{
  "best_metric": 1.8410229682922363,
  "best_model_checkpoint": "/content/drive/MyDrive/ZephyrAI/zephyr_model_v11_turbo/checkpoint-75",
  "epoch": 4.918032786885246,
  "eval_steps": 1,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 1.070236325263977,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.4899,
      "step": 1
    },
    {
      "epoch": 0.06557377049180328,
      "eval_loss": 2.437901258468628,
      "eval_runtime": 46.6808,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 1
    },
    {
      "epoch": 0.13114754098360656,
      "grad_norm": 1.1805078983306885,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.4403,
      "step": 2
    },
    {
      "epoch": 0.13114754098360656,
      "eval_loss": 2.434871196746826,
      "eval_runtime": 46.7714,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 2
    },
    {
      "epoch": 0.19672131147540983,
      "grad_norm": 1.0782222747802734,
      "learning_rate": 2e-05,
      "loss": 2.3851,
      "step": 3
    },
    {
      "epoch": 0.19672131147540983,
      "eval_loss": 2.421125650405884,
      "eval_runtime": 46.6915,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 3
    },
    {
      "epoch": 0.26229508196721313,
      "grad_norm": 1.0158095359802246,
      "learning_rate": 1.9722222222222224e-05,
      "loss": 2.4596,
      "step": 4
    },
    {
      "epoch": 0.26229508196721313,
      "eval_loss": 2.3971059322357178,
      "eval_runtime": 46.6786,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.279,
      "step": 4
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.9539541006088257,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 2.382,
      "step": 5
    },
    {
      "epoch": 0.32786885245901637,
      "eval_loss": 2.3755452632904053,
      "eval_runtime": 46.6915,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 5
    },
    {
      "epoch": 0.39344262295081966,
      "grad_norm": 0.8312937021255493,
      "learning_rate": 1.916666666666667e-05,
      "loss": 2.3304,
      "step": 6
    },
    {
      "epoch": 0.39344262295081966,
      "eval_loss": 2.3568789958953857,
      "eval_runtime": 46.7831,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 6
    },
    {
      "epoch": 0.45901639344262296,
      "grad_norm": 0.7678759694099426,
      "learning_rate": 1.888888888888889e-05,
      "loss": 2.3028,
      "step": 7
    },
    {
      "epoch": 0.45901639344262296,
      "eval_loss": 2.340029716491699,
      "eval_runtime": 46.7542,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 7
    },
    {
      "epoch": 0.5245901639344263,
      "grad_norm": 0.6792626976966858,
      "learning_rate": 1.8611111111111114e-05,
      "loss": 2.3466,
      "step": 8
    },
    {
      "epoch": 0.5245901639344263,
      "eval_loss": 2.3247592449188232,
      "eval_runtime": 46.7003,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 8
    },
    {
      "epoch": 0.5901639344262295,
      "grad_norm": 0.660761833190918,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 2.3271,
      "step": 9
    },
    {
      "epoch": 0.5901639344262295,
      "eval_loss": 2.3108019828796387,
      "eval_runtime": 46.7515,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 9
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.6685893535614014,
      "learning_rate": 1.8055555555555558e-05,
      "loss": 2.2604,
      "step": 10
    },
    {
      "epoch": 0.6557377049180327,
      "eval_loss": 2.2978525161743164,
      "eval_runtime": 46.6847,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 10
    },
    {
      "epoch": 0.7213114754098361,
      "grad_norm": 0.5920826196670532,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 2.2218,
      "step": 11
    },
    {
      "epoch": 0.7213114754098361,
      "eval_loss": 2.2857038974761963,
      "eval_runtime": 46.7809,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 11
    },
    {
      "epoch": 0.7868852459016393,
      "grad_norm": 0.6445866823196411,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 2.2014,
      "step": 12
    },
    {
      "epoch": 0.7868852459016393,
      "eval_loss": 2.2739903926849365,
      "eval_runtime": 46.6906,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 12
    },
    {
      "epoch": 0.8524590163934426,
      "grad_norm": 0.6221867203712463,
