{
  "best_metric": 0.15990132093429565,
  "best_model_checkpoint": "strategydisofrisksv1/checkpoint-205",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 205,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 3.658454656600952,
      "learning_rate": 9.523809523809525e-07,
      "loss": 1.4175,
      "step": 2
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 3.2751364707946777,
      "learning_rate": 1.904761904761905e-06,
      "loss": 1.4034,
      "step": 4
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 2.307509422302246,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 1.4033,
      "step": 6
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 7.359793186187744,
      "learning_rate": 3.80952380952381e-06,
      "loss": 1.5018,
      "step": 8
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 5.59666633605957,
      "learning_rate": 4.761904761904762e-06,
      "loss": 1.4805,
      "step": 10
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 4.317787170410156,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 1.4057,
      "step": 12
    },
    {
      "epoch": 0.34146341463414637,
      "grad_norm": 5.5472493171691895,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.3436,
      "step": 14
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 3.424031972885132,
      "learning_rate": 7.61904761904762e-06,
      "loss": 1.377,
      "step": 16
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 3.460782051086426,
      "learning_rate": 8.571428571428571e-06,
      "loss": 1.3405,
      "step": 18
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 3.272519588470459,
      "learning_rate": 9.523809523809525e-06,
      "loss": 1.3732,
      "step": 20
    },
    {
      "epoch": 0.5365853658536586,
      "grad_norm": 2.9090654850006104,
      "learning_rate": 9.945652173913044e-06,
      "loss": 1.3401,
      "step": 22
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 2.4508166313171387,
      "learning_rate": 9.836956521739131e-06,
      "loss": 1.3892,
      "step": 24
    },
    {
      "epoch": 0.6341463414634146,
      "grad_norm": 3.865966320037842,
      "learning_rate": 9.728260869565218e-06,
      "loss": 1.3603,
      "step": 26
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 3.798243999481201,
      "learning_rate": 9.619565217391305e-06,
      "loss": 1.3379,
      "step": 28
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 3.441756248474121,
      "learning_rate": 9.510869565217392e-06,
      "loss": 1.3618,
      "step": 30
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 3.554654121398926,
      "learning_rate": 9.402173913043479e-06,
      "loss": 1.3416,
      "step": 32
    },
    {
      "epoch": 0.8292682926829268,
      "grad_norm": 2.5521254539489746,
      "learning_rate": 9.293478260869566e-06,
      "loss": 1.3339,
      "step": 34
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 3.268244743347168,
      "learning_rate": 9.184782608695653e-06,
      "loss": 1.299,
      "step": 36
    },
    {
      "epoch": 0.926829268292683,
      "grad_norm": 3.396571636199951,
      "learning_rate": 9.07608695652174e-06,
      "loss": 1.3283,
      "step": 38
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 5.777693748474121,
      "learning_rate": 8.967391304347827e-06,
      "loss": 1.3184,
      "step": 40
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5487804878048781,
      "eval_f1_macro": 0.5079113924050633,
      "eval_f1_micro": 0.5487804878048781,
      "eval_f1_weighted": 0.5020067922198209,
      "eval_loss": 1.3049376010894775,
      "eval_precision_macro": 0.5905172413793103,
      "eval_precision_micro": 0.5487804878048781,
      "eval_precision_weighted": 0.5805298570227082,
      "eval_recall_macro": 0.55,
      "eval_recall_micro": 0.5487804878048781,
      "eval_recall_weighted": 0.5487804878048781,
      "eval_runtime": 0.4986,
      "eval_samples_per_second": 164.454,
      "eval_steps_per_second": 12.033,
      "step": 41
    },
    {
      "epoch": 1.024390243902439,
      "grad_norm": 3.4227399826049805,
      "learning_rate": 8.858695652173914e-06,
