{
  "best_metric": 1.6580705642700195,
  "best_model_checkpoint": "/scratch/kwamea/llama-output/checkpoint-700",
  "epoch": 1.9023136246786634,
  "eval_steps": 5,
  "global_step": 740,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 9.93573264781491e-05,
      "loss": 1.9824,
      "step": 5
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.954728126525879,
      "eval_runtime": 31.6803,
      "eval_samples_per_second": 2.651,
      "eval_steps_per_second": 0.347,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.87146529562982e-05,
      "loss": 1.9249,
      "step": 10
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.8934264183044434,
      "eval_runtime": 31.7798,
      "eval_samples_per_second": 2.643,
      "eval_steps_per_second": 0.346,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.80719794344473e-05,
      "loss": 1.8609,
      "step": 15
    },
    {
      "epoch": 0.04,
      "eval_loss": 1.8421852588653564,
      "eval_runtime": 31.7999,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.742930591259641e-05,
      "loss": 1.8268,
      "step": 20
    },
    {
      "epoch": 0.05,
      "eval_loss": 1.8279638290405273,
      "eval_runtime": 31.8095,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.67866323907455e-05,
      "loss": 1.8349,
      "step": 25
    },
    {
      "epoch": 0.06,
      "eval_loss": 1.813267469406128,
      "eval_runtime": 31.8291,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 25
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.61439588688946e-05,
      "loss": 1.8239,
      "step": 30
    },
    {
      "epoch": 0.08,
      "eval_loss": 1.8008779287338257,
      "eval_runtime": 31.82,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.550128534704372e-05,
      "loss": 1.7177,
      "step": 35
    },
    {
      "epoch": 0.09,
      "eval_loss": 1.789797067642212,
      "eval_runtime": 31.8423,
      "eval_samples_per_second": 2.638,
      "eval_steps_per_second": 0.345,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.485861182519281e-05,
      "loss": 1.7962,
      "step": 40
    },
    {
      "epoch": 0.1,
      "eval_loss": 1.7808287143707275,
      "eval_runtime": 31.8387,
      "eval_samples_per_second": 2.638,
      "eval_steps_per_second": 0.345,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.421593830334192e-05,
      "loss": 1.715,
      "step": 45
    },
    {
      "epoch": 0.12,
      "eval_loss": 1.771236777305603,
      "eval_runtime": 31.8526,
      "eval_samples_per_second": 2.637,
      "eval_steps_per_second": 0.345,
      "step": 45
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.357326478149101e-05,
      "loss": 1.7577,
      "step": 50
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.7619521617889404,
      "eval_runtime": 31.828,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.29305912596401e-05,
      "loss": 1.7323,
      "step": 55
    },
    {
      "epoch": 0.14,
      "eval_loss": 1.7440986633300781,
      "eval_runtime": 31.8301,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 55
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.228791773778921e-05,
      "loss": 1.7122,
      "step": 60
    },
    {
      "epoch": 0.15,
      "eval_loss": 1.712996006011963,
      "eval_runtime": 31.8185,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.16452442159383e-05,
      "loss": 1.7042,
      "step": 65
    },
    {
      "epoch": 0.17,
      "eval_loss": 1.7101707458496094,
      "eval_runtime": 31.8153,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 65
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.100257069408741e-05,
      "loss": 1.7242,
      "step": 70
    },
    {
      "epoch": 0.18,
      "eval_loss": 1.7038702964782715,
      "eval_runtime": 31.8191,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 70
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.03598971722365e-05,
      "loss": 1.7033,
      "step": 75
    },
    {
      "epoch": 0.19,
      "eval_loss": 1.7004183530807495,
      "eval_runtime": 31.811,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 75
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.97172236503856e-05,
      "loss": 1.6934,
      "step": 80
    },
    {
      "epoch": 0.21,
      "eval_loss": 1.6985355615615845,
      "eval_runtime": 31.8221,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 80
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.907455012853471e-05,
      "loss": 1.6443,
      "step": 85
    },
    {
      "epoch": 0.22,
      "eval_loss": 1.696852684020996,
      "eval_runtime": 31.8219,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 85
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.84318766066838e-05,
      "loss": 1.7008,
      "step": 90
    },
    {
      "epoch": 0.23,
      "eval_loss": 1.695594072341919,
      "eval_runtime": 31.8205,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 90
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.778920308483291e-05,
      "loss": 1.6873,
      "step": 95
    },
    {
      "epoch": 0.24,
      "eval_loss": 1.6928850412368774,
      "eval_runtime": 31.814,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 95