      "learning_rate": 1.7222222222222224e-05,
      "loss": 2.2426,
      "step": 13
    },
    {
      "epoch": 0.8524590163934426,
      "eval_loss": 2.2625272274017334,
      "eval_runtime": 46.7451,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 13
    },
    {
      "epoch": 0.9180327868852459,
      "grad_norm": 0.6631550192832947,
      "learning_rate": 1.6944444444444446e-05,
      "loss": 2.2368,
      "step": 14
    },
    {
      "epoch": 0.9180327868852459,
      "eval_loss": 2.2512171268463135,
      "eval_runtime": 46.674,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.279,
      "step": 14
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.5557384490966797,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.1956,
      "step": 15
    },
    {
      "epoch": 0.9836065573770492,
      "eval_loss": 2.23983097076416,
      "eval_runtime": 46.7325,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 15
    },
    {
      "epoch": 1.0491803278688525,
      "grad_norm": 0.5928459167480469,
      "learning_rate": 1.638888888888889e-05,
      "loss": 2.1429,
      "step": 16
    },
    {
      "epoch": 1.0491803278688525,
      "eval_loss": 2.2281932830810547,
      "eval_runtime": 46.768,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 16
    },
    {
      "epoch": 1.1147540983606556,
      "grad_norm": 0.6136890053749084,
      "learning_rate": 1.6111111111111115e-05,
      "loss": 2.1862,
      "step": 17
    },
    {
      "epoch": 1.1147540983606556,
      "eval_loss": 2.2162652015686035,
      "eval_runtime": 46.7237,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 17
    },
    {
      "epoch": 1.180327868852459,
      "grad_norm": 0.5814841389656067,
      "learning_rate": 1.5833333333333333e-05,
      "loss": 2.2012,
      "step": 18
    },
    {
      "epoch": 1.180327868852459,
      "eval_loss": 2.204092264175415,
      "eval_runtime": 46.7753,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 18
    },
    {
      "epoch": 1.2459016393442623,
      "grad_norm": 0.5701133608818054,
      "learning_rate": 1.555555555555556e-05,
      "loss": 2.1545,
      "step": 19
    },
    {
      "epoch": 1.2459016393442623,
      "eval_loss": 2.191829204559326,
      "eval_runtime": 46.7098,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 19
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 0.5770221948623657,
      "learning_rate": 1.5277777777777777e-05,
      "loss": 2.1463,
      "step": 20
    },
    {
      "epoch": 1.3114754098360657,
      "eval_loss": 2.1793527603149414,
      "eval_runtime": 46.7538,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 20
    },
    {
      "epoch": 1.3770491803278688,
      "grad_norm": 0.541409969329834,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.062,
      "step": 21
    },
    {
      "epoch": 1.3770491803278688,
      "eval_loss": 2.1669070720672607,
      "eval_runtime": 46.6875,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 21
    },
    {
      "epoch": 1.4426229508196722,
      "grad_norm": 0.6078354120254517,
      "learning_rate": 1.4722222222222224e-05,
      "loss": 2.1365,
      "step": 22
    },
    {
      "epoch": 1.4426229508196722,
      "eval_loss": 2.154656410217285,
      "eval_runtime": 46.7354,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 22
    },
    {
      "epoch": 1.5081967213114753,
      "grad_norm": 0.6025573015213013,
      "learning_rate": 1.4444444444444446e-05,
      "loss": 2.0426,
      "step": 23
    },
    {
      "epoch": 1.5081967213114753,
      "eval_loss": 2.1424319744110107,
      "eval_runtime": 46.7734,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 23
    },
    {
      "epoch": 1.5737704918032787,
      "grad_norm": 0.5577809810638428,
      "learning_rate": 1.416666666666667e-05,
      "loss": 2.0489,
      "step": 24
    },
    {
      "epoch": 1.5737704918032787,
      "eval_loss": 2.1300365924835205,
      "eval_runtime": 46.8011,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 24
    },
    {
      "epoch": 1.639344262295082,
      "grad_norm": 0.5722355842590332,
      "learning_rate": 1.388888888888889e-05,
      "loss": 2.0289,
      "step": 25
    },
    {
      "epoch": 1.639344262295082,
      "eval_loss": 2.1180951595306396,
      "eval_runtime": 46.6691,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.279,