      "loss": 1.2624,
      "step": 42
    },
    {
      "epoch": 1.0731707317073171,
      "grad_norm": 3.7791168689727783,
      "learning_rate": 8.750000000000001e-06,
      "loss": 1.2806,
      "step": 44
    },
    {
      "epoch": 1.1219512195121952,
      "grad_norm": 5.1954498291015625,
      "learning_rate": 8.641304347826088e-06,
      "loss": 1.3604,
      "step": 46
    },
    {
      "epoch": 1.170731707317073,
      "grad_norm": 6.211756229400635,
      "learning_rate": 8.532608695652175e-06,
      "loss": 1.2671,
      "step": 48
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 3.809525489807129,
      "learning_rate": 8.423913043478262e-06,
      "loss": 1.2143,
      "step": 50
    },
    {
      "epoch": 1.2682926829268293,
      "grad_norm": 4.3469696044921875,
      "learning_rate": 8.315217391304349e-06,
      "loss": 1.2812,
      "step": 52
    },
    {
      "epoch": 1.3170731707317074,
      "grad_norm": 5.45401668548584,
      "learning_rate": 8.206521739130436e-06,
      "loss": 1.302,
      "step": 54
    },
    {
      "epoch": 1.3658536585365852,
      "grad_norm": 4.719168663024902,
      "learning_rate": 8.097826086956523e-06,
      "loss": 1.2044,
      "step": 56
    },
    {
      "epoch": 1.4146341463414633,
      "grad_norm": 5.400396823883057,
      "learning_rate": 7.98913043478261e-06,
      "loss": 1.2528,
      "step": 58
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 4.081637859344482,
      "learning_rate": 7.880434782608695e-06,
      "loss": 1.0832,
      "step": 60
    },
    {
      "epoch": 1.5121951219512195,
      "grad_norm": 8.081562995910645,
      "learning_rate": 7.771739130434784e-06,
      "loss": 1.1357,
      "step": 62
    },
    {
      "epoch": 1.5609756097560976,
      "grad_norm": 5.839077949523926,
      "learning_rate": 7.66304347826087e-06,
      "loss": 1.0947,
      "step": 64
    },
    {
      "epoch": 1.6097560975609757,
      "grad_norm": 5.829254627227783,
      "learning_rate": 7.5543478260869576e-06,
      "loss": 1.0257,
      "step": 66
    },
    {
      "epoch": 1.6585365853658538,
      "grad_norm": 5.4526448249816895,
      "learning_rate": 7.445652173913044e-06,
      "loss": 1.0797,
      "step": 68
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 6.3645524978637695,
      "learning_rate": 7.3369565217391315e-06,
      "loss": 0.9097,
      "step": 70
    },
    {
      "epoch": 1.7560975609756098,
      "grad_norm": 5.510509490966797,
      "learning_rate": 7.228260869565218e-06,
      "loss": 1.0205,
      "step": 72
    },
    {
      "epoch": 1.8048780487804879,
      "grad_norm": 6.244691371917725,
      "learning_rate": 7.119565217391305e-06,
      "loss": 1.0144,
      "step": 74
    },
    {
      "epoch": 1.8536585365853657,
      "grad_norm": 7.428989887237549,
      "learning_rate": 7.0108695652173915e-06,
      "loss": 0.9632,
      "step": 76
    },
    {
      "epoch": 1.9024390243902438,
      "grad_norm": 6.228334426879883,
      "learning_rate": 6.9021739130434785e-06,
      "loss": 0.8049,
      "step": 78
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 4.784652233123779,
      "learning_rate": 6.793478260869566e-06,
      "loss": 0.7772,
      "step": 80
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.2926740646362305,
      "learning_rate": 6.6847826086956524e-06,
      "loss": 0.8149,
      "step": 82
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.926829268292683,
      "eval_f1_macro": 0.9260584103480483,
      "eval_f1_micro": 0.926829268292683,
      "eval_f1_weighted": 0.9262945592194588,
      "eval_loss": 0.7190239429473877,
      "eval_precision_macro": 0.9312770562770563,
      "eval_precision_micro": 0.926829268292683,
      "eval_precision_weighted": 0.9323989019110971,
      "eval_recall_macro": 0.9273809523809523,
      "eval_recall_micro": 0.926829268292683,
      "eval_recall_weighted": 0.926829268292683,
      "eval_runtime": 0.4833,
      "eval_samples_per_second": 169.67,
      "eval_steps_per_second": 12.415,
      "step": 82
    },
    {
      "epoch": 2.048780487804878,
      "grad_norm": 5.493005275726318,
