{
  "best_metric": 1.5823931694030762,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.11293054771315642,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000564652738565782,
      "grad_norm": 0.5402987599372864,
      "learning_rate": 1.013e-05,
      "loss": 1.4633,
      "step": 1
    },
    {
      "epoch": 0.000564652738565782,
      "eval_loss": 2.135667562484741,
      "eval_runtime": 33.7351,
      "eval_samples_per_second": 22.113,
      "eval_steps_per_second": 5.543,
      "step": 1
    },
    {
      "epoch": 0.001129305477131564,
      "grad_norm": 0.36689239740371704,
      "learning_rate": 2.026e-05,
      "loss": 1.8992,
      "step": 2
    },
    {
      "epoch": 0.0016939582156973462,
      "grad_norm": 0.3763646185398102,
      "learning_rate": 3.039e-05,
      "loss": 0.8535,
      "step": 3
    },
    {
      "epoch": 0.002258610954263128,
      "grad_norm": 0.34807297587394714,
      "learning_rate": 4.052e-05,
      "loss": 1.7749,
      "step": 4
    },
    {
      "epoch": 0.00282326369282891,
      "grad_norm": 0.5206761360168457,
      "learning_rate": 5.065e-05,
      "loss": 1.8843,
      "step": 5
    },
    {
      "epoch": 0.0033879164313946925,
      "grad_norm": 0.3446935713291168,
      "learning_rate": 6.078e-05,
      "loss": 2.4299,
      "step": 6
    },
    {
      "epoch": 0.003952569169960474,
      "grad_norm": 0.353129506111145,
      "learning_rate": 7.091e-05,
      "loss": 1.9346,
      "step": 7
    },
    {
      "epoch": 0.004517221908526256,
      "grad_norm": 0.2856239378452301,
      "learning_rate": 8.104e-05,
      "loss": 1.7326,
      "step": 8
    },
    {
      "epoch": 0.005081874647092038,
      "grad_norm": 0.4531644880771637,
      "learning_rate": 9.117e-05,
      "loss": 1.7827,
      "step": 9
    },
    {
      "epoch": 0.00564652738565782,
      "grad_norm": 0.47059357166290283,
      "learning_rate": 0.0001013,
      "loss": 2.4921,
      "step": 10
    },
    {
      "epoch": 0.006211180124223602,
      "grad_norm": 0.4820435345172882,
      "learning_rate": 0.00010076684210526316,
      "loss": 1.8598,
      "step": 11
    },
    {
      "epoch": 0.006775832862789385,
      "grad_norm": 0.37354958057403564,
      "learning_rate": 0.0001002336842105263,
      "loss": 1.7825,
      "step": 12
    },
    {
      "epoch": 0.007340485601355167,
      "grad_norm": 0.3483826220035553,
      "learning_rate": 9.970052631578946e-05,
      "loss": 2.0361,
      "step": 13
    },
    {
      "epoch": 0.007905138339920948,
      "grad_norm": 0.45971325039863586,
      "learning_rate": 9.916736842105263e-05,
      "loss": 1.9319,
      "step": 14
    },
    {
      "epoch": 0.00846979107848673,
      "grad_norm": 0.9301943182945251,
      "learning_rate": 9.863421052631579e-05,
      "loss": 1.6979,
      "step": 15
    },
    {
      "epoch": 0.009034443817052512,
      "grad_norm": 0.32556048035621643,
      "learning_rate": 9.810105263157895e-05,
      "loss": 2.2257,
      "step": 16
    },
    {
      "epoch": 0.009599096555618294,
      "grad_norm": 0.46048063039779663,
      "learning_rate": 9.756789473684211e-05,
      "loss": 1.7091,
      "step": 17
    },
    {
      "epoch": 0.010163749294184076,
      "grad_norm": 0.3488789498806,
      "learning_rate": 9.703473684210525e-05,
      "loss": 2.019,
      "step": 18
    },
    {
      "epoch": 0.010728402032749858,
      "grad_norm": 0.5194416642189026,
      "learning_rate": 9.650157894736842e-05,
      "loss": 1.9075,
      "step": 19
    },
    {
      "epoch": 0.01129305477131564,
      "grad_norm": 0.46956583857536316,
      "learning_rate": 9.596842105263158e-05,
      "loss": 1.8816,
      "step": 20
    },
    {
      "epoch": 0.011857707509881422,
      "grad_norm": 0.4933469891548157,
      "learning_rate": 9.543526315789474e-05,
      "loss": 1.729,
      "step": 21
    },
    {
      "epoch": 0.012422360248447204,
      "grad_norm": 0.3997938930988312,
      "learning_rate": 9.49021052631579e-05,
      "loss": 1.6959,
      "step": 22
    },
    {
      "epoch": 0.012987012987012988,
      "grad_norm": 0.5408119559288025,
      "learning_rate": 9.436894736842105e-05,
      "loss": 2.0254,
      "step": 23
    },
    {
      "epoch": 0.01355166572557877,
      "grad_norm": 0.41266539692878723,
      "learning_rate": 9.38357894736842e-05,
      "loss": 1.9554,
      "step": 24
    },
    {
      "epoch": 0.014116318464144552,
      "grad_norm": 0.5079236030578613,