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.7146529562982e-05,
      "loss": 1.6721,
      "step": 100
    },
    {
      "epoch": 0.26,
      "eval_loss": 1.6919386386871338,
      "eval_runtime": 31.8127,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 8.650385604113111e-05,
      "loss": 1.6669,
      "step": 105
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.6905940771102905,
      "eval_runtime": 31.8874,
      "eval_samples_per_second": 2.634,
      "eval_steps_per_second": 0.345,
      "step": 105
    },
    {
      "epoch": 0.28,
      "learning_rate": 8.586118251928022e-05,
      "loss": 1.7009,
      "step": 110
    },
    {
      "epoch": 0.28,
      "eval_loss": 1.689422607421875,
      "eval_runtime": 31.8489,
      "eval_samples_per_second": 2.637,
      "eval_steps_per_second": 0.345,
      "step": 110
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.521850899742931e-05,
      "loss": 1.7151,
      "step": 115
    },
    {
      "epoch": 0.3,
      "eval_loss": 1.688527226448059,
      "eval_runtime": 31.8318,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 115
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.457583547557842e-05,
      "loss": 1.7165,
      "step": 120
    },
    {
      "epoch": 0.31,
      "eval_loss": 1.686748743057251,
      "eval_runtime": 31.835,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 120
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.393316195372751e-05,
      "loss": 1.7015,
      "step": 125
    },
    {
      "epoch": 0.32,
      "eval_loss": 1.6855812072753906,
      "eval_runtime": 31.8269,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 125
    },
    {
      "epoch": 0.33,
      "learning_rate": 8.32904884318766e-05,
      "loss": 1.6818,
      "step": 130
    },
    {
      "epoch": 0.33,
      "eval_loss": 1.6846078634262085,
      "eval_runtime": 31.8617,
      "eval_samples_per_second": 2.636,
      "eval_steps_per_second": 0.345,
      "step": 130
    },
    {
      "epoch": 0.35,
      "learning_rate": 8.264781491002571e-05,
      "loss": 1.7151,
      "step": 135
    },
    {
      "epoch": 0.35,
      "eval_loss": 1.6845166683197021,
      "eval_runtime": 31.8631,
      "eval_samples_per_second": 2.636,
      "eval_steps_per_second": 0.345,
      "step": 135
    },
    {
      "epoch": 0.36,
      "learning_rate": 8.200514138817481e-05,
      "loss": 1.6667,
      "step": 140
    },
    {
      "epoch": 0.36,
      "eval_loss": 1.6832246780395508,
      "eval_runtime": 31.8276,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 140
    },
    {
      "epoch": 0.37,
      "learning_rate": 8.136246786632391e-05,
      "loss": 1.6586,
      "step": 145
    },
    {
      "epoch": 0.37,
      "eval_loss": 1.6824573278427124,
      "eval_runtime": 31.8115,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 145
    },
    {
      "epoch": 0.39,
      "learning_rate": 8.071979434447301e-05,
      "loss": 1.6999,
      "step": 150
    },
    {
      "epoch": 0.39,
      "eval_loss": 1.681317687034607,
      "eval_runtime": 31.805,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 150
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.007712082262212e-05,
      "loss": 1.6894,
      "step": 155
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.6812355518341064,
      "eval_runtime": 31.8039,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 155
    },
    {
      "epoch": 0.41,
      "learning_rate": 7.943444730077121e-05,
      "loss": 1.6669,
      "step": 160
    },
    {
      "epoch": 0.41,
      "eval_loss": 1.679802656173706,
      "eval_runtime": 31.8021,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 160
    },
    {
      "epoch": 0.42,
      "learning_rate": 7.87917737789203e-05,
      "loss": 1.6481,
      "step": 165
    },
    {
      "epoch": 0.42,
      "eval_loss": 1.679994821548462,
      "eval_runtime": 31.8201,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 165
    },
    {
      "epoch": 0.44,
      "learning_rate": 7.814910025706941e-05,
      "loss": 1.7042,
      "step": 170
    },
    {
      "epoch": 0.44,
      "eval_loss": 1.6786224842071533,
      "eval_runtime": 31.8184,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 170
    },
    {
      "epoch": 0.45,
      "learning_rate": 7.750642673521852e-05,
      "loss": 1.6564,
      "step": 175
    },
    {
      "epoch": 0.45,
      "eval_loss": 1.6783201694488525,
      "eval_runtime": 31.8137,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 175
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.686375321336761e-05,
      "loss": 1.6714,
      "step": 180
    },
    {
      "epoch": 0.46,
      "eval_loss": 1.677714228630066,
      "eval_runtime": 31.804,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 180
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.622107969151672e-05,
      "loss": 1.6705,
      "step": 185
    },
    {
      "epoch": 0.48,
      "eval_loss": 1.6772773265838623,
      "eval_runtime": 31.8077,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 185
    },
    {
      "epoch": 0.49,
      "learning_rate": 7.557840616966581e-05,
