.4,
"learning_rate": 1.1647880203661147e-05,
"loss": 0.4926,
"step": 1420
},
{
"epoch": 1.4,
"learning_rate": 1.1637378953438469e-05,
"loss": 0.5581,
"step": 1421
},
{
"epoch": 1.4,
"learning_rate": 1.162687584750416e-05,
"loss": 0.3664,
"step": 1422
},
{
"epoch": 1.4,
"learning_rate": 1.1616370897761846e-05,
"loss": 0.4974,
"step": 1423
},
{
"epoch": 1.4,
"learning_rate": 1.1605864116117231e-05,
"loss": 0.352,
"step": 1424
},
{
"epoch": 1.4,
"learning_rate": 1.1595355514478101e-05,
"loss": 0.4963,
"step": 1425
},
{
"epoch": 1.4,
"learning_rate": 1.1584845104754305e-05,
"loss": 0.6589,
"step": 1426
},
{
"epoch": 1.4,
"learning_rate": 1.1574332898857738e-05,
"loss": 0.4397,
"step": 1427
},
{
"epoch": 1.4,
"learning_rate": 1.1563818908702338e-05,
"loss": 0.445,
"step": 1428
},
{
"epoch": 1.4,
"learning_rate": 1.1553303146204051e-05,
"loss": 0.4173,
"step": 1429
},
{
"epoch": 1.41,
"learning_rate": 1.1542785623280847e-05,
"loss": 0.4003,
"step": 1430
},
{
"epoch": 1.41,
"learning_rate": 1.1532266351852685e-05,
"loss": 0.5473,
"step": 1431
},
{
"epoch": 1.41,
"learning_rate": 1.1521745343841502e-05,
"loss": 0.4505,
"step": 1432
},
{
"epoch": 1.41,
"learning_rate": 1.1511222611171212e-05,
"loss": 0.3665,
"step": 1433
},
{
"epoch": 1.41,
"learning_rate": 1.150069816576767e-05,
"loss": 0.5364,
"step": 1434
},
{
"epoch": 1.41,
"learning_rate": 1.1490172019558688e-05,
"loss": 0.4384,
"step": 1435
},
{
"epoch": 1.41,
"learning_rate": 1.147964418447399e-05,
"loss": 0.4475,
"step": 1436
},
{
"epoch": 1.41,
"learning_rate": 1.1469114672445232e-05,
"loss": 0.4499,
"step": 1437
},
{
"epoch": 1.41,
"learning_rate": 1.1458583495405953e-05,
"loss": 0.3847,
"step": 1438
},
{
"epoch": 1.41,
"learning_rate": 1.1448050665291587e-05,
"loss": 0.4208,
"step": 1439
},
{
"epoch": 1.41,
"learning_rate": 1.1437516194039445e-05,
"loss": 0.522,
"step": 1440
},
{
"epoch": 1.42,
"learning_rate": 1.1426980093588688e-05,
"loss": 0.4422,
"step": 1441
},
{
"epoch": 1.42,
"learning_rate": 1.141644237588034e-05,
"loss": 0.4069,
"step": 1442
},
{
"epoch": 1.42,
"learning_rate": 1.1405903052857233e-05,
"loss": 0.4009,
"step": 1443
},
{
"epoch": 1.42,
"learning_rate": 1.1395362136464045e-05,
"loss": 0.572,
"step": 1444
},
{
"epoch": 1.42,
"learning_rate": 1.1384819638647242e-05,
"loss": 0.3693,
"step": 1445
},
{
"epoch": 1.42,
"learning_rate": 1.137427557135509e-05,
"loss": 0.5795,
"step": 1446
},
{
"epoch": 1.42,
"learning_rate": 1.1363729946537626e-05,
"loss": 0.4233,
"step": 1447
},
{
"epoch": 1.42,
"learning_rate": 1.1353182776146665e-05,
"loss": 0.4394,
"step": 1448
},
{
"epoch": 1.42,
"learning_rate": 1.1342634072135767e-05,
"loss": 0.4274,
"step": 1449
},
{
"epoch": 1.42,
"learning_rate": 1.1332083846460222e-05,
"loss": 0.5785,
"step": 1450
},
{
"epoch": 1.43,
"learning_rate": 1.132153211107706e-05,
"loss": 0.5227,
"step": 1451
},
{
"epoch": 1.43,
"learning_rate": 1.1310978877945007e-05,
"loss": 0.4407,
"step": 1452
},
{
"epoch": 1.43,
"learning_rate": 1.1300424159024498e-05,
"loss": 0.3294,
"step": 1453
},
{
"epoch": 1.43,
"learning_rate": 1.128986796627765e-05,
"loss": 0.4914,
"step": 1454
},
{
"epoch": 1.43,
"learning_rate": 1.127931031166824e-05,
"loss": 0.4081,
"step": 1455
},
{
"epoch": 1.43,
"learning_rate": 1.1268751207161718e-05,
"loss": 0.3605,
"step": 1456
},
{
"epoch": 1.43,
"learning_rate": 1.1258190664725164e-05,
"loss": 0.4707,
"step": 1457
},
{
"epoch": 1.43,
"learning_rate": 1.1247628696327297e-05,
"loss": 0.4822,
"step": 1458
},
{
"epoch": 1.43,
"learning_rate": 1.1237065313938442e-05,
"loss": 0.5421,
"step": 1459
},
{
"epoch": 1.43,
"learning_rate": 1.1226500529530535e-05,
"loss": 0.5348,
"step": 1460
},
{
"epoch": 1.44,
"learning_rate": 1.1215934355077098e-05,
"loss": 0.4236,
"step": 1461
},
{
"epoch": 1.44,
"learning_rate": 1.1205366802553231e-05,
"loss": 0.616,
"step": 1462
},
{
"epoch": 1.44,
"learning_rate": 1.1194797883935593e-05,
"loss": 0.6513,
"step": 1463
},
{
"epoch": 1.44,
"learning_rate": 1.1184227611202386e-05,
"loss": 0.4161,
"step": 1464
},
{
"epoch": 1.44,
"learning_rate": 1.1173655996333356e-05,
"loss": 0.4594,
"step": 1465
},
{
"epoch": 1.44,
"learning_rate": 1.1163083051309768e-05,
"loss": 0.4249,
"step": 1466
},
{
"epoch": 1.44,
"learning_rate": 1.1152508788114395e-05,
"loss": 0.5858,
"step": 1467
},
{
"epoch": 1.44,
"learning_rate": 1.1141933218731498e-05,
"loss": 0.4029,
"step": 1468
},
{
"epoch": 1.44,
"learning_rate": 1.1131356355146818e-05,
"loss": 0.5355,
"step": 1469
},
{
"epoch": 1.44,
"learning_rate": 1.1120778209347578e-05,
"loss": 0.5773,
"step": 1470
},
{
"epoch": 1.45,
"learning_rate": 1.1110198793322433e-05,
"loss": 0.3876,
"step": 1471
},
{
"epoch": 1.45,
"learning_rate": 1.1099618119061498e-05,
"loss": 0.4397,
"step": 1472
},
{
"epoch": 1.45,
"eval_loss": 0.6387297511100769,
"eval_runtime": 92.1391,
"eval_samples_per_second": 21.706,
"eval_steps_per_second": 10.853,
"step": 1472
},
{
"epoch": 1.45,
"learning_rate": 1.1089036198556292e-05,
"loss": 0.4879,
"step": 1473
},
{
"epoch": 1.45,
"learning_rate": 1.1078453043799766e-05,
"loss": 0.4402,
"step": 1474
},
{
"epoch": 1.45,
"learning_rate": 1.1067868666786263e-05,
"loss": 0.4395,
"step": 1475
},
{
"epoch": 1.45,
"learning_rate": 1.1057283079511506e-05,
"loss": 0.3103,
"step": 1476
},
{
"epoch": 1.45,
"learning_rate": 1.1046696293972594e-05,
"loss": 0.4221,
"step": 1477
},
{
"epoch": 1.45,
"learning_rate": 1.1036108322167988e-05,
"loss": 0.4549,
"step": 1478
},
{
"epoch": 1.45,
"learning_rate": 1.102551917609749e-05,
"loss": 0.4012,
"step": 1479
},
{
"epoch": 1.45,
"learning_rate": 1.1014928867762227e-05,
"loss": 0.4058,
"step": 1480
},
{
"epoch": 1.46,
"learning_rate": 1.100433740916465e-05,
"loss": 0.5172,
"step": 1481
},
{
"epoch": 1.46,
"learning_rate": 1.0993744812308516e-05,
"loss": 0.5288,
"step": 1482
},
{
"epoch": 1.46,
"learning_rate": 1.0983151089198867e-05,
"loss": 0.386,
"step": 1483
},
{
"epoch": 1.46,
"learning_rate": 1.097255625184202e-05,
"loss": 0.4847,
"step": 1484
},
{
"epoch": 1.46,
"learning_rate": 1.0961960312245557e-05,
"loss": 0.4124,
"step": 1485
},
{
"epoch": 1.46,
"learning_rate": 1.0951363282418312e-05,
"loss": 0.6911,
"step": 1486
},
{
"epoch": 1.46,
"learning_rate": 1.0940765174370353e-05,
"loss": 0.4448,
"step": 1487
},
{
"epoch": 1.46,
"learning_rate": 1.093016600011297e-05,
"loss": 0.4107,
"step": 1488
},
{
"epoch": 1.46,
"learning_rate": 1.0919565771658657e-05,
"loss": 0.4369,
"step": 1489
},
{
"epoch": 1.46,
"learning_rate": 1.0908964501021108e-05,