      "learning_rate": 9.330263157894737e-05,
      "loss": 2.0457,
      "step": 25
    },
    {
      "epoch": 0.014680971202710334,
      "grad_norm": 0.5814744830131531,
      "learning_rate": 9.276947368421051e-05,
      "loss": 2.0399,
      "step": 26
    },
    {
      "epoch": 0.015245623941276116,
      "grad_norm": 0.6485530138015747,
      "learning_rate": 9.223631578947369e-05,
      "loss": 1.4858,
      "step": 27
    },
    {
      "epoch": 0.015810276679841896,
      "grad_norm": 0.5585585832595825,
      "learning_rate": 9.170315789473684e-05,
      "loss": 1.9193,
      "step": 28
    },
    {
      "epoch": 0.01637492941840768,
      "grad_norm": 0.6046280860900879,
      "learning_rate": 9.117e-05,
      "loss": 2.3537,
      "step": 29
    },
    {
      "epoch": 0.01693958215697346,
      "grad_norm": 0.5263966917991638,
      "learning_rate": 9.063684210526316e-05,
      "loss": 1.5335,
      "step": 30
    },
    {
      "epoch": 0.017504234895539244,
      "grad_norm": 0.8364748358726501,
      "learning_rate": 9.010368421052632e-05,
      "loss": 1.7004,
      "step": 31
    },
    {
      "epoch": 0.018068887634105024,
      "grad_norm": 0.5951048135757446,
      "learning_rate": 8.957052631578946e-05,
      "loss": 2.4489,
      "step": 32
    },
    {
      "epoch": 0.018633540372670808,
      "grad_norm": 0.5281526446342468,
      "learning_rate": 8.903736842105263e-05,
      "loss": 1.1862,
      "step": 33
    },
    {
      "epoch": 0.019198193111236588,
      "grad_norm": 0.8356189727783203,
      "learning_rate": 8.850421052631579e-05,
      "loss": 1.5012,
      "step": 34
    },
    {
      "epoch": 0.019762845849802372,
      "grad_norm": 0.6029136180877686,
      "learning_rate": 8.797105263157895e-05,
      "loss": 1.4578,
      "step": 35
    },
    {
      "epoch": 0.020327498588368152,
      "grad_norm": 0.6786731481552124,
      "learning_rate": 8.743789473684211e-05,
      "loss": 1.547,
      "step": 36
    },
    {
      "epoch": 0.020892151326933936,
      "grad_norm": 0.877357542514801,
      "learning_rate": 8.690473684210526e-05,
      "loss": 1.7824,
      "step": 37
    },
    {
      "epoch": 0.021456804065499716,
      "grad_norm": 1.265729546546936,
      "learning_rate": 8.637157894736842e-05,
      "loss": 2.1181,
      "step": 38
    },
    {
      "epoch": 0.0220214568040655,
      "grad_norm": 1.4670414924621582,
      "learning_rate": 8.583842105263158e-05,
      "loss": 1.3309,
      "step": 39
    },
    {
      "epoch": 0.02258610954263128,
      "grad_norm": 1.3509232997894287,
      "learning_rate": 8.530526315789472e-05,
      "loss": 2.5148,
      "step": 40
    },
    {
      "epoch": 0.023150762281197064,
      "grad_norm": 1.4195291996002197,
      "learning_rate": 8.47721052631579e-05,
      "loss": 2.0859,
      "step": 41
    },
    {
      "epoch": 0.023715415019762844,
      "grad_norm": 1.6967036724090576,
      "learning_rate": 8.423894736842105e-05,
      "loss": 1.6782,
      "step": 42
    },
    {
      "epoch": 0.024280067758328628,
      "grad_norm": 1.9785702228546143,
      "learning_rate": 8.37057894736842e-05,
      "loss": 1.8815,
      "step": 43
    },
    {
      "epoch": 0.024844720496894408,
      "grad_norm": 2.209860324859619,
      "learning_rate": 8.317263157894737e-05,
      "loss": 1.5545,
      "step": 44
    },
    {
      "epoch": 0.025409373235460192,
      "grad_norm": 2.2609925270080566,
      "learning_rate": 8.263947368421053e-05,
      "loss": 1.3009,
      "step": 45
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 3.240757703781128,
      "learning_rate": 8.210631578947368e-05,
      "loss": 2.1366,
      "step": 46
    },
    {
      "epoch": 0.026538678712591756,
      "grad_norm": 3.1858623027801514,
      "learning_rate": 8.157315789473684e-05,
      "loss": 1.119,
      "step": 47
    },
    {
      "epoch": 0.02710333145115754,
      "grad_norm": 3.827558994293213,
      "learning_rate": 8.104e-05,
      "loss": 1.5671,
      "step": 48
    },
    {
      "epoch": 0.02766798418972332,
      "grad_norm": 4.33996057510376,
      "learning_rate": 8.050684210526316e-05,
      "loss": 1.3891,
      "step": 49
    },
    {
      "epoch": 0.028232636928289104,
      "grad_norm": 5.596718788146973,
      "learning_rate": 7.997368421052632e-05,
      "loss": 1.572,
      "step": 50
    },
    {
      "epoch": 0.028232636928289104,
      "eval_loss": 1.7320042848587036,