      "step": 25
    },
    {
      "epoch": 1.7049180327868854,
      "grad_norm": 0.5458038449287415,
      "learning_rate": 1.3611111111111113e-05,
      "loss": 2.0995,
      "step": 26
    },
    {
      "epoch": 1.7049180327868854,
      "eval_loss": 2.1060945987701416,
      "eval_runtime": 46.7807,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 26
    },
    {
      "epoch": 1.7704918032786885,
      "grad_norm": 0.5661202073097229,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.0379,
      "step": 27
    },
    {
      "epoch": 1.7704918032786885,
      "eval_loss": 2.0944411754608154,
      "eval_runtime": 46.7187,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 27
    },
    {
      "epoch": 1.8360655737704918,
      "grad_norm": 0.5147558450698853,
      "learning_rate": 1.3055555555555557e-05,
      "loss": 2.0116,
      "step": 28
    },
    {
      "epoch": 1.8360655737704918,
      "eval_loss": 2.082529306411743,
      "eval_runtime": 46.7106,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 28
    },
    {
      "epoch": 1.901639344262295,
      "grad_norm": 0.552470326423645,
      "learning_rate": 1.2777777777777777e-05,
      "loss": 2.0063,
      "step": 29
    },
    {
      "epoch": 1.901639344262295,
      "eval_loss": 2.071108102798462,
      "eval_runtime": 46.7582,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 29
    },
    {
      "epoch": 1.9672131147540983,
      "grad_norm": 0.5569080114364624,
      "learning_rate": 1.25e-05,
      "loss": 2.0361,
      "step": 30
    },
    {
      "epoch": 1.9672131147540983,
      "eval_loss": 2.059589385986328,
      "eval_runtime": 46.7694,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 30
    },
    {
      "epoch": 2.0327868852459017,
      "grad_norm": 0.5699050426483154,
      "learning_rate": 1.2222222222222224e-05,
      "loss": 1.9885,
      "step": 31
    },
    {
      "epoch": 2.0327868852459017,
      "eval_loss": 2.048337459564209,
      "eval_runtime": 46.8642,
      "eval_samples_per_second": 0.555,
      "eval_steps_per_second": 0.277,
      "step": 31
    },
    {
      "epoch": 2.098360655737705,
      "grad_norm": 0.5750185251235962,
      "learning_rate": 1.1944444444444444e-05,
      "loss": 2.0413,
      "step": 32
    },
    {
      "epoch": 2.098360655737705,
      "eval_loss": 2.0375266075134277,
      "eval_runtime": 46.7785,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 32
    },
    {
      "epoch": 2.1639344262295084,
      "grad_norm": 0.5735768675804138,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 1.9587,
      "step": 33
    },
    {
      "epoch": 2.1639344262295084,
      "eval_loss": 2.026817798614502,
      "eval_runtime": 46.7523,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 33
    },
    {
      "epoch": 2.2295081967213113,
      "grad_norm": 0.551645040512085,
      "learning_rate": 1.138888888888889e-05,
      "loss": 1.9807,
      "step": 34
    },
    {
      "epoch": 2.2295081967213113,
      "eval_loss": 2.0163915157318115,
      "eval_runtime": 46.8045,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 34
    },
    {
      "epoch": 2.2950819672131146,
      "grad_norm": 0.5482759475708008,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 1.9198,
      "step": 35
    },
    {
      "epoch": 2.2950819672131146,
      "eval_loss": 2.0062360763549805,
      "eval_runtime": 46.762,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 35
    },
    {
      "epoch": 2.360655737704918,
      "grad_norm": 0.535072922706604,
      "learning_rate": 1.0833333333333334e-05,
      "loss": 1.9425,
      "step": 36
    },
    {
      "epoch": 2.360655737704918,
      "eval_loss": 1.9964103698730469,
      "eval_runtime": 46.7787,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 36
    },
    {
      "epoch": 2.4262295081967213,
      "grad_norm": 0.5778989791870117,
      "learning_rate": 1.0555555555555557e-05,
      "loss": 1.895,
      "step": 37
    },
    {
      "epoch": 2.4262295081967213,
      "eval_loss": 1.9869199991226196,
      "eval_runtime": 46.7633,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 37
    },
    {
      "epoch": 2.4918032786885247,
      "grad_norm": 0.5230702757835388,
      "learning_rate": 1.0277777777777777e-05,
      "loss": 1.9428,
      "step": 38