"loss": 0.4505,
"step": 1490
},
{
"epoch": 1.46,
"learning_rate": 1.0898362200215199e-05,
"loss": 0.5908,
"step": 1491
},
{
"epoch": 1.47,
"learning_rate": 1.0887758881256967e-05,
"loss": 0.4599,
"step": 1492
},
{
"epoch": 1.47,
"learning_rate": 1.0877154556163614e-05,
"loss": 0.5783,
"step": 1493
},
{
"epoch": 1.47,
"learning_rate": 1.0866549236953468e-05,
"loss": 0.4547,
"step": 1494
},
{
"epoch": 1.47,
"learning_rate": 1.085594293564599e-05,
"loss": 0.4619,
"step": 1495
},
{
"epoch": 1.47,
"learning_rate": 1.0845335664261762e-05,
"loss": 0.4365,
"step": 1496
},
{
"epoch": 1.47,
"learning_rate": 1.0834727434822458e-05,
"loss": 0.5584,
"step": 1497
},
{
"epoch": 1.47,
"learning_rate": 1.0824118259350834e-05,
"loss": 0.4061,
"step": 1498
},
{
"epoch": 1.47,
"learning_rate": 1.0813508149870722e-05,
"loss": 0.4664,
"step": 1499
},
{
"epoch": 1.47,
"learning_rate": 1.0802897118407018e-05,
"loss": 0.5548,
"step": 1500
},
{
"epoch": 1.47,
"learning_rate": 1.0792285176985653e-05,
"loss": 0.5281,
"step": 1501
},
{
"epoch": 1.48,
"learning_rate": 1.07816723376336e-05,
"loss": 0.392,
"step": 1502
},
{
"epoch": 1.48,
"learning_rate": 1.0771058612378837e-05,
"loss": 0.4433,
"step": 1503
},
{
"epoch": 1.48,
"learning_rate": 1.076044401325036e-05,
"loss": 0.3674,
"step": 1504
},
{
"epoch": 1.48,
"learning_rate": 1.0749828552278141e-05,
"loss": 0.4554,
"step": 1505
},
{
"epoch": 1.48,
"learning_rate": 1.0739212241493142e-05,
"loss": 0.5205,
"step": 1506
},
{
"epoch": 1.48,
"learning_rate": 1.0728595092927279e-05,
"loss": 0.4059,
"step": 1507
},
{
"epoch": 1.48,
"learning_rate": 1.0717977118613424e-05,
"loss": 0.4432,
"step": 1508
},
{
"epoch": 1.48,
"learning_rate": 1.070735833058538e-05,
"loss": 0.4337,
"step": 1509
},
{
"epoch": 1.48,
"learning_rate": 1.0696738740877872e-05,
"loss": 0.4521,
"step": 1510
},
{
"epoch": 1.48,
"learning_rate": 1.0686118361526537e-05,
"loss": 0.5516,
"step": 1511
},
{
"epoch": 1.49,
"learning_rate": 1.0675497204567904e-05,
"loss": 0.3802,
"step": 1512
},
{
"epoch": 1.49,
"learning_rate": 1.0664875282039386e-05,
"loss": 0.4828,
"step": 1513
},
{
"epoch": 1.49,
"learning_rate": 1.0654252605979266e-05,
"loss": 0.6109,
"step": 1514
},
{
"epoch": 1.49,
"learning_rate": 1.0643629188426669e-05,
"loss": 0.5209,
"step": 1515
},
{
"epoch": 1.49,
"learning_rate": 1.0633005041421573e-05,
"loss": 0.496,
"step": 1516
},
{
"epoch": 1.49,
"learning_rate": 1.062238017700478e-05,
"loss": 0.5634,
"step": 1517
},
{
"epoch": 1.49,
"learning_rate": 1.0611754607217906e-05,
"loss": 0.4525,
"step": 1518
},
{
"epoch": 1.49,
"learning_rate": 1.0601128344103354e-05,
"loss": 0.3718,
"step": 1519
},
{
"epoch": 1.49,
"learning_rate": 1.0590501399704332e-05,
"loss": 0.5073,
"step": 1520
},
{
"epoch": 1.49,
"learning_rate": 1.0579873786064804e-05,
"loss": 0.3695,
"step": 1521
},
{
"epoch": 1.5,
"learning_rate": 1.0569245515229505e-05,
"loss": 0.3856,
"step": 1522
},
{
"epoch": 1.5,
"learning_rate": 1.0558616599243907e-05,
"loss": 0.4899,
"step": 1523
},
{
"epoch": 1.5,
"learning_rate": 1.0547987050154214e-05,
"loss": 0.4733,
"step": 1524
},
{
"epoch": 1.5,
"learning_rate": 1.053735688000735e-05,
"loss": 0.4708,
"step": 1525
},
{
"epoch": 1.5,
"learning_rate": 1.052672610085094e-05,
"loss": 0.3553,
"step": 1526
},
{
"epoch": 1.5,
"learning_rate": 1.0516094724733305e-05,
"loss": 0.5207,
"step": 1527
},
{
"epoch": 1.5,
"learning_rate": 1.0505462763703434e-05,
"loss": 0.7059,
"step": 1528
},
{
"epoch": 1.5,
"learning_rate": 1.049483022981098e-05,
"loss": 0.4595,
"step": 1529
},
{
"epoch": 1.5,
"learning_rate": 1.0484197135106265e-05,
"loss": 0.4208,
"step": 1530
},
{
"epoch": 1.5,
"learning_rate": 1.0473563491640211e-05,
"loss": 0.4145,
"step": 1531
},
{
"epoch": 1.51,
"learning_rate": 1.0462929311464393e-05,
"loss": 0.5641,
"step": 1532
},
{
"epoch": 1.51,
"learning_rate": 1.0452294606630975e-05,
"loss": 0.3867,
"step": 1533
},
{
"epoch": 1.51,
"learning_rate": 1.0441659389192728e-05,
"loss": 0.3608,
"step": 1534
},
{
"epoch": 1.51,
"learning_rate": 1.0431023671202997e-05,
"loss": 0.4607,
"step": 1535
},
{
"epoch": 1.51,
"learning_rate": 1.0420387464715698e-05,
"loss": 0.5879,
"step": 1536
},
{
"epoch": 1.51,
"eval_loss": 0.6388291120529175,
"eval_runtime": 92.126,
"eval_samples_per_second": 21.709,
"eval_steps_per_second": 10.855,
"step": 1536
},
{
"epoch": 1.51,
"learning_rate": 1.0409750781785298e-05,
"loss": 0.4694,
"step": 1537
},
{
"epoch": 1.51,
"learning_rate": 1.0399113634466803e-05,
"loss": 0.5898,
"step": 1538
},
{
"epoch": 1.51,
"learning_rate": 1.038847603481575e-05,
"loss": 0.4367,
"step": 1539
},
{
"epoch": 1.51,
"learning_rate": 1.0377837994888183e-05,
"loss": 0.6579,
"step": 1540
},
{
"epoch": 1.51,
"learning_rate": 1.036719952674065e-05,
"loss": 0.4103,
"step": 1541
},
{
"epoch": 1.52,
"learning_rate": 1.035656064243018e-05,
"loss": 0.4438,
"step": 1542
},
{
"epoch": 1.52,
"learning_rate": 1.0345921354014279e-05,
"loss": 0.4706,
"step": 1543
},
{
"epoch": 1.52,
"learning_rate": 1.033528167355091e-05,
"loss": 0.4878,
"step": 1544
},
{
"epoch": 1.52,
"learning_rate": 1.032464161309847e-05,
"loss": 0.5765,
"step": 1545
},
{
"epoch": 1.52,
"learning_rate": 1.0314001184715798e-05,
"loss": 0.3265,
"step": 1546
},
{
"epoch": 1.52,
"learning_rate": 1.030336040046215e-05,
"loss": 0.4661,
"step": 1547
},
{
"epoch": 1.52,
"learning_rate": 1.0292719272397182e-05,
"loss": 0.4378,
"step": 1548
},
{
"epoch": 1.52,
"learning_rate": 1.0282077812580936e-05,
"loss": 0.43,
"step": 1549
},
{
"epoch": 1.52,
"learning_rate": 1.0271436033073834e-05,
"loss": 0.5716,
"step": 1550
},
{
"epoch": 1.52,
"learning_rate": 1.026079394593666e-05,
"loss": 0.4337,
"step": 1551
},
{
"epoch": 1.52,
"learning_rate": 1.025015156323055e-05,
"loss": 0.3949,
"step": 1552
},
{
"epoch": 1.53,
"learning_rate": 1.0239508897016974e-05,
"loss": 0.493,
"step": 1553
},
{
"epoch": 1.53,
"learning_rate": 1.0228865959357712e-05,
"loss": 0.4297,
"step": 1554
},
{
"epoch": 1.53,
"learning_rate": 1.0218222762314867e-05,
"loss": 0.4611,
"step": 1555
},
{
"epoch": 1.53,
"learning_rate": 1.0207579317950826e-05,
"loss": 0.4523,
"step": 1556
},
{
"epoch": 1.53,
"learning_rate": 1.0196935638328267e-05,
"loss": 0.5728,
"step": 1557
},
{
"epoch": 1.53,
"learning_rate": 1.018629173551012e-05,
"loss": 0.4151,
"step": 1558
},
{
"epoch": 1.53,
"learning_rate": 1.0175647621559575e-05,
"loss": 0.4431,
"step": 1559
},
{
"epoch": 1.53,
"learning_rate": 1.0165003308540069e-05,
"loss": 0.4174,
"step": 1560
},
{
"epoch": 1.53,