      "eval_runtime": 33.7715,
      "eval_samples_per_second": 22.09,
      "eval_steps_per_second": 5.537,
      "step": 50
    },
    {
      "epoch": 0.028797289666854884,
      "grad_norm": 0.710443913936615,
      "learning_rate": 7.944052631578947e-05,
      "loss": 2.2345,
      "step": 51
    },
    {
      "epoch": 0.029361942405420668,
      "grad_norm": 0.6612917184829712,
      "learning_rate": 7.890736842105263e-05,
      "loss": 2.0899,
      "step": 52
    },
    {
      "epoch": 0.029926595143986448,
      "grad_norm": 0.7144291996955872,
      "learning_rate": 7.837421052631579e-05,
      "loss": 0.9424,
      "step": 53
    },
    {
      "epoch": 0.030491247882552232,
      "grad_norm": 0.6780564188957214,
      "learning_rate": 7.784105263157893e-05,
      "loss": 2.0563,
      "step": 54
    },
    {
      "epoch": 0.031055900621118012,
      "grad_norm": 0.7346010208129883,
      "learning_rate": 7.730789473684211e-05,
      "loss": 1.8291,
      "step": 55
    },
    {
      "epoch": 0.03162055335968379,
      "grad_norm": 0.4565852880477905,
      "learning_rate": 7.677473684210526e-05,
      "loss": 1.2565,
      "step": 56
    },
    {
      "epoch": 0.032185206098249576,
      "grad_norm": 0.5821838974952698,
      "learning_rate": 7.624157894736842e-05,
      "loss": 1.6761,
      "step": 57
    },
    {
      "epoch": 0.03274985883681536,
      "grad_norm": 1.3336795568466187,
      "learning_rate": 7.570842105263158e-05,
      "loss": 1.9984,
      "step": 58
    },
    {
      "epoch": 0.033314511575381144,
      "grad_norm": 0.7882184982299805,
      "learning_rate": 7.517526315789474e-05,
      "loss": 0.7926,
      "step": 59
    },
    {
      "epoch": 0.03387916431394692,
      "grad_norm": 0.4720506966114044,
      "learning_rate": 7.464210526315789e-05,
      "loss": 1.5786,
      "step": 60
    },
    {
      "epoch": 0.034443817052512704,
      "grad_norm": 0.4207099974155426,
      "learning_rate": 7.410894736842106e-05,
      "loss": 1.1193,
      "step": 61
    },
    {
      "epoch": 0.03500846979107849,
      "grad_norm": 0.5080116391181946,
      "learning_rate": 7.35757894736842e-05,
      "loss": 1.6818,
      "step": 62
    },
    {
      "epoch": 0.03557312252964427,
      "grad_norm": 0.5660998225212097,
      "learning_rate": 7.304263157894737e-05,
      "loss": 1.8537,
      "step": 63
    },
    {
      "epoch": 0.03613777526821005,
      "grad_norm": 0.4343119263648987,
      "learning_rate": 7.250947368421053e-05,
      "loss": 1.3433,
      "step": 64
    },
    {
      "epoch": 0.03670242800677583,
      "grad_norm": 0.561114490032196,
      "learning_rate": 7.197631578947368e-05,
      "loss": 1.6089,
      "step": 65
    },
    {
      "epoch": 0.037267080745341616,
      "grad_norm": 0.41408398747444153,
      "learning_rate": 7.144315789473684e-05,
      "loss": 2.1082,
      "step": 66
    },
    {
      "epoch": 0.0378317334839074,
      "grad_norm": 0.40642455220222473,
      "learning_rate": 7.091e-05,
      "loss": 1.952,
      "step": 67
    },
    {
      "epoch": 0.038396386222473176,
      "grad_norm": 0.49146607518196106,
      "learning_rate": 7.037684210526316e-05,
      "loss": 1.929,
      "step": 68
    },
    {
      "epoch": 0.03896103896103896,
      "grad_norm": 0.43934860825538635,
      "learning_rate": 6.984368421052632e-05,
      "loss": 1.8151,
      "step": 69
    },
    {
      "epoch": 0.039525691699604744,
      "grad_norm": 0.39021074771881104,
      "learning_rate": 6.931052631578947e-05,
      "loss": 1.7151,
      "step": 70
    },
    {
      "epoch": 0.04009034443817053,
      "grad_norm": 0.5213768482208252,
      "learning_rate": 6.877736842105263e-05,
      "loss": 2.1129,
      "step": 71
    },
    {
      "epoch": 0.040654997176736304,
      "grad_norm": 0.42245039343833923,
      "learning_rate": 6.824421052631579e-05,
      "loss": 2.1972,
      "step": 72
    },
    {
      "epoch": 0.04121964991530209,
      "grad_norm": 0.4925639033317566,
      "learning_rate": 6.771105263157895e-05,
      "loss": 2.3312,
      "step": 73
    },
    {
      "epoch": 0.04178430265386787,
      "grad_norm": 0.41615986824035645,
      "learning_rate": 6.71778947368421e-05,
      "loss": 1.9326,
      "step": 74
    },
    {
      "epoch": 0.042348955392433656,
      "grad_norm": 0.4477844834327698,
      "learning_rate": 6.664473684210527e-05,
      "loss": 1.9983,
      "step": 75