    },
    {
      "epoch": 2.4918032786885247,
      "eval_loss": 1.9776345491409302,
      "eval_runtime": 46.7004,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 38
    },
    {
      "epoch": 2.557377049180328,
      "grad_norm": 0.5722452402114868,
      "learning_rate": 1e-05,
      "loss": 1.8718,
      "step": 39
    },
    {
      "epoch": 2.557377049180328,
      "eval_loss": 1.9689091444015503,
      "eval_runtime": 46.7098,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 39
    },
    {
      "epoch": 2.6229508196721314,
      "grad_norm": 0.5922034382820129,
      "learning_rate": 9.722222222222223e-06,
      "loss": 1.8852,
      "step": 40
    },
    {
      "epoch": 2.6229508196721314,
      "eval_loss": 1.9604159593582153,
      "eval_runtime": 46.7444,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 40
    },
    {
      "epoch": 2.6885245901639343,
      "grad_norm": 0.6062042117118835,
      "learning_rate": 9.444444444444445e-06,
      "loss": 1.9446,
      "step": 41
    },
    {
      "epoch": 2.6885245901639343,
      "eval_loss": 1.952351450920105,
      "eval_runtime": 46.7995,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 41
    },
    {
      "epoch": 2.7540983606557377,
      "grad_norm": 0.5561647415161133,
      "learning_rate": 9.166666666666666e-06,
      "loss": 1.9389,
      "step": 42
    },
    {
      "epoch": 2.7540983606557377,
      "eval_loss": 1.9445891380310059,
      "eval_runtime": 46.7054,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 42
    },
    {
      "epoch": 2.819672131147541,
      "grad_norm": 0.5309848189353943,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.8356,
      "step": 43
    },
    {
      "epoch": 2.819672131147541,
      "eval_loss": 1.9371622800827026,
      "eval_runtime": 46.6887,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 43
    },
    {
      "epoch": 2.8852459016393444,
      "grad_norm": 0.5254234075546265,
      "learning_rate": 8.611111111111112e-06,
      "loss": 1.7884,
      "step": 44
    },
    {
      "epoch": 2.8852459016393444,
      "eval_loss": 1.9301851987838745,
      "eval_runtime": 46.6917,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 44
    },
    {
      "epoch": 2.9508196721311473,
      "grad_norm": 0.5549314022064209,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.8899,
      "step": 45
    },
    {
      "epoch": 2.9508196721311473,
      "eval_loss": 1.923454761505127,
      "eval_runtime": 46.7648,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 45
    },
    {
      "epoch": 3.0163934426229506,
      "grad_norm": 0.5211459398269653,
      "learning_rate": 8.055555555555557e-06,
      "loss": 1.8435,
      "step": 46
    },
    {
      "epoch": 3.0163934426229506,
      "eval_loss": 1.9169979095458984,
      "eval_runtime": 46.7864,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 46
    },
    {
      "epoch": 3.081967213114754,
      "grad_norm": 0.5590901970863342,
      "learning_rate": 7.77777777777778e-06,
      "loss": 1.8431,
      "step": 47
    },
    {
      "epoch": 3.081967213114754,
      "eval_loss": 1.910991907119751,
      "eval_runtime": 46.7269,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 47
    },
    {
      "epoch": 3.1475409836065573,
      "grad_norm": 0.5320960283279419,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.7688,
      "step": 48
    },
    {
      "epoch": 3.1475409836065573,
      "eval_loss": 1.905371904373169,
      "eval_runtime": 46.6869,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 48
    },
    {
      "epoch": 3.2131147540983607,
      "grad_norm": 0.49724167585372925,
      "learning_rate": 7.222222222222223e-06,
      "loss": 1.8617,
      "step": 49
    },
    {
      "epoch": 3.2131147540983607,
      "eval_loss": 1.9000388383865356,
      "eval_runtime": 46.7814,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 49
    },
    {
      "epoch": 3.278688524590164,
      "grad_norm": 0.5152797102928162,
      "learning_rate": 6.944444444444445e-06,
      "loss": 1.8381,
      "step": 50
    },
    {
      "epoch": 3.278688524590164,
      "eval_loss": 1.8951764106750488,
      "eval_runtime": 46.7657,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 50
    },
    {
      "epoch": 3.3442622950819674,