"learning_rate": 1.015435880851525e-05,
"loss": 0.5497,
"step": 1561
},
{
"epoch": 1.53,
"learning_rate": 1.0143714133548992e-05,
"loss": 0.504,
"step": 1562
},
{
"epoch": 1.54,
"learning_rate": 1.0133069295705353e-05,
"loss": 0.3981,
"step": 1563
},
{
"epoch": 1.54,
"learning_rate": 1.0122424307048593e-05,
"loss": 0.5052,
"step": 1564
},
{
"epoch": 1.54,
"learning_rate": 1.0111779179643124e-05,
"loss": 0.4386,
"step": 1565
},
{
"epoch": 1.54,
"learning_rate": 1.0101133925553527e-05,
"loss": 0.534,
"step": 1566
},
{
"epoch": 1.54,
"learning_rate": 1.0090488556844526e-05,
"loss": 0.4958,
"step": 1567
},
{
"epoch": 1.54,
"learning_rate": 1.0079843085580972e-05,
"loss": 0.3536,
"step": 1568
},
{
"epoch": 1.54,
"learning_rate": 1.0069197523827835e-05,
"loss": 0.6202,
"step": 1569
},
{
"epoch": 1.54,
"learning_rate": 1.005855188365018e-05,
"loss": 0.5226,
"step": 1570
},
{
"epoch": 1.54,
"learning_rate": 1.0047906177113172e-05,
"loss": 0.3764,
"step": 1571
},
{
"epoch": 1.54,
"learning_rate": 1.0037260416282042e-05,
"loss": 0.4622,
"step": 1572
},
{
"epoch": 1.55,
"learning_rate": 1.0026614613222087e-05,
"loss": 0.3598,
"step": 1573
},
{
"epoch": 1.55,
"learning_rate": 1.0015968779998654e-05,
"loss": 0.3924,
"step": 1574
},
{
"epoch": 1.55,
"learning_rate": 1.000532292867712e-05,
"loss": 0.4679,
"step": 1575
},
{
"epoch": 1.55,
"learning_rate": 9.994677071322883e-06,
"loss": 0.414,
"step": 1576
},
{
"epoch": 1.55,
"learning_rate": 9.984031220001349e-06,
"loss": 0.6014,
"step": 1577
},
{
"epoch": 1.55,
"learning_rate": 9.973385386777913e-06,
"loss": 0.5991,
"step": 1578
},
{
"epoch": 1.55,
"learning_rate": 9.962739583717962e-06,
"loss": 0.5219,
"step": 1579
},
{
"epoch": 1.55,
"learning_rate": 9.952093822886833e-06,
"loss": 0.3687,
"step": 1580
},
{
"epoch": 1.55,
"learning_rate": 9.94144811634982e-06,
"loss": 0.4187,
"step": 1581
},
{
"epoch": 1.55,
"learning_rate": 9.930802476172169e-06,
"loss": 0.5493,
"step": 1582
},
{
"epoch": 1.56,
"learning_rate": 9.920156914419031e-06,
"loss": 0.4454,
"step": 1583
},
{
"epoch": 1.56,
"learning_rate": 9.909511443155477e-06,
"loss": 0.4895,
"step": 1584
},
{
"epoch": 1.56,
"learning_rate": 9.898866074446473e-06,
"loss": 0.5126,
"step": 1585
},
{
"epoch": 1.56,
"learning_rate": 9.888220820356879e-06,
"loss": 0.4028,
"step": 1586
},
{
"epoch": 1.56,
"learning_rate": 9.877575692951412e-06,
"loss": 0.5656,
"step": 1587
},
{
"epoch": 1.56,
"learning_rate": 9.866930704294647e-06,
"loss": 0.3432,
"step": 1588
},
{
"epoch": 1.56,
"learning_rate": 9.85628586645101e-06,
"loss": 0.4643,
"step": 1589
},
{
"epoch": 1.56,
"learning_rate": 9.845641191484752e-06,
"loss": 0.5426,
"step": 1590
},
{
"epoch": 1.56,
"learning_rate": 9.834996691459938e-06,
"loss": 0.4192,
"step": 1591
},
{
"epoch": 1.56,
"learning_rate": 9.824352378440427e-06,
"loss": 0.5616,
"step": 1592
},
{
"epoch": 1.57,
"learning_rate": 9.813708264489884e-06,
"loss": 0.573,
"step": 1593
},
{
"epoch": 1.57,
"learning_rate": 9.803064361671738e-06,
"loss": 0.4184,
"step": 1594
},
{
"epoch": 1.57,
"learning_rate": 9.792420682049174e-06,
"loss": 0.4205,
"step": 1595
},
{
"epoch": 1.57,
"learning_rate": 9.781777237685137e-06,
"loss": 0.3727,
"step": 1596
},
{
"epoch": 1.57,
"learning_rate": 9.771134040642291e-06,
"loss": 0.4713,
"step": 1597
},
{
"epoch": 1.57,
"learning_rate": 9.760491102983033e-06,
"loss": 0.4816,
"step": 1598
},
{
"epoch": 1.57,
"learning_rate": 9.74984843676945e-06,
"loss": 0.5111,
"step": 1599
},
{
"epoch": 1.57,
"learning_rate": 9.739206054063341e-06,
"loss": 0.3391,
"step": 1600
},
{
"epoch": 1.57,
"eval_loss": 0.6377896070480347,
"eval_runtime": 92.1341,
"eval_samples_per_second": 21.707,
"eval_steps_per_second": 10.854,
"step": 1600
},
{
"epoch": 1.57,
"learning_rate": 9.72856396692617e-06,
"loss": 0.4489,
"step": 1601
},
{
"epoch": 1.57,
"learning_rate": 9.717922187419068e-06,
"loss": 0.3862,
"step": 1602
},
{
"epoch": 1.58,
"learning_rate": 9.707280727602821e-06,
"loss": 0.5073,
"step": 1603
},
{
"epoch": 1.58,
"learning_rate": 9.696639599537853e-06,
"loss": 0.4588,
"step": 1604
},
{
"epoch": 1.58,
"learning_rate": 9.685998815284204e-06,
"loss": 0.5045,
"step": 1605
},
{
"epoch": 1.58,
"learning_rate": 9.675358386901534e-06,
"loss": 0.5552,
"step": 1606
},
{
"epoch": 1.58,
"learning_rate": 9.664718326449093e-06,
"loss": 0.5562,
"step": 1607
},
{
"epoch": 1.58,
"learning_rate": 9.654078645985723e-06,
"loss": 0.4568,
"step": 1608
},
{
"epoch": 1.58,
"learning_rate": 9.643439357569819e-06,
"loss": 0.3418,
"step": 1609
},
{
"epoch": 1.58,
"learning_rate": 9.632800473259355e-06,
"loss": 0.5243,
"step": 1610
},
{
"epoch": 1.58,
"learning_rate": 9.62216200511182e-06,
"loss": 0.4415,
"step": 1611
},
{
"epoch": 1.58,
"learning_rate": 9.611523965184256e-06,
"loss": 0.486,
"step": 1612
},
{
"epoch": 1.58,
"learning_rate": 9.600886365533199e-06,
"loss": 0.3758,
"step": 1613
},
{
"epoch": 1.59,
"learning_rate": 9.590249218214707e-06,
"loss": 0.4263,
"step": 1614
},
{
"epoch": 1.59,
"learning_rate": 9.579612535284306e-06,
"loss": 0.5539,
"step": 1615
},
{
"epoch": 1.59,
"learning_rate": 9.568976328797003e-06,
"loss": 0.6405,
"step": 1616
},
{
"epoch": 1.59,
"learning_rate": 9.558340610807273e-06,
"loss": 0.4204,
"step": 1617
},
{
"epoch": 1.59,
"learning_rate": 9.547705393369028e-06,
"loss": 0.5082,
"step": 1618
},
{
"epoch": 1.59,
"learning_rate": 9.537070688535612e-06,
"loss": 0.3769,
"step": 1619
},
{
"epoch": 1.59,
"learning_rate": 9.52643650835979e-06,
"loss": 0.5339,
"step": 1620
},
{
"epoch": 1.59,
"learning_rate": 9.51580286489374e-06,
"loss": 1.298,
"step": 1621
},
{
"epoch": 1.59,
"learning_rate": 9.50516977018902e-06,
"loss": 0.5258,
"step": 1622
},
{
"epoch": 1.59,
"learning_rate": 9.494537236296571e-06,
"loss": 0.3849,
"step": 1623
},
{
"epoch": 1.6,
"learning_rate": 9.483905275266698e-06,
"loss": 0.5001,
"step": 1624
},
{
"epoch": 1.6,
"learning_rate": 9.473273899149064e-06,
"loss": 0.5695,
"step": 1625
},
{
"epoch": 1.6,
"learning_rate": 9.462643119992657e-06,
"loss": 0.4692,
"step": 1626
},
{
"epoch": 1.6,
"learning_rate": 9.45201294984579e-06,
"loss": 0.3799,
"step": 1627
},
{
"epoch": 1.6,
"learning_rate": 9.441383400756096e-06,
"loss": 0.5431,
"step": 1628
},
{
"epoch": 1.6,
"learning_rate": 9.430754484770498e-06,
"loss": 0.3264,
"step": 1629
},
{
"epoch": 1.6,
"learning_rate": 9.4201262139352e-06,
"loss": 0.6177,
"step": 1630
},
{
"epoch": 1.6,
"learning_rate": 9.409498600295672e-06,
"loss": 0.5492,
"step": 1631
},
{
"epoch": 1.6,