    },
    {
      "epoch": 0.04291360813099943,
      "grad_norm": 0.45667552947998047,
      "learning_rate": 6.611157894736842e-05,
      "loss": 1.7302,
      "step": 76
    },
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 0.5657249093055725,
      "learning_rate": 6.557842105263158e-05,
      "loss": 1.3501,
      "step": 77
    },
    {
      "epoch": 0.044042913608131,
      "grad_norm": 0.48479339480400085,
      "learning_rate": 6.504526315789474e-05,
      "loss": 2.1838,
      "step": 78
    },
    {
      "epoch": 0.044607566346696784,
      "grad_norm": 0.5657017230987549,
      "learning_rate": 6.451210526315789e-05,
      "loss": 1.5316,
      "step": 79
    },
    {
      "epoch": 0.04517221908526256,
      "grad_norm": 0.6498041152954102,
      "learning_rate": 6.397894736842105e-05,
      "loss": 1.7707,
      "step": 80
    },
    {
      "epoch": 0.045736871823828344,
      "grad_norm": 0.5205366611480713,
      "learning_rate": 6.344578947368421e-05,
      "loss": 1.5243,
      "step": 81
    },
    {
      "epoch": 0.04630152456239413,
      "grad_norm": 0.6816235780715942,
      "learning_rate": 6.291263157894737e-05,
      "loss": 1.9903,
      "step": 82
    },
    {
      "epoch": 0.04686617730095991,
      "grad_norm": 0.5851727724075317,
      "learning_rate": 6.237947368421053e-05,
      "loss": 1.086,
      "step": 83
    },
    {
      "epoch": 0.04743083003952569,
      "grad_norm": 0.5946785807609558,
      "learning_rate": 6.184631578947368e-05,
      "loss": 1.6933,
      "step": 84
    },
    {
      "epoch": 0.04799548277809147,
      "grad_norm": 0.9167661666870117,
      "learning_rate": 6.131315789473684e-05,
      "loss": 1.3954,
      "step": 85
    },
    {
      "epoch": 0.048560135516657256,
      "grad_norm": 0.6855114698410034,
      "learning_rate": 6.078e-05,
      "loss": 1.6794,
      "step": 86
    },
    {
      "epoch": 0.04912478825522304,
      "grad_norm": 0.9877620935440063,
      "learning_rate": 6.024684210526315e-05,
      "loss": 1.5267,
      "step": 87
    },
    {
      "epoch": 0.049689440993788817,
      "grad_norm": 1.2663705348968506,
      "learning_rate": 5.9713684210526305e-05,
      "loss": 1.2142,
      "step": 88
    },
    {
      "epoch": 0.0502540937323546,
      "grad_norm": 0.8730637431144714,
      "learning_rate": 5.918052631578947e-05,
      "loss": 1.9942,
      "step": 89
    },
    {
      "epoch": 0.050818746470920384,
      "grad_norm": 1.022507905960083,
      "learning_rate": 5.8647368421052634e-05,
      "loss": 1.7698,
      "step": 90
    },
    {
      "epoch": 0.05138339920948617,
      "grad_norm": 1.0070384740829468,
      "learning_rate": 5.811421052631579e-05,
      "loss": 2.1813,
      "step": 91
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 1.0603997707366943,
      "learning_rate": 5.758105263157894e-05,
      "loss": 1.5043,
      "step": 92
    },
    {
      "epoch": 0.05251270468661773,
      "grad_norm": 1.5354747772216797,
      "learning_rate": 5.70478947368421e-05,
      "loss": 1.4871,
      "step": 93
    },
    {
      "epoch": 0.05307735742518351,
      "grad_norm": 1.4360660314559937,
      "learning_rate": 5.6514736842105256e-05,
      "loss": 1.1194,
      "step": 94
    },
    {
      "epoch": 0.053642010163749296,
      "grad_norm": 2.7259883880615234,
      "learning_rate": 5.5981578947368424e-05,
      "loss": 1.3859,
      "step": 95
    },
    {
      "epoch": 0.05420666290231508,
      "grad_norm": 2.0067079067230225,
      "learning_rate": 5.544842105263158e-05,
      "loss": 1.1774,
      "step": 96
    },
    {
      "epoch": 0.054771315640880856,
      "grad_norm": 1.9540057182312012,
      "learning_rate": 5.491526315789474e-05,
      "loss": 1.838,
      "step": 97
    },
    {
      "epoch": 0.05533596837944664,
      "grad_norm": 3.2931625843048096,
      "learning_rate": 5.438210526315789e-05,
      "loss": 1.8081,
      "step": 98
    },
    {
      "epoch": 0.055900621118012424,
      "grad_norm": 4.112388610839844,
      "learning_rate": 5.384894736842105e-05,
      "loss": 1.0519,
      "step": 99
    },
    {
      "epoch": 0.05646527385657821,
      "grad_norm": 4.771429061889648,
      "learning_rate": 5.331578947368421e-05,
      "loss": 2.072,
      "step": 100
    },
    {
      "epoch": 0.05646527385657821,
      "eval_loss": 1.61591374874115,
      "eval_runtime": 33.6813,
      "eval_samples_per_second": 22.149,