      "loss": 1.6624,
      "step": 190
    },
    {
      "epoch": 0.49,
      "eval_loss": 1.6766114234924316,
      "eval_runtime": 31.8164,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 190
    },
    {
      "epoch": 0.5,
      "learning_rate": 7.493573264781492e-05,
      "loss": 1.6415,
      "step": 195
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.675940752029419,
      "eval_runtime": 31.8124,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 195
    },
    {
      "epoch": 0.51,
      "learning_rate": 7.429305912596401e-05,
      "loss": 1.6633,
      "step": 200
    },
    {
      "epoch": 0.51,
      "eval_loss": 1.6751865148544312,
      "eval_runtime": 31.8123,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 200
    },
    {
      "epoch": 0.53,
      "learning_rate": 7.365038560411311e-05,
      "loss": 1.6142,
      "step": 205
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.6750575304031372,
      "eval_runtime": 31.8049,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 205
    },
    {
      "epoch": 0.54,
      "learning_rate": 7.300771208226222e-05,
      "loss": 1.6736,
      "step": 210
    },
    {
      "epoch": 0.54,
      "eval_loss": 1.6746423244476318,
      "eval_runtime": 31.8111,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 210
    },
    {
      "epoch": 0.55,
      "learning_rate": 7.236503856041131e-05,
      "loss": 1.6414,
      "step": 215
    },
    {
      "epoch": 0.55,
      "eval_loss": 1.6740491390228271,
      "eval_runtime": 31.8083,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 215
    },
    {
      "epoch": 0.57,
      "learning_rate": 7.172236503856042e-05,
      "loss": 1.6725,
      "step": 220
    },
    {
      "epoch": 0.57,
      "eval_loss": 1.673694372177124,
      "eval_runtime": 31.8025,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 220
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.107969151670951e-05,
      "loss": 1.679,
      "step": 225
    },
    {
      "epoch": 0.58,
      "eval_loss": 1.6733818054199219,
      "eval_runtime": 31.8077,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 225
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.043701799485862e-05,
      "loss": 1.7204,
      "step": 230
    },
    {
      "epoch": 0.59,
      "eval_loss": 1.6725033521652222,
      "eval_runtime": 31.8079,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 230
    },
    {
      "epoch": 0.6,
      "learning_rate": 6.979434447300771e-05,
      "loss": 1.6816,
      "step": 235
    },
    {
      "epoch": 0.6,
      "eval_loss": 1.67205011844635,
      "eval_runtime": 31.809,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 235
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.91516709511568e-05,
      "loss": 1.634,
      "step": 240
    },
    {
      "epoch": 0.62,
      "eval_loss": 1.6717994213104248,
      "eval_runtime": 31.8075,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 240
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.850899742930593e-05,
      "loss": 1.6761,
      "step": 245
    },
    {
      "epoch": 0.63,
      "eval_loss": 1.6714757680892944,
      "eval_runtime": 31.8052,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 245
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.786632390745502e-05,
      "loss": 1.6996,
      "step": 250
    },
    {
      "epoch": 0.64,
      "eval_loss": 1.671559453010559,
      "eval_runtime": 31.8089,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 250
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.722365038560411e-05,
      "loss": 1.6302,
      "step": 255
    },
    {
      "epoch": 0.66,
      "eval_loss": 1.6711652278900146,
      "eval_runtime": 31.8105,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 255
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.658097686375322e-05,
      "loss": 1.6611,
      "step": 260
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.6704061031341553,
      "eval_runtime": 31.8135,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 260
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.593830334190231e-05,
      "loss": 1.6586,
      "step": 265
    },
    {
      "epoch": 0.68,
      "eval_loss": 1.6705658435821533,
      "eval_runtime": 31.7998,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 265
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.529562982005142e-05,
      "loss": 1.6838,
      "step": 270
    },
    {
      "epoch": 0.69,
      "eval_loss": 1.6697953939437866,
      "eval_runtime": 31.7994,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 270
    },
    {
      "epoch": 0.71,
      "learning_rate": 6.465295629820052e-05,
      "loss": 1.6499,
      "step": 275
    },
    {
      "epoch": 0.71,
      "eval_loss": 1.669343113899231,
      "eval_runtime": 31.8147,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 275
    },
    {
      "epoch": 0.72,
      "learning_rate": 6.401028277634962e-05,
      "loss": 1.6424,
      "step": 280
    },
    {
      "epoch": 0.72,
      "eval_loss": 1.6693596839904785,
      "eval_runtime": 31.8155,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 280
    },