"learning_rate": 9.398871655896647e-06,
"loss": 0.4666,
"step": 1632
},
{
"epoch": 1.6,
"learning_rate": 9.388245392782099e-06,
"loss": 0.4886,
"step": 1633
},
{
"epoch": 1.61,
"learning_rate": 9.37761982299522e-06,
"loss": 0.5038,
"step": 1634
},
{
"epoch": 1.61,
"learning_rate": 9.366994958578429e-06,
"loss": 0.4768,
"step": 1635
},
{
"epoch": 1.61,
"learning_rate": 9.356370811573333e-06,
"loss": 0.3442,
"step": 1636
},
{
"epoch": 1.61,
"learning_rate": 9.34574739402074e-06,
"loss": 0.4312,
"step": 1637
},
{
"epoch": 1.61,
"learning_rate": 9.335124717960614e-06,
"loss": 0.4284,
"step": 1638
},
{
"epoch": 1.61,
"learning_rate": 9.324502795432099e-06,
"loss": 0.4041,
"step": 1639
},
{
"epoch": 1.61,
"learning_rate": 9.313881638473468e-06,
"loss": 0.5715,
"step": 1640
},
{
"epoch": 1.61,
"learning_rate": 9.30326125912213e-06,
"loss": 0.4744,
"step": 1641
},
{
"epoch": 1.61,
"learning_rate": 9.292641669414624e-06,
"loss": 0.358,
"step": 1642
},
{
"epoch": 1.61,
"learning_rate": 9.28202288138658e-06,
"loss": 0.48,
"step": 1643
},
{
"epoch": 1.62,
"learning_rate": 9.271404907072723e-06,
"loss": 0.4449,
"step": 1644
},
{
"epoch": 1.62,
"learning_rate": 9.260787758506858e-06,
"loss": 0.3776,
"step": 1645
},
{
"epoch": 1.62,
"learning_rate": 9.25017144772186e-06,
"loss": 0.4264,
"step": 1646
},
{
"epoch": 1.62,
"learning_rate": 9.239555986749645e-06,
"loss": 0.5093,
"step": 1647
},
{
"epoch": 1.62,
"learning_rate": 9.228941387621165e-06,
"loss": 0.5649,
"step": 1648
},
{
"epoch": 1.62,
"learning_rate": 9.218327662366402e-06,
"loss": 0.3846,
"step": 1649
},
{
"epoch": 1.62,
"learning_rate": 9.207714823014349e-06,
"loss": 0.4209,
"step": 1650
},
{
"epoch": 1.62,
"learning_rate": 9.197102881592987e-06,
"loss": 0.5408,
"step": 1651
},
{
"epoch": 1.62,
"learning_rate": 9.18649185012928e-06,
"loss": 0.6125,
"step": 1652
},
{
"epoch": 1.62,
"learning_rate": 9.175881740649168e-06,
"loss": 0.4763,
"step": 1653
},
{
"epoch": 1.63,
"learning_rate": 9.165272565177547e-06,
"loss": 0.577,
"step": 1654
},
{
"epoch": 1.63,
"learning_rate": 9.154664335738236e-06,
"loss": 0.4142,
"step": 1655
},
{
"epoch": 1.63,
"learning_rate": 9.144057064354011e-06,
"loss": 0.4213,
"step": 1656
},
{
"epoch": 1.63,
"learning_rate": 9.133450763046537e-06,
"loss": 0.4787,
"step": 1657
},
{
"epoch": 1.63,
"learning_rate": 9.122845443836392e-06,
"loss": 0.674,
"step": 1658
},
{
"epoch": 1.63,
"learning_rate": 9.112241118743034e-06,
"loss": 0.4664,
"step": 1659
},
{
"epoch": 1.63,
"learning_rate": 9.101637799784805e-06,
"loss": 0.5318,
"step": 1660
},
{
"epoch": 1.63,
"learning_rate": 9.091035498978894e-06,
"loss": 0.5057,
"step": 1661
},
{
"epoch": 1.63,
"learning_rate": 9.080434228341345e-06,
"loss": 0.4249,
"step": 1662
},
{
"epoch": 1.63,
"learning_rate": 9.069833999887033e-06,
"loss": 0.31,
"step": 1663
},
{
"epoch": 1.63,
"learning_rate": 9.05923482562965e-06,
"loss": 0.4282,
"step": 1664
},
{
"epoch": 1.63,
"eval_loss": 0.6382916569709778,
"eval_runtime": 92.1178,
"eval_samples_per_second": 21.711,
"eval_steps_per_second": 10.856,
"step": 1664
},
{
"epoch": 1.64,
"learning_rate": 9.048636717581692e-06,
"loss": 0.6104,
"step": 1665
},
{
"epoch": 1.64,
"learning_rate": 9.038039687754445e-06,
"loss": 0.6048,
"step": 1666
},
{
"epoch": 1.64,
"learning_rate": 9.027443748157985e-06,
"loss": 0.4412,
"step": 1667
},
{
"epoch": 1.64,
"learning_rate": 9.01684891080114e-06,
"loss": 0.4939,
"step": 1668
},
{
"epoch": 1.64,
"learning_rate": 9.006255187691485e-06,
"loss": 0.4716,
"step": 1669
},
{
"epoch": 1.64,
"learning_rate": 8.995662590835353e-06,
"loss": 0.5776,
"step": 1670
},
{
"epoch": 1.64,
"learning_rate": 8.985071132237776e-06,
"loss": 0.4152,
"step": 1671
},
{
"epoch": 1.64,
"learning_rate": 8.974480823902514e-06,
"loss": 0.5301,
"step": 1672
},
{
"epoch": 1.64,
"learning_rate": 8.963891677832012e-06,
"loss": 0.3383,
"step": 1673
},
{
"epoch": 1.64,
"learning_rate": 8.953303706027407e-06,
"loss": 0.6176,
"step": 1674
},
{
"epoch": 1.65,
"learning_rate": 8.942716920488499e-06,
"loss": 0.4631,
"step": 1675
},
{
"epoch": 1.65,
"learning_rate": 8.932131333213739e-06,
"loss": 0.4152,
"step": 1676
},
{
"epoch": 1.65,
"learning_rate": 8.921546956200236e-06,
"loss": 0.5078,
"step": 1677
},
{
"epoch": 1.65,
"learning_rate": 8.910963801443713e-06,
"loss": 0.506,
"step": 1678
},
{
"epoch": 1.65,
"learning_rate": 8.900381880938507e-06,
"loss": 0.5205,
"step": 1679
},
{
"epoch": 1.65,
"learning_rate": 8.889801206677566e-06,
"loss": 0.5374,
"step": 1680
},
{
"epoch": 1.65,
"learning_rate": 8.879221790652426e-06,
"loss": 0.4249,
"step": 1681
},
{
"epoch": 1.65,
"learning_rate": 8.868643644853185e-06,
"loss": 0.4993,
"step": 1682
},
{
"epoch": 1.65,
"learning_rate": 8.858066781268506e-06,
"loss": 0.3935,
"step": 1683
},
{
"epoch": 1.65,
"learning_rate": 8.847491211885607e-06,
"loss": 0.3895,
"step": 1684
},
{
"epoch": 1.66,
"learning_rate": 8.836916948690234e-06,
"loss": 0.4381,
"step": 1685
},
{
"epoch": 1.66,
"learning_rate": 8.826344003666647e-06,
"loss": 0.4502,
"step": 1686
},
{
"epoch": 1.66,
"learning_rate": 8.815772388797616e-06,
"loss": 0.4715,
"step": 1687
},
{
"epoch": 1.66,
"learning_rate": 8.80520211606441e-06,
"loss": 0.5691,
"step": 1688
},
{
"epoch": 1.66,
"learning_rate": 8.79463319744677e-06,
"loss": 0.4046,
"step": 1689
},
{
"epoch": 1.66,
"learning_rate": 8.7840656449229e-06,
"loss": 0.4401,
"step": 1690
},
{
"epoch": 1.66,
"learning_rate": 8.773499470469467e-06,
"loss": 0.4181,
"step": 1691
},
{
"epoch": 1.66,
"learning_rate": 8.762934686061561e-06,
"loss": 0.5826,
"step": 1692
},
{
"epoch": 1.66,
"learning_rate": 8.752371303672708e-06,
"loss": 0.4741,
"step": 1693
},
{
"epoch": 1.66,
"learning_rate": 8.741809335274835e-06,
"loss": 0.3806,
"step": 1694
},
{
"epoch": 1.67,
"learning_rate": 8.731248792838285e-06,
"loss": 0.4389,
"step": 1695
},
{
"epoch": 1.67,
"learning_rate": 8.720689688331761e-06,
"loss": 0.5005,
"step": 1696
},
{
"epoch": 1.67,
"learning_rate": 8.710132033722351e-06,
"loss": 0.5207,
"step": 1697
},
{
"epoch": 1.67,
"learning_rate": 8.699575840975503e-06,
"loss": 0.6446,
"step": 1698
},
{
"epoch": 1.67,
"learning_rate": 8.689021122054996e-06,
"loss": 0.3636,
"step": 1699
},
{
"epoch": 1.67,
"learning_rate": 8.678467888922944e-06,
"loss": 0.4758,
"step": 1700
},
{
"epoch": 1.67,
"learning_rate": 8.667916153539778e-06,
"loss": 0.4702,
"step": 1701
},
{
"epoch": 1.67,
"learning_rate": 8.657365927864236e-06,
"loss": 0.4927,
"step": 1702
},
{
"epoch": 1.67,
"learning_rate": 8.646817223853337e-06,