      "eval_steps_per_second": 5.552,
      "step": 100
    },
    {
      "epoch": 0.057029926595143984,
      "grad_norm": 0.26157695055007935,
      "learning_rate": 5.278263157894736e-05,
      "loss": 1.3786,
      "step": 101
    },
    {
      "epoch": 0.05759457933370977,
      "grad_norm": 0.31872278451919556,
      "learning_rate": 5.224947368421053e-05,
      "loss": 1.7082,
      "step": 102
    },
    {
      "epoch": 0.05815923207227555,
      "grad_norm": 0.40259334444999695,
      "learning_rate": 5.171631578947368e-05,
      "loss": 1.7991,
      "step": 103
    },
    {
      "epoch": 0.058723884810841336,
      "grad_norm": 0.5885865688323975,
      "learning_rate": 5.1183157894736844e-05,
      "loss": 1.5969,
      "step": 104
    },
    {
      "epoch": 0.05928853754940711,
      "grad_norm": 0.41334208846092224,
      "learning_rate": 5.065e-05,
      "loss": 1.8226,
      "step": 105
    },
    {
      "epoch": 0.059853190287972896,
      "grad_norm": 0.5378217101097107,
      "learning_rate": 5.011684210526315e-05,
      "loss": 1.6466,
      "step": 106
    },
    {
      "epoch": 0.06041784302653868,
      "grad_norm": 0.5085050463676453,
      "learning_rate": 4.958368421052631e-05,
      "loss": 1.9653,
      "step": 107
    },
    {
      "epoch": 0.060982495765104464,
      "grad_norm": 0.49602341651916504,
      "learning_rate": 4.9050526315789473e-05,
      "loss": 1.409,
      "step": 108
    },
    {
      "epoch": 0.06154714850367024,
      "grad_norm": 0.5390165448188782,
      "learning_rate": 4.851736842105263e-05,
      "loss": 1.3066,
      "step": 109
    },
    {
      "epoch": 0.062111801242236024,
      "grad_norm": 0.5828697085380554,
      "learning_rate": 4.798421052631579e-05,
      "loss": 1.8615,
      "step": 110
    },
    {
      "epoch": 0.06267645398080181,
      "grad_norm": 0.63508141040802,
      "learning_rate": 4.745105263157895e-05,
      "loss": 2.0458,
      "step": 111
    },
    {
      "epoch": 0.06324110671936758,
      "grad_norm": 0.5427883863449097,
      "learning_rate": 4.69178947368421e-05,
      "loss": 1.7312,
      "step": 112
    },
    {
      "epoch": 0.06380575945793338,
      "grad_norm": 0.5502323508262634,
      "learning_rate": 4.638473684210526e-05,
      "loss": 2.3985,
      "step": 113
    },
    {
      "epoch": 0.06437041219649915,
      "grad_norm": 0.4255567491054535,
      "learning_rate": 4.585157894736842e-05,
      "loss": 2.0969,
      "step": 114
    },
    {
      "epoch": 0.06493506493506493,
      "grad_norm": 0.6290948390960693,
      "learning_rate": 4.531842105263158e-05,
      "loss": 1.712,
      "step": 115
    },
    {
      "epoch": 0.06549971767363072,
      "grad_norm": 0.6249313950538635,
      "learning_rate": 4.478526315789473e-05,
      "loss": 1.1716,
      "step": 116
    },
    {
      "epoch": 0.0660643704121965,
      "grad_norm": 0.4874264597892761,
      "learning_rate": 4.425210526315789e-05,
      "loss": 1.614,
      "step": 117
    },
    {
      "epoch": 0.06662902315076229,
      "grad_norm": 0.5078814625740051,
      "learning_rate": 4.3718947368421054e-05,
      "loss": 2.0362,
      "step": 118
    },
    {
      "epoch": 0.06719367588932806,
      "grad_norm": 0.6948334574699402,
      "learning_rate": 4.318578947368421e-05,
      "loss": 1.6969,
      "step": 119
    },
    {
      "epoch": 0.06775832862789384,
      "grad_norm": 0.46054255962371826,
      "learning_rate": 4.265263157894736e-05,
      "loss": 1.9061,
      "step": 120
    },
    {
      "epoch": 0.06832298136645963,
      "grad_norm": 0.4674294590950012,
      "learning_rate": 4.211947368421052e-05,
      "loss": 1.4067,
      "step": 121
    },
    {
      "epoch": 0.06888763410502541,
      "grad_norm": 0.49073663353919983,
      "learning_rate": 4.1586315789473684e-05,
      "loss": 2.3371,
      "step": 122
    },
    {
      "epoch": 0.06945228684359118,
      "grad_norm": 0.49056804180145264,
      "learning_rate": 4.105315789473684e-05,
      "loss": 2.1801,
      "step": 123
    },
    {
      "epoch": 0.07001693958215698,
      "grad_norm": 0.608372688293457,
      "learning_rate": 4.052e-05,
      "loss": 2.0307,
      "step": 124
    },
    {
      "epoch": 0.07058159232072275,
      "grad_norm": 0.46089833974838257,
      "learning_rate": 3.998684210526316e-05,
      "loss": 1.9543,
      "step": 125
    },
    {
      "epoch": 0.07114624505928854,
      "grad_norm": 0.4646291136741638,