    {
      "epoch": 0.73,
      "learning_rate": 6.336760925449872e-05,
      "loss": 1.6238,
      "step": 285
    },
    {
      "epoch": 0.73,
      "eval_loss": 1.669128179550171,
      "eval_runtime": 31.8219,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 285
    },
    {
      "epoch": 0.75,
      "learning_rate": 6.272493573264781e-05,
      "loss": 1.6538,
      "step": 290
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.6691263914108276,
      "eval_runtime": 31.81,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 290
    },
    {
      "epoch": 0.76,
      "learning_rate": 6.208226221079692e-05,
      "loss": 1.656,
      "step": 295
    },
    {
      "epoch": 0.76,
      "eval_loss": 1.66847825050354,
      "eval_runtime": 31.7918,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 295
    },
    {
      "epoch": 0.77,
      "learning_rate": 6.143958868894601e-05,
      "loss": 1.6407,
      "step": 300
    },
    {
      "epoch": 0.77,
      "eval_loss": 1.6683858633041382,
      "eval_runtime": 31.8114,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 300
    },
    {
      "epoch": 0.78,
      "learning_rate": 6.079691516709511e-05,
      "loss": 1.6468,
      "step": 305
    },
    {
      "epoch": 0.78,
      "eval_loss": 1.6678352355957031,
      "eval_runtime": 31.7975,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 305
    },
    {
      "epoch": 0.8,
      "learning_rate": 6.015424164524421e-05,
      "loss": 1.6579,
      "step": 310
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.6675294637680054,
      "eval_runtime": 31.8059,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 310
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.951156812339333e-05,
      "loss": 1.6331,
      "step": 315
    },
    {
      "epoch": 0.81,
      "eval_loss": 1.6670397520065308,
      "eval_runtime": 31.7994,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 315
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.886889460154242e-05,
      "loss": 1.6634,
      "step": 320
    },
    {
      "epoch": 0.82,
      "eval_loss": 1.6668330430984497,
      "eval_runtime": 31.807,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 320
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.822622107969152e-05,
      "loss": 1.6406,
      "step": 325
    },
    {
      "epoch": 0.84,
      "eval_loss": 1.6668546199798584,
      "eval_runtime": 31.8004,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 325
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.758354755784062e-05,
      "loss": 1.6614,
      "step": 330
    },
    {
      "epoch": 0.85,
      "eval_loss": 1.666812539100647,
      "eval_runtime": 31.8023,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 330
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.694087403598972e-05,
      "loss": 1.6598,
      "step": 335
    },
    {
      "epoch": 0.86,
      "eval_loss": 1.666398048400879,
      "eval_runtime": 31.8087,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 335
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.6298200514138824e-05,
      "loss": 1.6698,
      "step": 340
    },
    {
      "epoch": 0.87,
      "eval_loss": 1.6660391092300415,
      "eval_runtime": 31.8016,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 340
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.5655526992287924e-05,
      "loss": 1.6346,
      "step": 345
    },
    {
      "epoch": 0.89,
      "eval_loss": 1.665901780128479,
      "eval_runtime": 31.7878,
      "eval_samples_per_second": 2.643,
      "eval_steps_per_second": 0.346,
      "step": 345
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.501285347043702e-05,
      "loss": 1.6617,
      "step": 350
    },
    {
      "epoch": 0.9,
      "eval_loss": 1.666027307510376,
      "eval_runtime": 31.7999,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 350
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.437017994858612e-05,
      "loss": 1.6623,
      "step": 355
    },
    {
      "epoch": 0.91,
      "eval_loss": 1.6658612489700317,
      "eval_runtime": 31.8128,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 355
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.372750642673522e-05,
      "loss": 1.6737,
      "step": 360
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.6656837463378906,
      "eval_runtime": 31.8094,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 360
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.308483290488432e-05,
      "loss": 1.6981,
      "step": 365
    },
    {
      "epoch": 0.94,
      "eval_loss": 1.6653661727905273,
      "eval_runtime": 31.8031,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 365
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.244215938303342e-05,
      "loss": 1.6832,
      "step": 370
    },
    {
      "epoch": 0.95,
      "eval_loss": 1.6652257442474365,
      "eval_runtime": 31.8077,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 370
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.1799485861182514e-05,
      "loss": 1.6925,
      "step": 375
    },
    {
      "epoch": 0.96,
      "eval_loss": 1.664839267730713,