"loss": 0.3763,
"step": 1703
},
{
"epoch": 1.67,
"learning_rate": 8.636270053462375e-06,
"loss": 0.4233,
"step": 1704
},
{
"epoch": 1.68,
"learning_rate": 8.625724428644913e-06,
"loss": 0.4638,
"step": 1705
},
{
"epoch": 1.68,
"learning_rate": 8.61518036135276e-06,
"loss": 0.4037,
"step": 1706
},
{
"epoch": 1.68,
"learning_rate": 8.604637863535958e-06,
"loss": 0.4406,
"step": 1707
},
{
"epoch": 1.68,
"learning_rate": 8.594096947142767e-06,
"loss": 0.3365,
"step": 1708
},
{
"epoch": 1.68,
"learning_rate": 8.583557624119664e-06,
"loss": 0.408,
"step": 1709
},
{
"epoch": 1.68,
"learning_rate": 8.573019906411313e-06,
"loss": 0.5262,
"step": 1710
},
{
"epoch": 1.68,
"learning_rate": 8.56248380596056e-06,
"loss": 0.5996,
"step": 1711
},
{
"epoch": 1.68,
"learning_rate": 8.551949334708416e-06,
"loss": 0.5121,
"step": 1712
},
{
"epoch": 1.68,
"learning_rate": 8.541416504594052e-06,
"loss": 0.4368,
"step": 1713
},
{
"epoch": 1.68,
"learning_rate": 8.530885327554773e-06,
"loss": 0.6197,
"step": 1714
},
{
"epoch": 1.69,
"learning_rate": 8.520355815526011e-06,
"loss": 0.3935,
"step": 1715
},
{
"epoch": 1.69,
"learning_rate": 8.509827980441316e-06,
"loss": 0.43,
"step": 1716
},
{
"epoch": 1.69,
"learning_rate": 8.499301834232332e-06,
"loss": 0.449,
"step": 1717
},
{
"epoch": 1.69,
"learning_rate": 8.488777388828793e-06,
"loss": 0.3959,
"step": 1718
},
{
"epoch": 1.69,
"learning_rate": 8.478254656158498e-06,
"loss": 0.4233,
"step": 1719
},
{
"epoch": 1.69,
"learning_rate": 8.467733648147318e-06,
"loss": 0.5662,
"step": 1720
},
{
"epoch": 1.69,
"learning_rate": 8.457214376719154e-06,
"loss": 0.4981,
"step": 1721
},
{
"epoch": 1.69,
"learning_rate": 8.446696853795949e-06,
"loss": 0.387,
"step": 1722
},
{
"epoch": 1.69,
"learning_rate": 8.436181091297665e-06,
"loss": 0.3343,
"step": 1723
},
{
"epoch": 1.69,
"learning_rate": 8.425667101142264e-06,
"loss": 0.7649,
"step": 1724
},
{
"epoch": 1.69,
"learning_rate": 8.415154895245698e-06,
"loss": 0.5276,
"step": 1725
},
{
"epoch": 1.7,
"learning_rate": 8.404644485521899e-06,
"loss": 0.3963,
"step": 1726
},
{
"epoch": 1.7,
"learning_rate": 8.39413588388277e-06,
"loss": 0.4786,
"step": 1727
},
{
"epoch": 1.7,
"learning_rate": 8.383629102238157e-06,
"loss": 0.3789,
"step": 1728
},
{
"epoch": 1.7,
"eval_loss": 0.6366282105445862,
"eval_runtime": 92.1334,
"eval_samples_per_second": 21.708,
"eval_steps_per_second": 10.854,
"step": 1728
},
{
"epoch": 1.7,
"learning_rate": 8.373124152495841e-06,
"loss": 0.494,
"step": 1729
},
{
"epoch": 1.7,
"learning_rate": 8.362621046561534e-06,
"loss": 0.3998,
"step": 1730
},
{
"epoch": 1.7,
"learning_rate": 8.352119796338858e-06,
"loss": 0.5048,
"step": 1731
},
{
"epoch": 1.7,
"learning_rate": 8.341620413729326e-06,
"loss": 0.3907,
"step": 1732
},
{
"epoch": 1.7,
"learning_rate": 8.331122910632334e-06,
"loss": 0.4621,
"step": 1733
},
{
"epoch": 1.7,
"learning_rate": 8.320627298945156e-06,
"loss": 0.3603,
"step": 1734
},
{
"epoch": 1.7,
"learning_rate": 8.310133590562922e-06,
"loss": 0.4474,
"step": 1735
},
{
"epoch": 1.71,
"learning_rate": 8.29964179737859e-06,
"loss": 0.511,
"step": 1736
},
{
"epoch": 1.71,
"learning_rate": 8.289151931282969e-06,
"loss": 0.3623,
"step": 1737
},
{
"epoch": 1.71,
"learning_rate": 8.278664004164665e-06,
"loss": 0.3578,
"step": 1738
},
{
"epoch": 1.71,
"learning_rate": 8.268178027910101e-06,
"loss": 0.4319,
"step": 1739
},
{
"epoch": 1.71,
"learning_rate": 8.257694014403474e-06,
"loss": 0.477,
"step": 1740
},
{
"epoch": 1.71,
"learning_rate": 8.247211975526776e-06,
"loss": 0.3845,
"step": 1741
},
{
"epoch": 1.71,
"learning_rate": 8.236731923159744e-06,
"loss": 0.545,
"step": 1742
},
{
"epoch": 1.71,
"learning_rate": 8.226253869179865e-06,
"loss": 0.4588,
"step": 1743
},
{
"epoch": 1.71,
"learning_rate": 8.215777825462375e-06,
"loss": 0.4231,
"step": 1744
},
{
"epoch": 1.71,
"learning_rate": 8.205303803880221e-06,
"loss": 0.3911,
"step": 1745
},
{
"epoch": 1.72,
"learning_rate": 8.194831816304057e-06,
"loss": 0.4096,
"step": 1746
},
{
"epoch": 1.72,
"learning_rate": 8.18436187460223e-06,
"loss": 0.46,
"step": 1747
},
{
"epoch": 1.72,
"learning_rate": 8.173893990640782e-06,
"loss": 0.4438,
"step": 1748
},
{
"epoch": 1.72,
"learning_rate": 8.163428176283411e-06,
"loss": 0.4925,
"step": 1749
},
{
"epoch": 1.72,
"learning_rate": 8.152964443391466e-06,
"loss": 0.4697,
"step": 1750
},
{
"epoch": 1.72,
"learning_rate": 8.142502803823954e-06,
"loss": 0.5983,
"step": 1751
},
{
"epoch": 1.72,
"learning_rate": 8.132043269437491e-06,
"loss": 0.4637,
"step": 1752
},
{
"epoch": 1.72,
"learning_rate": 8.12158585208632e-06,
"loss": 0.5559,
"step": 1753
},
{
"epoch": 1.72,
"learning_rate": 8.11113056362227e-06,
"loss": 0.4191,
"step": 1754
},
{
"epoch": 1.72,
"learning_rate": 8.10067741589478e-06,
"loss": 0.4358,
"step": 1755
},
{
"epoch": 1.73,
"learning_rate": 8.09022642075084e-06,
"loss": 0.3739,
"step": 1756
},
{
"epoch": 1.73,
"learning_rate": 8.07977759003501e-06,
"loss": 0.4587,
"step": 1757
},
{
"epoch": 1.73,
"learning_rate": 8.069330935589403e-06,
"loss": 0.6105,
"step": 1758
},
{
"epoch": 1.73,
"learning_rate": 8.058886469253658e-06,
"loss": 0.4264,
"step": 1759
},
{
"epoch": 1.73,
"learning_rate": 8.048444202864932e-06,
"loss": 0.4025,
"step": 1760
},
{
"epoch": 1.73,
"learning_rate": 8.038004148257892e-06,
"loss": 0.5097,
"step": 1761
},
{
"epoch": 1.73,
"learning_rate": 8.027566317264704e-06,
"loss": 0.4013,
"step": 1762
},
{
"epoch": 1.73,
"learning_rate": 8.017130721715006e-06,
"loss": 0.5686,
"step": 1763
},
{
"epoch": 1.73,
"learning_rate": 8.0066973734359e-06,
"loss": 0.6541,
"step": 1764
},
{
"epoch": 1.73,
"learning_rate": 7.996266284251952e-06,
"loss": 0.4391,
"step": 1765
},
{
"epoch": 1.74,
"learning_rate": 7.985837465985163e-06,
"loss": 0.4452,
"step": 1766
},
{
"epoch": 1.74,
"learning_rate": 7.975410930454954e-06,
"loss": 0.4595,
"step": 1767
},
{
"epoch": 1.74,
"learning_rate": 7.964986689478164e-06,
"loss": 0.3849,
"step": 1768
},
{
"epoch": 1.74,
"learning_rate": 7.954564754869034e-06,
"loss": 0.4759,
"step": 1769
},
{
"epoch": 1.74,
"learning_rate": 7.944145138439189e-06,
"loss": 0.3483,
"step": 1770
},
{
"epoch": 1.74,
"learning_rate": 7.933727851997621e-06,
"loss": 0.3787,
"step": 1771
},
{
"epoch": 1.74,
"learning_rate": 7.923312907350694e-06,
"loss": 0.4934,
"step": 1772
},
{
"epoch": 1.74,
"learning_rate": 7.912900316302106e-06,
"loss": 0.4731,
"step": 1773
},
{
"epoch": 1.74,
"learning_rate": 7.902490090652892e-06,
"loss": 0.5358,
"step": 1774
},
{