      "learning_rate": 3.945368421052631e-05,
      "loss": 1.6708,
      "step": 126
    },
    {
      "epoch": 0.07171089779785432,
      "grad_norm": 0.545235276222229,
      "learning_rate": 3.892052631578947e-05,
      "loss": 2.0372,
      "step": 127
    },
    {
      "epoch": 0.0722755505364201,
      "grad_norm": 0.7160872220993042,
      "learning_rate": 3.838736842105263e-05,
      "loss": 2.0102,
      "step": 128
    },
    {
      "epoch": 0.07284020327498589,
      "grad_norm": 0.5753077864646912,
      "learning_rate": 3.785421052631579e-05,
      "loss": 1.7705,
      "step": 129
    },
    {
      "epoch": 0.07340485601355166,
      "grad_norm": 0.6134698390960693,
      "learning_rate": 3.732105263157894e-05,
      "loss": 1.5995,
      "step": 130
    },
    {
      "epoch": 0.07396950875211744,
      "grad_norm": 0.5752911567687988,
      "learning_rate": 3.67878947368421e-05,
      "loss": 1.4896,
      "step": 131
    },
    {
      "epoch": 0.07453416149068323,
      "grad_norm": 0.7670300602912903,
      "learning_rate": 3.6254736842105264e-05,
      "loss": 1.784,
      "step": 132
    },
    {
      "epoch": 0.07509881422924901,
      "grad_norm": 0.5910040140151978,
      "learning_rate": 3.572157894736842e-05,
      "loss": 1.3716,
      "step": 133
    },
    {
      "epoch": 0.0756634669678148,
      "grad_norm": 0.5962346196174622,
      "learning_rate": 3.518842105263158e-05,
      "loss": 1.6385,
      "step": 134
    },
    {
      "epoch": 0.07622811970638058,
      "grad_norm": 1.3207964897155762,
      "learning_rate": 3.465526315789473e-05,
      "loss": 1.2742,
      "step": 135
    },
    {
      "epoch": 0.07679277244494635,
      "grad_norm": 1.1188924312591553,
      "learning_rate": 3.4122105263157894e-05,
      "loss": 1.9659,
      "step": 136
    },
    {
      "epoch": 0.07735742518351214,
      "grad_norm": 0.6829027533531189,
      "learning_rate": 3.358894736842105e-05,
      "loss": 1.1681,
      "step": 137
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 0.8137729167938232,
      "learning_rate": 3.305578947368421e-05,
      "loss": 1.4063,
      "step": 138
    },
    {
      "epoch": 0.07848673066064371,
      "grad_norm": 0.711093008518219,
      "learning_rate": 3.252263157894737e-05,
      "loss": 1.4551,
      "step": 139
    },
    {
      "epoch": 0.07905138339920949,
      "grad_norm": 1.0196043252944946,
      "learning_rate": 3.198947368421052e-05,
      "loss": 1.8365,
      "step": 140
    },
    {
      "epoch": 0.07961603613777526,
      "grad_norm": 0.8647313714027405,
      "learning_rate": 3.1456315789473684e-05,
      "loss": 1.253,
      "step": 141
    },
    {
      "epoch": 0.08018068887634106,
      "grad_norm": 0.863608717918396,
      "learning_rate": 3.092315789473684e-05,
      "loss": 1.2664,
      "step": 142
    },
    {
      "epoch": 0.08074534161490683,
      "grad_norm": 1.0043619871139526,
      "learning_rate": 3.039e-05,
      "loss": 1.5368,
      "step": 143
    },
    {
      "epoch": 0.08130999435347261,
      "grad_norm": 1.3296562433242798,
      "learning_rate": 2.9856842105263153e-05,
      "loss": 0.8377,
      "step": 144
    },
    {
      "epoch": 0.0818746470920384,
      "grad_norm": 1.5807889699935913,
      "learning_rate": 2.9323684210526317e-05,
      "loss": 1.4706,
      "step": 145
    },
    {
      "epoch": 0.08243929983060418,
      "grad_norm": 1.4404282569885254,
      "learning_rate": 2.879052631578947e-05,
      "loss": 1.6419,
      "step": 146
    },
    {
      "epoch": 0.08300395256916997,
      "grad_norm": 1.8414446115493774,
      "learning_rate": 2.8257368421052628e-05,
      "loss": 1.2406,
      "step": 147
    },
    {
      "epoch": 0.08356860530773574,
      "grad_norm": 6.275533199310303,
      "learning_rate": 2.772421052631579e-05,
      "loss": 2.1809,
      "step": 148
    },
    {
      "epoch": 0.08413325804630152,
      "grad_norm": 3.404439687728882,
      "learning_rate": 2.7191052631578946e-05,
      "loss": 1.8676,
      "step": 149
    },
    {
      "epoch": 0.08469791078486731,
      "grad_norm": 4.620980262756348,
      "learning_rate": 2.6657894736842104e-05,
      "loss": 2.8781,
      "step": 150
    },
    {
      "epoch": 0.08469791078486731,
      "eval_loss": 1.586492657661438,
      "eval_runtime": 33.7145,
      "eval_samples_per_second": 22.127,
      "eval_steps_per_second": 5.547,
      "step": 150
    },
    {