      "eval_runtime": 31.8082,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 375
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.1156812339331615e-05,
      "loss": 1.6721,
      "step": 380
    },
    {
      "epoch": 0.98,
      "eval_loss": 1.6642415523529053,
      "eval_runtime": 31.7927,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 380
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.051413881748073e-05,
      "loss": 1.6208,
      "step": 385
    },
    {
      "epoch": 0.99,
      "eval_loss": 1.6641273498535156,
      "eval_runtime": 31.8006,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 385
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.987146529562982e-05,
      "loss": 1.6519,
      "step": 390
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6645455360412598,
      "eval_runtime": 31.8026,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 390
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.922879177377892e-05,
      "loss": 1.6581,
      "step": 395
    },
    {
      "epoch": 1.02,
      "eval_loss": 1.6641591787338257,
      "eval_runtime": 31.8025,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 395
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.8586118251928024e-05,
      "loss": 1.6768,
      "step": 400
    },
    {
      "epoch": 1.03,
      "eval_loss": 1.6637850999832153,
      "eval_runtime": 31.806,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 400
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.7943444730077124e-05,
      "loss": 1.6257,
      "step": 405
    },
    {
      "epoch": 1.04,
      "eval_loss": 1.6636526584625244,
      "eval_runtime": 31.8116,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 405
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.7300771208226225e-05,
      "loss": 1.6522,
      "step": 410
    },
    {
      "epoch": 1.05,
      "eval_loss": 1.6634690761566162,
      "eval_runtime": 31.8063,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 410
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.6658097686375325e-05,
      "loss": 1.615,
      "step": 415
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.6637413501739502,
      "eval_runtime": 31.8115,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 415
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.6015424164524426e-05,
      "loss": 1.5967,
      "step": 420
    },
    {
      "epoch": 1.08,
      "eval_loss": 1.6633188724517822,
      "eval_runtime": 31.8016,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 420
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.537275064267352e-05,
      "loss": 1.6708,
      "step": 425
    },
    {
      "epoch": 1.09,
      "eval_loss": 1.6634286642074585,
      "eval_runtime": 31.8074,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 425
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.473007712082262e-05,
      "loss": 1.6696,
      "step": 430
    },
    {
      "epoch": 1.11,
      "eval_loss": 1.663163661956787,
      "eval_runtime": 31.799,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 430
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.408740359897173e-05,
      "loss": 1.6344,
      "step": 435
    },
    {
      "epoch": 1.12,
      "eval_loss": 1.6632493734359741,
      "eval_runtime": 31.8032,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 435
    },
    {
      "epoch": 1.13,
      "learning_rate": 4.344473007712083e-05,
      "loss": 1.5922,
      "step": 440
    },
    {
      "epoch": 1.13,
      "eval_loss": 1.6627737283706665,
      "eval_runtime": 31.8064,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 440
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.280205655526993e-05,
      "loss": 1.6541,
      "step": 445
    },
    {
      "epoch": 1.14,
      "eval_loss": 1.6630815267562866,
      "eval_runtime": 31.8083,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 445
    },
    {
      "epoch": 1.16,
      "learning_rate": 4.215938303341902e-05,
      "loss": 1.6348,
      "step": 450
    },
    {
      "epoch": 1.16,
      "eval_loss": 1.662713885307312,
      "eval_runtime": 31.7977,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 450
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.151670951156812e-05,
      "loss": 1.6444,
      "step": 455
    },
    {
      "epoch": 1.17,
      "eval_loss": 1.6629937887191772,
      "eval_runtime": 31.799,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 455
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.0874035989717224e-05,
      "loss": 1.6629,
      "step": 460
    },
    {
      "epoch": 1.18,
      "eval_loss": 1.6626592874526978,
      "eval_runtime": 31.8136,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 460
    },
    {
      "epoch": 1.2,
      "learning_rate": 4.0231362467866324e-05,
      "loss": 1.6327,
      "step": 465
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.6625391244888306,
      "eval_runtime": 31.802,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 465
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.958868894601543e-05,
      "loss": 1.6236,
      "step": 470