"epoch": 1.74,
"learning_rate": 7.892082242201405e-06,
"loss": 0.5422,
"step": 1775
},
{
"epoch": 1.75,
"learning_rate": 7.88167678274331e-06,
"loss": 0.4138,
"step": 1776
},
{
"epoch": 1.75,
"learning_rate": 7.871273724071553e-06,
"loss": 0.3642,
"step": 1777
},
{
"epoch": 1.75,
"learning_rate": 7.860873077976366e-06,
"loss": 0.4246,
"step": 1778
},
{
"epoch": 1.75,
"learning_rate": 7.850474856245255e-06,
"loss": 0.525,
"step": 1779
},
{
"epoch": 1.75,
"learning_rate": 7.840079070662962e-06,
"loss": 0.4635,
"step": 1780
},
{
"epoch": 1.75,
"learning_rate": 7.829685733011477e-06,
"loss": 0.3396,
"step": 1781
},
{
"epoch": 1.75,
"learning_rate": 7.81929485507001e-06,
"loss": 0.4801,
"step": 1782
},
{
"epoch": 1.75,
"learning_rate": 7.808906448614997e-06,
"loss": 0.4123,
"step": 1783
},
{
"epoch": 1.75,
"learning_rate": 7.79852052542006e-06,
"loss": 0.3435,
"step": 1784
},
{
"epoch": 1.75,
"learning_rate": 7.788137097256003e-06,
"loss": 0.426,
"step": 1785
},
{
"epoch": 1.75,
"learning_rate": 7.777756175890815e-06,
"loss": 0.4428,
"step": 1786
},
{
"epoch": 1.76,
"learning_rate": 7.767377773089642e-06,
"loss": 0.707,
"step": 1787
},
{
"epoch": 1.76,
"learning_rate": 7.757001900614769e-06,
"loss": 0.422,
"step": 1788
},
{
"epoch": 1.76,
"learning_rate": 7.746628570225612e-06,
"loss": 0.4756,
"step": 1789
},
{
"epoch": 1.76,
"learning_rate": 7.736257793678714e-06,
"loss": 0.4771,
"step": 1790
},
{
"epoch": 1.76,
"learning_rate": 7.725889582727724e-06,
"loss": 0.4686,
"step": 1791
},
{
"epoch": 1.76,
"learning_rate": 7.715523949123372e-06,
"loss": 0.405,
"step": 1792
},
{
"epoch": 1.76,
"eval_loss": 0.6360684633255005,
"eval_runtime": 92.1297,
"eval_samples_per_second": 21.709,
"eval_steps_per_second": 10.854,
"step": 1792
},
{
"epoch": 1.76,
"learning_rate": 7.705160904613474e-06,
"loss": 0.4946,
"step": 1793
},
{
"epoch": 1.76,
"learning_rate": 7.694800460942917e-06,
"loss": 0.5357,
"step": 1794
},
{
"epoch": 1.76,
"learning_rate": 7.684442629853634e-06,
"loss": 0.4391,
"step": 1795
},
{
"epoch": 1.76,
"learning_rate": 7.674087423084593e-06,
"loss": 0.3798,
"step": 1796
},
{
"epoch": 1.77,
"learning_rate": 7.663734852371802e-06,
"loss": 0.3308,
"step": 1797
},
{
"epoch": 1.77,
"learning_rate": 7.653384929448264e-06,
"loss": 0.4469,
"step": 1798
},
{
"epoch": 1.77,
"learning_rate": 7.643037666043993e-06,
"loss": 0.4975,
"step": 1799
},
{
"epoch": 1.77,
"learning_rate": 7.632693073885982e-06,
"loss": 0.4033,
"step": 1800
},
{
"epoch": 1.77,
"learning_rate": 7.622351164698209e-06,
"loss": 0.4367,
"step": 1801
},
{
"epoch": 1.77,
"learning_rate": 7.612011950201592e-06,
"loss": 0.5034,
"step": 1802
},
{
"epoch": 1.77,
"learning_rate": 7.601675442114009e-06,
"loss": 0.4027,
"step": 1803
},
{
"epoch": 1.77,
"learning_rate": 7.591341652150268e-06,
"loss": 0.4486,
"step": 1804
},
{
"epoch": 1.77,
"learning_rate": 7.581010592022096e-06,
"loss": 0.448,
"step": 1805
},
{
"epoch": 1.77,
"learning_rate": 7.570682273438122e-06,
"loss": 0.5458,
"step": 1806
},
{
"epoch": 1.78,
"learning_rate": 7.560356708103873e-06,
"loss": 0.6205,
"step": 1807
},
{
"epoch": 1.78,
"learning_rate": 7.550033907721754e-06,
"loss": 0.4875,
"step": 1808
},
{
"epoch": 1.78,
"learning_rate": 7.53971388399104e-06,
"loss": 0.4856,
"step": 1809
},
{
"epoch": 1.78,
"learning_rate": 7.529396648607848e-06,
"loss": 0.354,
"step": 1810
},
{
"epoch": 1.78,
"learning_rate": 7.51908221326515e-06,
"loss": 0.3779,
"step": 1811
},
{
"epoch": 1.78,
"learning_rate": 7.508770589652731e-06,
"loss": 0.449,
"step": 1812
},
{
"epoch": 1.78,
"learning_rate": 7.498461789457201e-06,
"loss": 0.5958,
"step": 1813
},
{
"epoch": 1.78,
"learning_rate": 7.488155824361955e-06,
"loss": 0.5937,
"step": 1814
},
{
"epoch": 1.78,
"learning_rate": 7.477852706047195e-06,
"loss": 0.505,
"step": 1815
},
{
"epoch": 1.78,
"learning_rate": 7.467552446189879e-06,
"loss": 0.3785,
"step": 1816
},
{
"epoch": 1.79,
"learning_rate": 7.457255056463732e-06,
"loss": 0.3735,
"step": 1817
},
{
"epoch": 1.79,
"learning_rate": 7.446960548539235e-06,
"loss": 0.4161,
"step": 1818
},
{
"epoch": 1.79,
"learning_rate": 7.4366689340835865e-06,
"loss": 0.4737,
"step": 1819
},
{
"epoch": 1.79,
"learning_rate": 7.426380224760712e-06,
"loss": 0.4035,
"step": 1820
},
{
"epoch": 1.79,
"learning_rate": 7.416094432231247e-06,
"loss": 0.4868,
"step": 1821
},
{
"epoch": 1.79,
"learning_rate": 7.405811568152528e-06,
"loss": 0.4374,
"step": 1822
},
{
"epoch": 1.79,
"learning_rate": 7.395531644178558e-06,
"loss": 0.3094,
"step": 1823
},
{
"epoch": 1.79,
"learning_rate": 7.385254671960012e-06,
"loss": 0.4262,
"step": 1824
},
{
"epoch": 1.79,
"learning_rate": 7.374980663144226e-06,
"loss": 0.7081,
"step": 1825
},
{
"epoch": 1.79,
"learning_rate": 7.36470962937518e-06,
"loss": 0.6272,
"step": 1826
},
{
"epoch": 1.8,
"learning_rate": 7.354441582293468e-06,
"loss": 0.4863,
"step": 1827
},
{
"epoch": 1.8,
"learning_rate": 7.344176533536305e-06,
"loss": 0.5306,
"step": 1828
},
{
"epoch": 1.8,
"learning_rate": 7.3339144947375155e-06,
"loss": 0.4422,
"step": 1829
},
{
"epoch": 1.8,
"learning_rate": 7.323655477527509e-06,
"loss": 0.3935,
"step": 1830
},
{
"epoch": 1.8,
"learning_rate": 7.3133994935332605e-06,
"loss": 0.4724,
"step": 1831
},
{
"epoch": 1.8,
"learning_rate": 7.303146554378325e-06,
"loss": 0.4738,
"step": 1832
},
{
"epoch": 1.8,
"learning_rate": 7.292896671682791e-06,
"loss": 0.4617,
"step": 1833
},
{
"epoch": 1.8,
"learning_rate": 7.282649857063292e-06,
"loss": 0.4899,
"step": 1834
},
{
"epoch": 1.8,
"learning_rate": 7.272406122132976e-06,
"loss": 0.4568,
"step": 1835
},
{
"epoch": 1.8,
"learning_rate": 7.262165478501515e-06,
"loss": 0.5881,
"step": 1836
},
{
"epoch": 1.8,
"learning_rate": 7.2519279377750605e-06,
"loss": 0.3809,
"step": 1837
},
{
"epoch": 1.81,
"learning_rate": 7.241693511556258e-06,
"loss": 0.5214,
"step": 1838
},
{
"epoch": 1.81,
"learning_rate": 7.231462211444226e-06,
"loss": 0.4687,
"step": 1839
},
{
"epoch": 1.81,
"learning_rate": 7.221234049034529e-06,
"loss": 0.7593,
"step": 1840
},
{
"epoch": 1.81,
"learning_rate": 7.211009035919181e-06,
"loss": 0.5124,
"step": 1841
},
{
"epoch": 1.81,
"learning_rate": 7.200787183686625e-06,
"loss": 0.4525,
"step": 1842
},
{
"epoch": 1.81,
"learning_rate": 7.190568503921731e-06,
"loss": 0.4785,
"step": 1843
},
{
"epoch": 1.81,
"learning_rate": 7.180353008205763e-06,
"loss": 0.4018,
"step": 1844
},
{
"epoch": 1.81,
"learning_rate": 7.170140708116373e-06,
"loss": 0.44,
"step": 1845
},
{
"epoch": 1.81,