      "epoch": 0.08526256352343309,
      "grad_norm": 0.3272818326950073,
      "learning_rate": 2.6124736842105265e-05,
      "loss": 1.4871,
      "step": 151
    },
    {
      "epoch": 0.08582721626199886,
      "grad_norm": 0.32894277572631836,
      "learning_rate": 2.5591578947368422e-05,
      "loss": 1.7465,
      "step": 152
    },
    {
      "epoch": 0.08639186900056466,
      "grad_norm": 0.34903210401535034,
      "learning_rate": 2.5058421052631576e-05,
      "loss": 2.1659,
      "step": 153
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.309485524892807,
      "learning_rate": 2.4525263157894737e-05,
      "loss": 0.9477,
      "step": 154
    },
    {
      "epoch": 0.08752117447769622,
      "grad_norm": 0.3330695927143097,
      "learning_rate": 2.3992105263157894e-05,
      "loss": 1.5259,
      "step": 155
    },
    {
      "epoch": 0.088085827216262,
      "grad_norm": 0.3170928657054901,
      "learning_rate": 2.345894736842105e-05,
      "loss": 2.1571,
      "step": 156
    },
    {
      "epoch": 0.08865047995482778,
      "grad_norm": 0.44350671768188477,
      "learning_rate": 2.292578947368421e-05,
      "loss": 1.7132,
      "step": 157
    },
    {
      "epoch": 0.08921513269339357,
      "grad_norm": 0.3251064419746399,
      "learning_rate": 2.2392631578947366e-05,
      "loss": 1.7776,
      "step": 158
    },
    {
      "epoch": 0.08977978543195934,
      "grad_norm": 0.4512995183467865,
      "learning_rate": 2.1859473684210527e-05,
      "loss": 1.6642,
      "step": 159
    },
    {
      "epoch": 0.09034443817052512,
      "grad_norm": 0.9298767447471619,
      "learning_rate": 2.132631578947368e-05,
      "loss": 1.8871,
      "step": 160
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.39221644401550293,
      "learning_rate": 2.0793157894736842e-05,
      "loss": 1.6345,
      "step": 161
    },
    {
      "epoch": 0.09147374364765669,
      "grad_norm": 0.4242939054965973,
      "learning_rate": 2.026e-05,
      "loss": 1.5644,
      "step": 162
    },
    {
      "epoch": 0.09203839638622248,
      "grad_norm": 0.39541876316070557,
      "learning_rate": 1.9726842105263157e-05,
      "loss": 2.0449,
      "step": 163
    },
    {
      "epoch": 0.09260304912478826,
      "grad_norm": 0.49802130460739136,
      "learning_rate": 1.9193684210526314e-05,
      "loss": 1.7162,
      "step": 164
    },
    {
      "epoch": 0.09316770186335403,
      "grad_norm": 0.38496336340904236,
      "learning_rate": 1.866052631578947e-05,
      "loss": 2.2872,
      "step": 165
    },
    {
      "epoch": 0.09373235460191982,
      "grad_norm": 0.5159594416618347,
      "learning_rate": 1.8127368421052632e-05,
      "loss": 1.8203,
      "step": 166
    },
    {
      "epoch": 0.0942970073404856,
      "grad_norm": 0.7461097836494446,
      "learning_rate": 1.759421052631579e-05,
      "loss": 2.0484,
      "step": 167
    },
    {
      "epoch": 0.09486166007905138,
      "grad_norm": 0.4127659797668457,
      "learning_rate": 1.7061052631578947e-05,
      "loss": 1.8052,
      "step": 168
    },
    {
      "epoch": 0.09542631281761717,
      "grad_norm": 0.4347990155220032,
      "learning_rate": 1.6527894736842104e-05,
      "loss": 1.7951,
      "step": 169
    },
    {
      "epoch": 0.09599096555618294,
      "grad_norm": 0.4800684154033661,
      "learning_rate": 1.599473684210526e-05,
      "loss": 1.5261,
      "step": 170
    },
    {
      "epoch": 0.09655561829474874,
      "grad_norm": 0.3702009320259094,
      "learning_rate": 1.546157894736842e-05,
      "loss": 2.0826,
      "step": 171
    },
    {
      "epoch": 0.09712027103331451,
      "grad_norm": 0.6166195273399353,
      "learning_rate": 1.4928421052631576e-05,
      "loss": 1.437,
      "step": 172
    },
    {
      "epoch": 0.09768492377188029,
      "grad_norm": 0.5393872857093811,
      "learning_rate": 1.4395263157894735e-05,
      "loss": 2.0329,
      "step": 173
    },
    {
      "epoch": 0.09824957651044608,
      "grad_norm": 0.3947698771953583,
      "learning_rate": 1.3862105263157895e-05,
      "loss": 1.9888,
      "step": 174
    },
    {
      "epoch": 0.09881422924901186,
      "grad_norm": 0.5108495354652405,
      "learning_rate": 1.3328947368421052e-05,
      "loss": 1.6187,
      "step": 175
    },
    {
      "epoch": 0.09937888198757763,
      "grad_norm": 0.42177772521972656,
      "learning_rate": 1.2795789473684211e-05,
      "loss": 1.752,