    },
    {
      "epoch": 1.21,
      "eval_loss": 1.6622934341430664,
      "eval_runtime": 31.8055,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 470
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.8946015424164526e-05,
      "loss": 1.6232,
      "step": 475
    },
    {
      "epoch": 1.22,
      "eval_loss": 1.661791443824768,
      "eval_runtime": 31.8035,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 475
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.8303341902313626e-05,
      "loss": 1.6374,
      "step": 480
    },
    {
      "epoch": 1.23,
      "eval_loss": 1.6618887186050415,
      "eval_runtime": 31.7892,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 480
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.766066838046273e-05,
      "loss": 1.6422,
      "step": 485
    },
    {
      "epoch": 1.25,
      "eval_loss": 1.6620476245880127,
      "eval_runtime": 31.7974,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 485
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.701799485861183e-05,
      "loss": 1.631,
      "step": 490
    },
    {
      "epoch": 1.26,
      "eval_loss": 1.6622774600982666,
      "eval_runtime": 31.7978,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 490
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.637532133676093e-05,
      "loss": 1.609,
      "step": 495
    },
    {
      "epoch": 1.27,
      "eval_loss": 1.661568284034729,
      "eval_runtime": 31.8034,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 495
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.573264781491003e-05,
      "loss": 1.6444,
      "step": 500
    },
    {
      "epoch": 1.29,
      "eval_loss": 1.6610949039459229,
      "eval_runtime": 31.8005,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 500
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.508997429305913e-05,
      "loss": 1.6387,
      "step": 505
    },
    {
      "epoch": 1.3,
      "eval_loss": 1.6611486673355103,
      "eval_runtime": 31.8079,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 505
    },
    {
      "epoch": 1.31,
      "learning_rate": 3.444730077120823e-05,
      "loss": 1.6507,
      "step": 510
    },
    {
      "epoch": 1.31,
      "eval_loss": 1.661084532737732,
      "eval_runtime": 31.8028,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 510
    },
    {
      "epoch": 1.32,
      "learning_rate": 3.380462724935733e-05,
      "loss": 1.6377,
      "step": 515
    },
    {
      "epoch": 1.32,
      "eval_loss": 1.6610103845596313,
      "eval_runtime": 31.8101,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 515
    },
    {
      "epoch": 1.34,
      "learning_rate": 3.316195372750643e-05,
      "loss": 1.6351,
      "step": 520
    },
    {
      "epoch": 1.34,
      "eval_loss": 1.6608690023422241,
      "eval_runtime": 31.7986,
      "eval_samples_per_second": 2.642,
      "eval_steps_per_second": 0.346,
      "step": 520
    },
    {
      "epoch": 1.35,
      "learning_rate": 3.251928020565553e-05,
      "loss": 1.6196,
      "step": 525
    },
    {
      "epoch": 1.35,
      "eval_loss": 1.6606587171554565,
      "eval_runtime": 31.8015,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 525
    },
    {
      "epoch": 1.36,
      "learning_rate": 3.1876606683804625e-05,
      "loss": 1.646,
      "step": 530
    },
    {
      "epoch": 1.36,
      "eval_loss": 1.6605886220932007,
      "eval_runtime": 31.804,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 530
    },
    {
      "epoch": 1.38,
      "learning_rate": 3.1233933161953726e-05,
      "loss": 1.6824,
      "step": 535
    },
    {
      "epoch": 1.38,
      "eval_loss": 1.6603879928588867,
      "eval_runtime": 31.8111,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 535
    },
    {
      "epoch": 1.39,
      "learning_rate": 3.059125964010283e-05,
      "loss": 1.6115,
      "step": 540
    },
    {
      "epoch": 1.39,
      "eval_loss": 1.660337209701538,
      "eval_runtime": 31.805,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 540
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.994858611825193e-05,
      "loss": 1.6243,
      "step": 545
    },
    {
      "epoch": 1.4,
      "eval_loss": 1.6606225967407227,
      "eval_runtime": 31.808,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 545
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.930591259640103e-05,
      "loss": 1.6486,
      "step": 550
    },
    {
      "epoch": 1.41,
      "eval_loss": 1.6604374647140503,
      "eval_runtime": 31.8072,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 550
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.866323907455013e-05,
      "loss": 1.6865,
      "step": 555
    },
    {
      "epoch": 1.43,
      "eval_loss": 1.6601544618606567,
      "eval_runtime": 31.8069,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 555
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.802056555269923e-05,
      "loss": 1.6616,
      "step": 560
    },
    {
      "epoch": 1.44,
      "eval_loss": 1.660386562347412,
      "eval_runtime": 31.803,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 560