"learning_rate": 7.159931615227604e-06,
"loss": 0.4688,
"step": 1846
},
{
"epoch": 1.81,
"learning_rate": 7.14972574110986e-06,
"loss": 0.4486,
"step": 1847
},
{
"epoch": 1.82,
"learning_rate": 7.13952309732989e-06,
"loss": 0.4782,
"step": 1848
},
{
"epoch": 1.82,
"learning_rate": 7.129323695450785e-06,
"loss": 0.4213,
"step": 1849
},
{
"epoch": 1.82,
"learning_rate": 7.119127547031967e-06,
"loss": 0.4074,
"step": 1850
},
{
"epoch": 1.82,
"learning_rate": 7.108934663629171e-06,
"loss": 0.3435,
"step": 1851
},
{
"epoch": 1.82,
"learning_rate": 7.09874505679442e-06,
"loss": 0.5096,
"step": 1852
},
{
"epoch": 1.82,
"learning_rate": 7.088558738076037e-06,
"loss": 0.5465,
"step": 1853
},
{
"epoch": 1.82,
"learning_rate": 7.0783757190186106e-06,
"loss": 0.483,
"step": 1854
},
{
"epoch": 1.82,
"learning_rate": 7.068196011162994e-06,
"loss": 0.3797,
"step": 1855
},
{
"epoch": 1.82,
"learning_rate": 7.058019626046281e-06,
"loss": 0.4041,
"step": 1856
},
{
"epoch": 1.82,
"eval_loss": 0.6353977918624878,
"eval_runtime": 92.119,
"eval_samples_per_second": 21.711,
"eval_steps_per_second": 10.856,
"step": 1856
},
{
"epoch": 1.82,
"learning_rate": 7.047846575201811e-06,
"loss": 0.4707,
"step": 1857
},
{
"epoch": 1.83,
"learning_rate": 7.037676870159131e-06,
"loss": 0.3582,
"step": 1858
},
{
"epoch": 1.83,
"learning_rate": 7.027510522444008e-06,
"loss": 0.482,
"step": 1859
},
{
"epoch": 1.83,
"learning_rate": 7.017347543578396e-06,
"loss": 0.5019,
"step": 1860
},
{
"epoch": 1.83,
"learning_rate": 7.007187945080438e-06,
"loss": 0.4815,
"step": 1861
},
{
"epoch": 1.83,
"learning_rate": 6.997031738464435e-06,
"loss": 0.4605,
"step": 1862
},
{
"epoch": 1.83,
"learning_rate": 6.986878935240855e-06,
"loss": 0.5482,
"step": 1863
},
{
"epoch": 1.83,
"learning_rate": 6.976729546916302e-06,
"loss": 0.3475,
"step": 1864
},
{
"epoch": 1.83,
"learning_rate": 6.9665835849935155e-06,
"loss": 0.4453,
"step": 1865
},
{
"epoch": 1.83,
"learning_rate": 6.956441060971346e-06,
"loss": 0.4791,
"step": 1866
},
{
"epoch": 1.83,
"learning_rate": 6.946301986344749e-06,
"loss": 0.5741,
"step": 1867
},
{
"epoch": 1.84,
"learning_rate": 6.936166372604773e-06,
"loss": 0.4522,
"step": 1868
},
{
"epoch": 1.84,
"learning_rate": 6.926034231238544e-06,
"loss": 0.6891,
"step": 1869
},
{
"epoch": 1.84,
"learning_rate": 6.915905573729246e-06,
"loss": 0.3555,
"step": 1870
},
{
"epoch": 1.84,
"learning_rate": 6.905780411556128e-06,
"loss": 0.6272,
"step": 1871
},
{
"epoch": 1.84,
"learning_rate": 6.895658756194463e-06,
"loss": 0.4046,
"step": 1872
},
{
"epoch": 1.84,
"learning_rate": 6.88554061911556e-06,
"loss": 0.4655,
"step": 1873
},
{
"epoch": 1.84,
"learning_rate": 6.875426011786731e-06,
"loss": 0.401,
"step": 1874
},
{
"epoch": 1.84,
"learning_rate": 6.865314945671302e-06,
"loss": 0.5063,
"step": 1875
},
{
"epoch": 1.84,
"learning_rate": 6.85520743222857e-06,
"loss": 0.4254,
"step": 1876
},
{
"epoch": 1.84,
"learning_rate": 6.845103482913813e-06,
"loss": 0.4412,
"step": 1877
},
{
"epoch": 1.85,
"learning_rate": 6.835003109178273e-06,
"loss": 0.4162,
"step": 1878
},
{
"epoch": 1.85,
"learning_rate": 6.8249063224691355e-06,
"loss": 0.5759,
"step": 1879
},
{
"epoch": 1.85,
"learning_rate": 6.814813134229516e-06,
"loss": 0.436,
"step": 1880
},
{
"epoch": 1.85,
"learning_rate": 6.804723555898458e-06,
"loss": 0.4049,
"step": 1881
},
{
"epoch": 1.85,
"learning_rate": 6.794637598910917e-06,
"loss": 0.517,
"step": 1882
},
{
"epoch": 1.85,
"learning_rate": 6.784555274697737e-06,
"loss": 0.4346,
"step": 1883
},
{
"epoch": 1.85,
"learning_rate": 6.7744765946856415e-06,
"loss": 0.3585,
"step": 1884
},
{
"epoch": 1.85,
"learning_rate": 6.764401570297239e-06,
"loss": 0.4579,
"step": 1885
},
{
"epoch": 1.85,
"learning_rate": 6.754330212950984e-06,
"loss": 0.4078,
"step": 1886
},
{
"epoch": 1.85,
"learning_rate": 6.744262534061173e-06,
"loss": 0.3594,
"step": 1887
},
{
"epoch": 1.86,
"learning_rate": 6.734198545037935e-06,
"loss": 0.5472,
"step": 1888
},
{
"epoch": 1.86,
"learning_rate": 6.724138257287227e-06,
"loss": 0.6798,
"step": 1889
},
{
"epoch": 1.86,
"learning_rate": 6.7140816822108e-06,
"loss": 0.6619,
"step": 1890
},
{
"epoch": 1.86,
"learning_rate": 6.704028831206197e-06,
"loss": 0.4327,
"step": 1891
},
{
"epoch": 1.86,
"learning_rate": 6.693979715666753e-06,
"loss": 0.5912,
"step": 1892
},
{
"epoch": 1.86,
"learning_rate": 6.683934346981553e-06,
"loss": 0.4366,
"step": 1893
},
{
"epoch": 1.86,
"learning_rate": 6.673892736535448e-06,
"loss": 0.521,
"step": 1894
},
{
"epoch": 1.86,
"learning_rate": 6.663854895709017e-06,
"loss": 0.4728,
"step": 1895
},
{
"epoch": 1.86,
"learning_rate": 6.653820835878584e-06,
"loss": 0.4916,
"step": 1896
},
{
"epoch": 1.86,
"learning_rate": 6.643790568416173e-06,
"loss": 0.4972,
"step": 1897
},
{
"epoch": 1.86,
"learning_rate": 6.6337641046895155e-06,
"loss": 0.542,
"step": 1898
},
{
"epoch": 1.87,
"learning_rate": 6.6237414560620335e-06,
"loss": 0.4949,
"step": 1899
},
{
"epoch": 1.87,
"learning_rate": 6.613722633892826e-06,
"loss": 0.4365,
"step": 1900
},
{
"epoch": 1.87,
"learning_rate": 6.603707649536647e-06,
"loss": 0.6086,
"step": 1901
},
{
"epoch": 1.87,
"learning_rate": 6.593696514343908e-06,
"loss": 0.4017,
"step": 1902
},
{
"epoch": 1.87,
"learning_rate": 6.583689239660663e-06,
"loss": 0.4984,
"step": 1903
},
{
"epoch": 1.87,
"learning_rate": 6.573685836828578e-06,
"loss": 0.3969,
"step": 1904
},
{
"epoch": 1.87,
"learning_rate": 6.563686317184937e-06,
"loss": 0.4314,
"step": 1905
},
{
"epoch": 1.87,
"learning_rate": 6.553690692062626e-06,
"loss": 0.4847,
"step": 1906
},
{
"epoch": 1.87,
"learning_rate": 6.543698972790118e-06,
"loss": 0.3494,
"step": 1907
},
{
"epoch": 1.87,
"learning_rate": 6.533711170691453e-06,
"loss": 0.3805,
"step": 1908
},
{
"epoch": 1.88,
"learning_rate": 6.52372729708623e-06,
"loss": 0.5161,
"step": 1909
},
{
"epoch": 1.88,
"learning_rate": 6.513747363289606e-06,
"loss": 0.4517,
"step": 1910
},
{
"epoch": 1.88,
"learning_rate": 6.503771380612267e-06,
"loss": 0.3866,
"step": 1911
},
{
"epoch": 1.88,
"learning_rate": 6.493799360360414e-06,
"loss": 0.4871,
"step": 1912
},
{
"epoch": 1.88,
"learning_rate": 6.483831313835776e-06,
"loss": 0.4364,
"step": 1913
},
{
"epoch": 1.88,
"learning_rate": 6.4738672523355565e-06,
"loss": 0.4856,
"step": 1914
},
{
"epoch": 1.88,
"learning_rate": 6.463907187152458e-06,
"loss": 0.7935,
"step": 1915
},
{
"epoch": 1.88,
"learning_rate": 6.453951129574644e-06,
"loss": 0.5483,
"step": 1916
},
{
"epoch": 1.88,