      "learning_rate": 6.57608695652174e-06,
      "loss": 0.7457,
      "step": 84
    },
    {
      "epoch": 2.097560975609756,
      "grad_norm": 6.086998462677002,
      "learning_rate": 6.521739130434783e-06,
      "loss": 0.7334,
      "step": 86
    },
    {
      "epoch": 2.1463414634146343,
      "grad_norm": 5.742645740509033,
      "learning_rate": 6.41304347826087e-06,
      "loss": 0.8067,
      "step": 88
    },
    {
      "epoch": 2.1951219512195124,
      "grad_norm": 7.06817626953125,
      "learning_rate": 6.304347826086958e-06,
      "loss": 0.6018,
      "step": 90
    },
    {
      "epoch": 2.2439024390243905,
      "grad_norm": 5.059027194976807,
      "learning_rate": 6.195652173913044e-06,
      "loss": 0.6361,
      "step": 92
    },
    {
      "epoch": 2.292682926829268,
      "grad_norm": 7.772392272949219,
      "learning_rate": 6.086956521739132e-06,
      "loss": 0.7838,
      "step": 94
    },
    {
      "epoch": 2.341463414634146,
      "grad_norm": 4.42880916595459,
      "learning_rate": 5.978260869565218e-06,
      "loss": 0.6915,
      "step": 96
    },
    {
      "epoch": 2.3902439024390243,
      "grad_norm": 4.635205268859863,
      "learning_rate": 5.8695652173913055e-06,
      "loss": 0.5535,
      "step": 98
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 4.7791666984558105,
      "learning_rate": 5.760869565217392e-06,
      "loss": 0.5392,
      "step": 100
    },
    {
      "epoch": 2.4878048780487805,
      "grad_norm": 6.933748722076416,
      "learning_rate": 5.652173913043479e-06,
      "loss": 0.5618,
      "step": 102
    },
    {
      "epoch": 2.5365853658536586,
      "grad_norm": 5.073132514953613,
      "learning_rate": 5.543478260869566e-06,
      "loss": 0.4763,
      "step": 104
    },
    {
      "epoch": 2.5853658536585367,
      "grad_norm": 5.315598487854004,
      "learning_rate": 5.4347826086956525e-06,
      "loss": 0.4308,
      "step": 106
    },
    {
      "epoch": 2.6341463414634148,
      "grad_norm": 5.840494632720947,
      "learning_rate": 5.3260869565217395e-06,
      "loss": 0.4109,
      "step": 108
    },
    {
      "epoch": 2.682926829268293,
      "grad_norm": 5.477383613586426,
      "learning_rate": 5.2173913043478265e-06,
      "loss": 0.5133,
      "step": 110
    },
    {
      "epoch": 2.7317073170731705,
      "grad_norm": 4.808891296386719,
      "learning_rate": 5.108695652173914e-06,
      "loss": 0.4048,
      "step": 112
    },
    {
      "epoch": 2.7804878048780486,
      "grad_norm": 6.304122447967529,
      "learning_rate": 5e-06,
      "loss": 0.4002,
      "step": 114
    },
    {
      "epoch": 2.8292682926829267,
      "grad_norm": 6.4951348304748535,
      "learning_rate": 4.891304347826087e-06,
      "loss": 0.3788,
      "step": 116
    },
    {
      "epoch": 2.8780487804878048,
      "grad_norm": 3.5770864486694336,
      "learning_rate": 4.782608695652174e-06,
      "loss": 0.3845,
      "step": 118
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 6.861332893371582,
      "learning_rate": 4.673913043478261e-06,
      "loss": 0.6693,
      "step": 120
    },
    {
      "epoch": 2.975609756097561,
      "grad_norm": 6.302731513977051,
      "learning_rate": 4.565217391304348e-06,
      "loss": 0.3862,
      "step": 122
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.975609756097561,
      "eval_f1_macro": 0.974930590799176,
      "eval_f1_micro": 0.975609756097561,
      "eval_f1_weighted": 0.9752584323168365,
      "eval_loss": 0.28084805607795715,
      "eval_precision_macro": 0.9767316017316017,
      "eval_precision_micro": 0.975609756097561,
      "eval_precision_weighted": 0.9767447999155316,
      "eval_recall_macro": 0.975,
      "eval_recall_micro": 0.975609756097561,
      "eval_recall_weighted": 0.975609756097561,
      "eval_runtime": 0.496,
      "eval_samples_per_second": 165.313,
      "eval_steps_per_second": 12.096,
      "step": 123
    },
    {
      "epoch": 3.024390243902439,
      "grad_norm": 5.4799089431762695,
      "learning_rate": 4.456521739130435e-06,
      "loss": 0.4782,
      "step": 124
    },
    {
      "epoch": 3.073170731707317,