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.737789203084833e-05,
      "loss": 1.6336,
      "step": 565
    },
    {
      "epoch": 1.45,
      "eval_loss": 1.660247802734375,
      "eval_runtime": 31.8084,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 565
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.673521850899743e-05,
      "loss": 1.6699,
      "step": 570
    },
    {
      "epoch": 1.47,
      "eval_loss": 1.660292148590088,
      "eval_runtime": 31.8031,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 570
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.6092544987146534e-05,
      "loss": 1.6472,
      "step": 575
    },
    {
      "epoch": 1.48,
      "eval_loss": 1.6598683595657349,
      "eval_runtime": 31.8181,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 575
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.5449871465295634e-05,
      "loss": 1.6723,
      "step": 580
    },
    {
      "epoch": 1.49,
      "eval_loss": 1.6599065065383911,
      "eval_runtime": 31.8124,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 580
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.480719794344473e-05,
      "loss": 1.663,
      "step": 585
    },
    {
      "epoch": 1.5,
      "eval_loss": 1.6599762439727783,
      "eval_runtime": 31.8175,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 585
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.4164524421593832e-05,
      "loss": 1.6519,
      "step": 590
    },
    {
      "epoch": 1.52,
      "eval_loss": 1.6599925756454468,
      "eval_runtime": 31.8209,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 590
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.3521850899742933e-05,
      "loss": 1.6345,
      "step": 595
    },
    {
      "epoch": 1.53,
      "eval_loss": 1.6600078344345093,
      "eval_runtime": 31.8031,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 595
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.2879177377892033e-05,
      "loss": 1.654,
      "step": 600
    },
    {
      "epoch": 1.54,
      "eval_loss": 1.6599884033203125,
      "eval_runtime": 31.8281,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 600
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.2236503856041134e-05,
      "loss": 1.691,
      "step": 605
    },
    {
      "epoch": 1.56,
      "eval_loss": 1.6599520444869995,
      "eval_runtime": 31.8168,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 605
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.159383033419023e-05,
      "loss": 1.6714,
      "step": 610
    },
    {
      "epoch": 1.57,
      "eval_loss": 1.659857988357544,
      "eval_runtime": 31.8153,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 610
    },
    {
      "epoch": 1.58,
      "learning_rate": 2.095115681233933e-05,
      "loss": 1.5977,
      "step": 615
    },
    {
      "epoch": 1.58,
      "eval_loss": 1.6596992015838623,
      "eval_runtime": 31.8087,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 615
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.0308483290488432e-05,
      "loss": 1.6429,
      "step": 620
    },
    {
      "epoch": 1.59,
      "eval_loss": 1.6595497131347656,
      "eval_runtime": 31.8151,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 620
    },
    {
      "epoch": 1.61,
      "learning_rate": 1.9665809768637533e-05,
      "loss": 1.6091,
      "step": 625
    },
    {
      "epoch": 1.61,
      "eval_loss": 1.6597559452056885,
      "eval_runtime": 31.8076,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 625
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.9023136246786633e-05,
      "loss": 1.5956,
      "step": 630
    },
    {
      "epoch": 1.62,
      "eval_loss": 1.6593599319458008,
      "eval_runtime": 31.8058,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 630
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.8380462724935734e-05,
      "loss": 1.6697,
      "step": 635
    },
    {
      "epoch": 1.63,
      "eval_loss": 1.6592466831207275,
      "eval_runtime": 31.8589,
      "eval_samples_per_second": 2.637,
      "eval_steps_per_second": 0.345,
      "step": 635
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.7737789203084834e-05,
      "loss": 1.6535,
      "step": 640
    },
    {
      "epoch": 1.65,
      "eval_loss": 1.6592165231704712,
      "eval_runtime": 31.8225,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 640
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.7095115681233935e-05,
      "loss": 1.6722,
      "step": 645
    },
    {
      "epoch": 1.66,
      "eval_loss": 1.659324049949646,
      "eval_runtime": 31.8388,
      "eval_samples_per_second": 2.638,
      "eval_steps_per_second": 0.345,
      "step": 645
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.6452442159383032e-05,
      "loss": 1.6347,
      "step": 650
    },
    {
      "epoch": 1.67,
      "eval_loss": 1.6590396165847778,
      "eval_runtime": 31.8174,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 650
    },
    {
      "epoch": 1.68,
      "learning_rate": 1.5809768637532136e-05,
      "loss": 1.6223,
      "step": 655
    },
    {