"learning_rate": 6.443999090885746e-06,
"loss": 0.4697,
"step": 1917
},
{
"epoch": 1.88,
"learning_rate": 6.434051082364832e-06,
"loss": 0.57,
"step": 1918
},
{
"epoch": 1.89,
"learning_rate": 6.424107115286404e-06,
"loss": 0.3966,
"step": 1919
},
{
"epoch": 1.89,
"learning_rate": 6.414167200920392e-06,
"loss": 0.4919,
"step": 1920
},
{
"epoch": 1.89,
"eval_loss": 0.634874701499939,
"eval_runtime": 92.1298,
"eval_samples_per_second": 21.709,
"eval_steps_per_second": 10.854,
"step": 1920
},
{
"epoch": 1.89,
"learning_rate": 6.404231350532122e-06,
"loss": 0.4639,
"step": 1921
},
{
"epoch": 1.89,
"learning_rate": 6.3942995753823165e-06,
"loss": 0.4586,
"step": 1922
},
{
"epoch": 1.89,
"learning_rate": 6.384371886727083e-06,
"loss": 0.5213,
"step": 1923
},
{
"epoch": 1.89,
"learning_rate": 6.3744482958178966e-06,
"loss": 0.3802,
"step": 1924
},
{
"epoch": 1.89,
"learning_rate": 6.364528813901587e-06,
"loss": 0.4894,
"step": 1925
},
{
"epoch": 1.89,
"learning_rate": 6.354613452220326e-06,
"loss": 0.5513,
"step": 1926
},
{
"epoch": 1.89,
"learning_rate": 6.344702222011621e-06,
"loss": 0.4721,
"step": 1927
},
{
"epoch": 1.89,
"learning_rate": 6.3347951345082895e-06,
"loss": 0.4272,
"step": 1928
},
{
"epoch": 1.9,
"learning_rate": 6.324892200938461e-06,
"loss": 0.5397,
"step": 1929
},
{
"epoch": 1.9,
"learning_rate": 6.314993432525547e-06,
"loss": 0.3788,
"step": 1930
},
{
"epoch": 1.9,
"learning_rate": 6.305098840488255e-06,
"loss": 0.5098,
"step": 1931
},
{
"epoch": 1.9,
"learning_rate": 6.295208436040543e-06,
"loss": 0.4564,
"step": 1932
},
{
"epoch": 1.9,
"learning_rate": 6.285322230391629e-06,
"loss": 0.423,
"step": 1933
},
{
"epoch": 1.9,
"learning_rate": 6.2754402347459795e-06,
"loss": 0.4401,
"step": 1934
},
{
"epoch": 1.9,
"learning_rate": 6.265562460303278e-06,
"loss": 0.5725,
"step": 1935
},
{
"epoch": 1.9,
"learning_rate": 6.255688918258429e-06,
"loss": 0.4069,
"step": 1936
},
{
"epoch": 1.9,
"learning_rate": 6.245819619801538e-06,
"loss": 0.5554,
"step": 1937
},
{
"epoch": 1.9,
"learning_rate": 6.23595457611791e-06,
"loss": 0.3837,
"step": 1938
},
{
"epoch": 1.91,
"learning_rate": 6.226093798388017e-06,
"loss": 0.4609,
"step": 1939
},
{
"epoch": 1.91,
"learning_rate": 6.216237297787495e-06,
"loss": 0.5702,
"step": 1940
},
{
"epoch": 1.91,
"learning_rate": 6.206385085487148e-06,
"loss": 0.6164,
"step": 1941
},
{
"epoch": 1.91,
"learning_rate": 6.196537172652905e-06,
"loss": 0.4971,
"step": 1942
},
{
"epoch": 1.91,
"learning_rate": 6.186693570445829e-06,
"loss": 0.3596,
"step": 1943
},
{
"epoch": 1.91,
"learning_rate": 6.176854290022087e-06,
"loss": 0.4854,
"step": 1944
},
{
"epoch": 1.91,
"learning_rate": 6.167019342532967e-06,
"loss": 0.4268,
"step": 1945
},
{
"epoch": 1.91,
"learning_rate": 6.157188739124834e-06,
"loss": 0.3915,
"step": 1946
},
{
"epoch": 1.91,
"learning_rate": 6.147362490939128e-06,
"loss": 0.5091,
"step": 1947
},
{
"epoch": 1.91,
"learning_rate": 6.137540609112356e-06,
"loss": 0.3956,
"step": 1948
},
{
"epoch": 1.92,
"learning_rate": 6.12772310477608e-06,
"loss": 0.3391,
"step": 1949
},
{
"epoch": 1.92,
"learning_rate": 6.117909989056899e-06,
"loss": 0.4569,
"step": 1950
},
{
"epoch": 1.92,
"learning_rate": 6.1081012730764285e-06,
"loss": 0.5229,
"step": 1951
},
{
"epoch": 1.92,
"learning_rate": 6.098296967951318e-06,
"loss": 0.4189,
"step": 1952
},
{
"epoch": 1.92,
"learning_rate": 6.088497084793197e-06,
"loss": 0.3107,
"step": 1953
},
{
"epoch": 1.92,
"learning_rate": 6.0787016347086995e-06,
"loss": 0.5258,
"step": 1954
},
{
"epoch": 1.92,
"learning_rate": 6.068910628799418e-06,
"loss": 0.5835,
"step": 1955
},
{
"epoch": 1.92,
"learning_rate": 6.059124078161929e-06,
"loss": 0.4095,
"step": 1956
},
{
"epoch": 1.92,
"learning_rate": 6.049341993887743e-06,
"loss": 0.3731,
"step": 1957
},
{
"epoch": 1.92,
"learning_rate": 6.039564387063315e-06,
"loss": 0.4466,
"step": 1958
},
{
"epoch": 1.92,
"learning_rate": 6.029791268770029e-06,
"loss": 0.3982,
"step": 1959
},
{
"epoch": 1.93,
"learning_rate": 6.020022650084176e-06,
"loss": 0.5393,
"step": 1960
},
{
"epoch": 1.93,
"learning_rate": 6.0102585420769475e-06,
"loss": 0.4372,
"step": 1961
},
{
"epoch": 1.93,
"learning_rate": 6.000498955814426e-06,
"loss": 0.519,
"step": 1962
},
{
"epoch": 1.93,
"learning_rate": 5.990743902357571e-06,
"loss": 0.3683,
"step": 1963
},
{
"epoch": 1.93,
"learning_rate": 5.9809933927622e-06,
"loss": 0.4062,
"step": 1964
},
{
"epoch": 1.93,
"learning_rate": 5.97124743807898e-06,
"loss": 0.5382,
"step": 1965
},
{
"epoch": 1.93,
"learning_rate": 5.96150604935342e-06,
"loss": 0.4759,
"step": 1966
},
{
"epoch": 1.93,
"learning_rate": 5.951769237625859e-06,
"loss": 0.5999,
"step": 1967
},
{
"epoch": 1.93,
"learning_rate": 5.942037013931434e-06,
"loss": 0.3666,
"step": 1968
},
{
"epoch": 1.93,
"learning_rate": 5.932309389300092e-06,
"loss": 0.4967,
"step": 1969
},
{
"epoch": 1.94,
"learning_rate": 5.922586374756568e-06,
"loss": 0.4625,
"step": 1970
},
{
"epoch": 1.94,
"learning_rate": 5.912867981320374e-06,
"loss": 0.5251,
"step": 1971
},
{
"epoch": 1.94,
"learning_rate": 5.903154220005771e-06,
"loss": 0.5449,
"step": 1972
},
{
"epoch": 1.94,
"learning_rate": 5.8934451018217916e-06,
"loss": 0.5532,
"step": 1973
},
{
"epoch": 1.94,
"learning_rate": 5.883740637772188e-06,
"loss": 0.519,
"step": 1974
},
{
"epoch": 1.94,
"learning_rate": 5.874040838855448e-06,
"loss": 0.3675,
"step": 1975
},
{
"epoch": 1.94,
"learning_rate": 5.8643457160647634e-06,
"loss": 0.4076,
"step": 1976
},
{
"epoch": 1.94,
"learning_rate": 5.85465528038804e-06,
"loss": 0.4484,
"step": 1977
},
{
"epoch": 1.94,
"learning_rate": 5.844969542807856e-06,
"loss": 0.4233,
"step": 1978
},
{
"epoch": 1.94,
"learning_rate": 5.835288514301473e-06,
"loss": 0.5404,
"step": 1979
},
{
"epoch": 1.95,
"learning_rate": 5.825612205840822e-06,
"loss": 0.5092,
"step": 1980
},
{
"epoch": 1.95,
"learning_rate": 5.815940628392469e-06,
"loss": 0.442,
"step": 1981
},
{
"epoch": 1.95,
"learning_rate": 5.806273792917629e-06,
"loss": 0.3897,
"step": 1982
},
{
"epoch": 1.95,
"learning_rate": 5.796611710372142e-06,
"loss": 0.4621,
"step": 1983
},
{
"epoch": 1.95,
"learning_rate": 5.786954391706458e-06,
"loss": 0.3411,
"step": 1984
},
{
"epoch": 1.95,
"eval_loss": 0.633979320526123,
"eval_runtime": 92.1205,
"eval_samples_per_second": 21.711,
"eval_steps_per_second": 10.855,
"step": 1984
}
],
"logging_steps": 1,
"max_steps": 3051,
"num_train_epochs": 3,
"save_steps": 64,
"total_flos": 5.809085963833442e+18,
"trial_name": null,
"trial_params": null
}