      "grad_norm": 4.1216254234313965,
      "learning_rate": 4.347826086956522e-06,
      "loss": 0.2859,
      "step": 126
    },
    {
      "epoch": 3.1219512195121952,
      "grad_norm": 2.9940977096557617,
      "learning_rate": 4.239130434782609e-06,
      "loss": 0.2228,
      "step": 128
    },
    {
      "epoch": 3.1707317073170733,
      "grad_norm": 5.191917419433594,
      "learning_rate": 4.130434782608696e-06,
      "loss": 0.4608,
      "step": 130
    },
    {
      "epoch": 3.2195121951219514,
      "grad_norm": 8.951691627502441,
      "learning_rate": 4.021739130434783e-06,
      "loss": 0.3534,
      "step": 132
    },
    {
      "epoch": 3.2682926829268295,
      "grad_norm": 3.320030450820923,
      "learning_rate": 3.91304347826087e-06,
      "loss": 0.3589,
      "step": 134
    },
    {
      "epoch": 3.317073170731707,
      "grad_norm": 5.8095927238464355,
      "learning_rate": 3.804347826086957e-06,
      "loss": 0.3599,
      "step": 136
    },
    {
      "epoch": 3.3658536585365852,
      "grad_norm": 4.727943420410156,
      "learning_rate": 3.6956521739130436e-06,
      "loss": 0.394,
      "step": 138
    },
    {
      "epoch": 3.4146341463414633,
      "grad_norm": 3.2468807697296143,
      "learning_rate": 3.5869565217391305e-06,
      "loss": 0.2072,
      "step": 140
    },
    {
      "epoch": 3.4634146341463414,
      "grad_norm": 2.6724114418029785,
      "learning_rate": 3.4782608695652175e-06,
      "loss": 0.2368,
      "step": 142
    },
    {
      "epoch": 3.5121951219512195,
      "grad_norm": 7.218781471252441,
      "learning_rate": 3.3695652173913045e-06,
      "loss": 0.3322,
      "step": 144
    },
    {
      "epoch": 3.5609756097560976,
      "grad_norm": 4.017630577087402,
      "learning_rate": 3.2608695652173914e-06,
      "loss": 0.2232,
      "step": 146
    },
    {
      "epoch": 3.6097560975609757,
      "grad_norm": 3.567613363265991,
      "learning_rate": 3.152173913043479e-06,
      "loss": 0.3167,
      "step": 148
    },
    {
      "epoch": 3.658536585365854,
      "grad_norm": 5.940097332000732,
      "learning_rate": 3.043478260869566e-06,
      "loss": 0.3129,
      "step": 150
    },
    {
      "epoch": 3.7073170731707314,
      "grad_norm": 1.8391088247299194,
      "learning_rate": 2.9347826086956528e-06,
      "loss": 0.2177,
      "step": 152
    },
    {
      "epoch": 3.7560975609756095,
      "grad_norm": 6.80277681350708,
      "learning_rate": 2.8260869565217393e-06,
      "loss": 0.2086,
      "step": 154
    },
    {
      "epoch": 3.8048780487804876,
      "grad_norm": 5.100131511688232,
      "learning_rate": 2.7173913043478263e-06,
      "loss": 0.2072,
      "step": 156
    },
    {
      "epoch": 3.8536585365853657,
      "grad_norm": 7.363709449768066,
      "learning_rate": 2.6086956521739132e-06,
      "loss": 0.4223,
      "step": 158
    },
    {
      "epoch": 3.902439024390244,
      "grad_norm": 2.784132480621338,
      "learning_rate": 2.5e-06,
      "loss": 0.2342,
      "step": 160
    },
    {
      "epoch": 3.951219512195122,
      "grad_norm": 10.512962341308594,
      "learning_rate": 2.391304347826087e-06,
      "loss": 0.3363,
      "step": 162
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.996764659881592,
      "learning_rate": 2.282608695652174e-06,
      "loss": 0.1728,
      "step": 164
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.975609756097561,
      "eval_f1_macro": 0.974930590799176,
      "eval_f1_micro": 0.975609756097561,
      "eval_f1_weighted": 0.9752584323168365,
      "eval_loss": 0.17828890681266785,
      "eval_precision_macro": 0.9767316017316017,
      "eval_precision_micro": 0.975609756097561,
      "eval_precision_weighted": 0.9767447999155316,
      "eval_recall_macro": 0.975,
      "eval_recall_micro": 0.975609756097561,
      "eval_recall_weighted": 0.975609756097561,
      "eval_runtime": 0.486,
      "eval_samples_per_second": 168.741,
      "eval_steps_per_second": 12.347,
      "step": 164
    },
    {
      "epoch": 4.048780487804878,
      "grad_norm": 11.200080871582031,
      "learning_rate": 2.173913043478261e-06,