      "epoch": 1.68,
      "eval_loss": 1.658969521522522,
      "eval_runtime": 31.8275,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 655
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.5167095115681235e-05,
      "loss": 1.6309,
      "step": 660
    },
    {
      "epoch": 1.7,
      "eval_loss": 1.6587274074554443,
      "eval_runtime": 31.8146,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 660
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.4524421593830334e-05,
      "loss": 1.6499,
      "step": 665
    },
    {
      "epoch": 1.71,
      "eval_loss": 1.65865957736969,
      "eval_runtime": 31.8091,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 665
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.3881748071979436e-05,
      "loss": 1.6713,
      "step": 670
    },
    {
      "epoch": 1.72,
      "eval_loss": 1.6586016416549683,
      "eval_runtime": 31.8229,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 670
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.3239074550128535e-05,
      "loss": 1.6348,
      "step": 675
    },
    {
      "epoch": 1.74,
      "eval_loss": 1.6584962606430054,
      "eval_runtime": 31.8035,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 675
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.2596401028277636e-05,
      "loss": 1.6447,
      "step": 680
    },
    {
      "epoch": 1.75,
      "eval_loss": 1.6585614681243896,
      "eval_runtime": 31.8101,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 680
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.1953727506426736e-05,
      "loss": 1.6511,
      "step": 685
    },
    {
      "epoch": 1.76,
      "eval_loss": 1.6583601236343384,
      "eval_runtime": 31.8125,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 685
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.1311053984575835e-05,
      "loss": 1.6496,
      "step": 690
    },
    {
      "epoch": 1.77,
      "eval_loss": 1.6583328247070312,
      "eval_runtime": 31.8179,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 690
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.0668380462724936e-05,
      "loss": 1.6421,
      "step": 695
    },
    {
      "epoch": 1.79,
      "eval_loss": 1.6583188772201538,
      "eval_runtime": 31.8165,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 695
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.0025706940874038e-05,
      "loss": 1.6126,
      "step": 700
    },
    {
      "epoch": 1.8,
      "eval_loss": 1.6580705642700195,
      "eval_runtime": 31.8164,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 700
    },
    {
      "epoch": 1.81,
      "learning_rate": 9.383033419023137e-06,
      "loss": 1.6226,
      "step": 705
    },
    {
      "epoch": 1.81,
      "eval_loss": 1.6584465503692627,
      "eval_runtime": 31.816,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 705
    },
    {
      "epoch": 1.83,
      "learning_rate": 8.740359897172237e-06,
      "loss": 1.6923,
      "step": 710
    },
    {
      "epoch": 1.83,
      "eval_loss": 1.658342957496643,
      "eval_runtime": 31.8215,
      "eval_samples_per_second": 2.64,
      "eval_steps_per_second": 0.346,
      "step": 710
    },
    {
      "epoch": 1.84,
      "learning_rate": 8.097686375321336e-06,
      "loss": 1.6224,
      "step": 715
    },
    {
      "epoch": 1.84,
      "eval_loss": 1.6582502126693726,
      "eval_runtime": 31.812,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 715
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.4550128534704376e-06,
      "loss": 1.6587,
      "step": 720
    },
    {
      "epoch": 1.85,
      "eval_loss": 1.658232569694519,
      "eval_runtime": 31.8059,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 720
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.812339331619537e-06,
      "loss": 1.6641,
      "step": 725
    },
    {
      "epoch": 1.86,
      "eval_loss": 1.6582419872283936,
      "eval_runtime": 31.81,
      "eval_samples_per_second": 2.641,
      "eval_steps_per_second": 0.346,
      "step": 725
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.169665809768638e-06,
      "loss": 1.6419,
      "step": 730
    },
    {
      "epoch": 1.88,
      "eval_loss": 1.6582107543945312,
      "eval_runtime": 31.833,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 730
    },
    {
      "epoch": 1.89,
      "learning_rate": 5.526992287917738e-06,
      "loss": 1.652,
      "step": 735
    },
    {
      "epoch": 1.89,
      "eval_loss": 1.6582270860671997,
      "eval_runtime": 31.8801,
      "eval_samples_per_second": 2.635,
      "eval_steps_per_second": 0.345,
      "step": 735
    },
    {
      "epoch": 1.9,
      "learning_rate": 4.884318766066838e-06,
      "loss": 1.6487,
      "step": 740
    },
    {
      "epoch": 1.9,
      "eval_loss": 1.6582915782928467,
      "eval_runtime": 31.8265,
      "eval_samples_per_second": 2.639,
      "eval_steps_per_second": 0.346,
      "step": 740
    }
  ],
  "logging_steps": 5,
  "max_steps": 778,
  "num_train_epochs": 2,
  "save_steps": 10,
  "total_flos": 2.4039678818648064e+17,
  "trial_name": null,
  "trial_params": null
}