      "grad_norm": 0.5719711780548096,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.8516,
      "step": 51
    },
    {
      "epoch": 3.3442622950819674,
      "eval_loss": 1.8905354738235474,
      "eval_runtime": 46.6775,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.279,
      "step": 51
    },
    {
      "epoch": 3.4098360655737707,
      "grad_norm": 0.5465454459190369,
      "learning_rate": 6.3888888888888885e-06,
      "loss": 1.8267,
      "step": 52
    },
    {
      "epoch": 3.4098360655737707,
      "eval_loss": 1.88612961769104,
      "eval_runtime": 46.6966,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 52
    },
    {
      "epoch": 3.4754098360655736,
      "grad_norm": 0.5389249324798584,
      "learning_rate": 6.111111111111112e-06,
      "loss": 1.8758,
      "step": 53
    },
    {
      "epoch": 3.4754098360655736,
      "eval_loss": 1.8819791078567505,
      "eval_runtime": 46.6711,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.279,
      "step": 53
    },
    {
      "epoch": 3.540983606557377,
      "grad_norm": 0.495549738407135,
      "learning_rate": 5.833333333333334e-06,
      "loss": 1.7792,
      "step": 54
    },
    {
      "epoch": 3.540983606557377,
      "eval_loss": 1.8781176805496216,
      "eval_runtime": 46.7024,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 54
    },
    {
      "epoch": 3.6065573770491803,
      "grad_norm": 0.49404528737068176,
      "learning_rate": 5.555555555555557e-06,
      "loss": 1.7878,
      "step": 55
    },
    {
      "epoch": 3.6065573770491803,
      "eval_loss": 1.8743711709976196,
      "eval_runtime": 46.725,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 55
    },
    {
      "epoch": 3.6721311475409837,
      "grad_norm": 0.5066283941268921,
      "learning_rate": 5.2777777777777785e-06,
      "loss": 1.763,
      "step": 56
    },
    {
      "epoch": 3.6721311475409837,
      "eval_loss": 1.8708436489105225,
      "eval_runtime": 46.7333,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 56
    },
    {
      "epoch": 3.737704918032787,
      "grad_norm": 0.5295591950416565,
      "learning_rate": 5e-06,
      "loss": 1.8013,
      "step": 57
    },
    {
      "epoch": 3.737704918032787,
      "eval_loss": 1.8677045106887817,
      "eval_runtime": 46.7182,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.278,
      "step": 57
    },
    {
      "epoch": 3.80327868852459,
      "grad_norm": 0.52997225522995,
      "learning_rate": 4.722222222222222e-06,
      "loss": 1.8064,
      "step": 58
    },
    {
      "epoch": 3.80327868852459,
      "eval_loss": 1.8646008968353271,
      "eval_runtime": 46.7441,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 58
    },
    {
      "epoch": 3.8688524590163933,
      "grad_norm": 0.6026036739349365,
      "learning_rate": 4.444444444444444e-06,
      "loss": 1.7201,
      "step": 59
    },
    {
      "epoch": 3.8688524590163933,
      "eval_loss": 1.8619288206100464,
      "eval_runtime": 46.7352,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 59
    },
    {
      "epoch": 3.9344262295081966,
      "grad_norm": 0.5750531554222107,
      "learning_rate": 4.166666666666667e-06,
      "loss": 1.7895,
      "step": 60
    },
    {
      "epoch": 3.9344262295081966,
      "eval_loss": 1.859217882156372,
      "eval_runtime": 46.7301,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 60
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.502881646156311,
      "learning_rate": 3.88888888888889e-06,
      "loss": 1.7837,
      "step": 61
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.8568609952926636,
      "eval_runtime": 46.7362,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 61
    },
    {
      "epoch": 4.065573770491803,
      "grad_norm": 0.5146604776382446,
      "learning_rate": 3.6111111111111115e-06,
      "loss": 1.6988,
      "step": 62
    },
    {
      "epoch": 4.065573770491803,
      "eval_loss": 1.8548047542572021,
      "eval_runtime": 46.7365,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 62
    },
    {
      "epoch": 4.131147540983607,
      "grad_norm": 0.5581990480422974,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.8038,
      "step": 63
    },
    {
      "epoch": 4.131147540983607,
      "eval_loss": 1.8527864217758179,