      "loss": 0.3192,
      "step": 166
    },
    {
      "epoch": 4.097560975609756,
      "grad_norm": 4.50062370300293,
      "learning_rate": 2.065217391304348e-06,
      "loss": 0.3224,
      "step": 168
    },
    {
      "epoch": 4.146341463414634,
      "grad_norm": 2.1641335487365723,
      "learning_rate": 1.956521739130435e-06,
      "loss": 0.2588,
      "step": 170
    },
    {
      "epoch": 4.195121951219512,
      "grad_norm": 6.210737705230713,
      "learning_rate": 1.8478260869565218e-06,
      "loss": 0.1391,
      "step": 172
    },
    {
      "epoch": 4.2439024390243905,
      "grad_norm": 4.513918876647949,
      "learning_rate": 1.7391304347826088e-06,
      "loss": 0.1949,
      "step": 174
    },
    {
      "epoch": 4.2926829268292686,
      "grad_norm": 5.105907917022705,
      "learning_rate": 1.6304347826086957e-06,
      "loss": 0.4274,
      "step": 176
    },
    {
      "epoch": 4.341463414634147,
      "grad_norm": 13.60393238067627,
      "learning_rate": 1.521739130434783e-06,
      "loss": 0.3062,
      "step": 178
    },
    {
      "epoch": 4.390243902439025,
      "grad_norm": 2.7764010429382324,
      "learning_rate": 1.4130434782608697e-06,
      "loss": 0.1415,
      "step": 180
    },
    {
      "epoch": 4.439024390243903,
      "grad_norm": 5.599649906158447,
      "learning_rate": 1.3043478260869566e-06,
      "loss": 0.308,
      "step": 182
    },
    {
      "epoch": 4.487804878048781,
      "grad_norm": 11.585519790649414,
      "learning_rate": 1.1956521739130436e-06,
      "loss": 0.3944,
      "step": 184
    },
    {
      "epoch": 4.536585365853659,
      "grad_norm": 2.6623806953430176,
      "learning_rate": 1.0869565217391306e-06,
      "loss": 0.1589,
      "step": 186
    },
    {
      "epoch": 4.585365853658536,
      "grad_norm": 12.680092811584473,
      "learning_rate": 9.782608695652175e-07,
      "loss": 0.236,
      "step": 188
    },
    {
      "epoch": 4.634146341463414,
      "grad_norm": 2.8459999561309814,
      "learning_rate": 8.695652173913044e-07,
      "loss": 0.284,
      "step": 190
    },
    {
      "epoch": 4.682926829268292,
      "grad_norm": 2.673713207244873,
      "learning_rate": 7.608695652173914e-07,
      "loss": 0.1493,
      "step": 192
    },
    {
      "epoch": 4.7317073170731705,
      "grad_norm": 2.6639437675476074,
      "learning_rate": 6.521739130434783e-07,
      "loss": 0.1627,
      "step": 194
    },
    {
      "epoch": 4.780487804878049,
      "grad_norm": 1.504746913909912,
      "learning_rate": 5.434782608695653e-07,
      "loss": 0.1257,
      "step": 196
    },
    {
      "epoch": 4.829268292682927,
      "grad_norm": 7.770730018615723,
      "learning_rate": 4.347826086956522e-07,
      "loss": 0.1999,
      "step": 198
    },
    {
      "epoch": 4.878048780487805,
      "grad_norm": 2.6138458251953125,
      "learning_rate": 3.2608695652173915e-07,
      "loss": 0.1497,
      "step": 200
    },
    {
      "epoch": 4.926829268292683,
      "grad_norm": 4.859775066375732,
      "learning_rate": 2.173913043478261e-07,
      "loss": 0.1766,
      "step": 202
    },
    {
      "epoch": 4.975609756097561,
      "grad_norm": 4.779507160186768,
      "learning_rate": 1.0869565217391305e-07,
      "loss": 0.1548,
      "step": 204
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.975609756097561,
      "eval_f1_macro": 0.974930590799176,
      "eval_f1_micro": 0.975609756097561,
      "eval_f1_weighted": 0.9752584323168365,
      "eval_loss": 0.15990132093429565,
      "eval_precision_macro": 0.9767316017316017,
      "eval_precision_micro": 0.975609756097561,
      "eval_precision_weighted": 0.9767447999155316,
      "eval_recall_macro": 0.975,
      "eval_recall_micro": 0.975609756097561,
      "eval_recall_weighted": 0.975609756097561,
      "eval_runtime": 0.4995,
      "eval_samples_per_second": 164.175,
      "eval_steps_per_second": 12.013,
      "step": 205
    }
  ],
  "logging_steps": 2,
  "max_steps": 205,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 215929561128960.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}