      "step": 176
    },
    {
      "epoch": 0.09994353472614342,
      "grad_norm": 0.4926985800266266,
      "learning_rate": 1.2262631578947368e-05,
      "loss": 2.1683,
      "step": 177
    },
    {
      "epoch": 0.1005081874647092,
      "grad_norm": 0.46454355120658875,
      "learning_rate": 1.1729473684210526e-05,
      "loss": 1.4214,
      "step": 178
    },
    {
      "epoch": 0.10107284020327499,
      "grad_norm": 0.4612448811531067,
      "learning_rate": 1.1196315789473683e-05,
      "loss": 1.7107,
      "step": 179
    },
    {
      "epoch": 0.10163749294184077,
      "grad_norm": 0.5232647657394409,
      "learning_rate": 1.066315789473684e-05,
      "loss": 2.0586,
      "step": 180
    },
    {
      "epoch": 0.10220214568040654,
      "grad_norm": 0.5285339951515198,
      "learning_rate": 1.013e-05,
      "loss": 1.5791,
      "step": 181
    },
    {
      "epoch": 0.10276679841897234,
      "grad_norm": 0.46414557099342346,
      "learning_rate": 9.596842105263157e-06,
      "loss": 1.7391,
      "step": 182
    },
    {
      "epoch": 0.10333145115753811,
      "grad_norm": 0.5057702660560608,
      "learning_rate": 9.063684210526316e-06,
      "loss": 1.7127,
      "step": 183
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 0.5308021903038025,
      "learning_rate": 8.530526315789473e-06,
      "loss": 1.691,
      "step": 184
    },
    {
      "epoch": 0.10446075663466968,
      "grad_norm": 0.6663089394569397,
      "learning_rate": 7.99736842105263e-06,
      "loss": 1.403,
      "step": 185
    },
    {
      "epoch": 0.10502540937323546,
      "grad_norm": 0.601261556148529,
      "learning_rate": 7.464210526315788e-06,
      "loss": 1.5466,
      "step": 186
    },
    {
      "epoch": 0.10559006211180125,
      "grad_norm": 0.563347578048706,
      "learning_rate": 6.931052631578947e-06,
      "loss": 1.389,
      "step": 187
    },
    {
      "epoch": 0.10615471485036702,
      "grad_norm": 0.6577058434486389,
      "learning_rate": 6.3978947368421055e-06,
      "loss": 2.0848,
      "step": 188
    },
    {
      "epoch": 0.1067193675889328,
      "grad_norm": 1.0290292501449585,
      "learning_rate": 5.864736842105263e-06,
      "loss": 1.715,
      "step": 189
    },
    {
      "epoch": 0.10728402032749859,
      "grad_norm": 1.501333475112915,
      "learning_rate": 5.33157894736842e-06,
      "loss": 1.8911,
      "step": 190
    },
    {
      "epoch": 0.10784867306606437,
      "grad_norm": 0.7974535226821899,
      "learning_rate": 4.7984210526315785e-06,
      "loss": 1.6194,
      "step": 191
    },
    {
      "epoch": 0.10841332580463016,
      "grad_norm": 0.6893588304519653,
      "learning_rate": 4.265263157894737e-06,
      "loss": 2.0794,
      "step": 192
    },
    {
      "epoch": 0.10897797854319594,
      "grad_norm": 0.7431008815765381,
      "learning_rate": 3.732105263157894e-06,
      "loss": 1.2137,
      "step": 193
    },
    {
      "epoch": 0.10954263128176171,
      "grad_norm": 0.8880150318145752,
      "learning_rate": 3.1989473684210527e-06,
      "loss": 1.3514,
      "step": 194
    },
    {
      "epoch": 0.1101072840203275,
      "grad_norm": 1.2837520837783813,
      "learning_rate": 2.66578947368421e-06,
      "loss": 1.6779,
      "step": 195
    },
    {
      "epoch": 0.11067193675889328,
      "grad_norm": 1.7506012916564941,
      "learning_rate": 2.1326315789473684e-06,
      "loss": 0.9495,
      "step": 196
    },
    {
      "epoch": 0.11123658949745906,
      "grad_norm": 1.3716044425964355,
      "learning_rate": 1.5994736842105264e-06,
      "loss": 1.1218,
      "step": 197
    },
    {
      "epoch": 0.11180124223602485,
      "grad_norm": 1.528428077697754,
      "learning_rate": 1.0663157894736842e-06,
      "loss": 0.9545,
      "step": 198
    },
    {
      "epoch": 0.11236589497459062,
      "grad_norm": 1.5911756753921509,
      "learning_rate": 5.331578947368421e-07,
      "loss": 1.27,
      "step": 199
    },
    {
      "epoch": 0.11293054771315642,
      "grad_norm": 2.935549259185791,
      "learning_rate": 0.0,
      "loss": 2.7936,
      "step": 200
    },
    {
      "epoch": 0.11293054771315642,
      "eval_loss": 1.5823931694030762,
      "eval_runtime": 33.5466,
      "eval_samples_per_second": 22.238,
      "eval_steps_per_second": 5.574,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.675201553104896e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}