      "eval_runtime": 46.7975,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 63
    },
    {
      "epoch": 4.19672131147541,
      "grad_norm": 0.5218520164489746,
      "learning_rate": 3.055555555555556e-06,
      "loss": 1.7717,
      "step": 64
    },
    {
      "epoch": 4.19672131147541,
      "eval_loss": 1.850966215133667,
      "eval_runtime": 46.7506,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 64
    },
    {
      "epoch": 4.262295081967213,
      "grad_norm": 0.5471401214599609,
      "learning_rate": 2.7777777777777783e-06,
      "loss": 1.7708,
      "step": 65
    },
    {
      "epoch": 4.262295081967213,
      "eval_loss": 1.849280834197998,
      "eval_runtime": 46.7943,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 65
    },
    {
      "epoch": 4.327868852459017,
      "grad_norm": 0.49679359793663025,
      "learning_rate": 2.5e-06,
      "loss": 1.7721,
      "step": 66
    },
    {
      "epoch": 4.327868852459017,
      "eval_loss": 1.847765564918518,
      "eval_runtime": 46.7913,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 66
    },
    {
      "epoch": 4.39344262295082,
      "grad_norm": 0.5536015033721924,
      "learning_rate": 2.222222222222222e-06,
      "loss": 1.7757,
      "step": 67
    },
    {
      "epoch": 4.39344262295082,
      "eval_loss": 1.8464475870132446,
      "eval_runtime": 46.7742,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 67
    },
    {
      "epoch": 4.459016393442623,
      "grad_norm": 0.5509213209152222,
      "learning_rate": 1.944444444444445e-06,
      "loss": 1.8043,
      "step": 68
    },
    {
      "epoch": 4.459016393442623,
      "eval_loss": 1.8451799154281616,
      "eval_runtime": 46.7554,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 68
    },
    {
      "epoch": 4.524590163934426,
      "grad_norm": 0.49126845598220825,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.7836,
      "step": 69
    },
    {
      "epoch": 4.524590163934426,
      "eval_loss": 1.8441420793533325,
      "eval_runtime": 46.7716,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 69
    },
    {
      "epoch": 4.590163934426229,
      "grad_norm": 0.5862410664558411,
      "learning_rate": 1.3888888888888892e-06,
      "loss": 1.8036,
      "step": 70
    },
    {
      "epoch": 4.590163934426229,
      "eval_loss": 1.8432250022888184,
      "eval_runtime": 46.7239,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 70
    },
    {
      "epoch": 4.655737704918033,
      "grad_norm": 0.5185004472732544,
      "learning_rate": 1.111111111111111e-06,
      "loss": 1.8121,
      "step": 71
    },
    {
      "epoch": 4.655737704918033,
      "eval_loss": 1.8424735069274902,
      "eval_runtime": 46.753,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 71
    },
    {
      "epoch": 4.721311475409836,
      "grad_norm": 0.5338285565376282,
      "learning_rate": 8.333333333333333e-07,
      "loss": 1.7523,
      "step": 72
    },
    {
      "epoch": 4.721311475409836,
      "eval_loss": 1.8418388366699219,
      "eval_runtime": 46.7365,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 72
    },
    {
      "epoch": 4.786885245901639,
      "grad_norm": 0.5311003923416138,
      "learning_rate": 5.555555555555555e-07,
      "loss": 1.7532,
      "step": 73
    },
    {
      "epoch": 4.786885245901639,
      "eval_loss": 1.841430425643921,
      "eval_runtime": 46.7626,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.278,
      "step": 73
    },
    {
      "epoch": 4.852459016393443,
      "grad_norm": 0.551410436630249,
      "learning_rate": 2.7777777777777776e-07,
      "loss": 1.7593,
      "step": 74
    },
    {
      "epoch": 4.852459016393443,
      "eval_loss": 1.8412089347839355,
      "eval_runtime": 46.8159,
      "eval_samples_per_second": 0.555,
      "eval_steps_per_second": 0.278,
      "step": 74
    },
    {
      "epoch": 4.918032786885246,
      "grad_norm": 0.49288997054100037,
      "learning_rate": 0.0,
      "loss": 1.7316,
      "step": 75
    },
    {
      "epoch": 4.918032786885246,
      "eval_loss": 1.8410229682922363,
      "eval_runtime": 46.8396,
      "eval_samples_per_second": 0.555,
      "eval_steps_per_second": 0.278,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.224575101730816e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}