{
  "best_metric": 0.6739130434782609,
  "best_model_checkpoint": "SW2-DMAE-2\\checkpoint-168",
  "epoch": 68.57142857142857,
  "eval_steps": 500,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 1.6269055604934692,
      "eval_runtime": 0.2761,
      "eval_samples_per_second": 166.629,
      "eval_steps_per_second": 10.867,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 1.6078405380249023,
      "eval_runtime": 0.2401,
      "eval_samples_per_second": 191.623,
      "eval_steps_per_second": 12.497,
      "step": 7
    },
    {
      "epoch": 2.86,
      "learning_rate": 1.4375e-05,
      "loss": 1.618,
      "step": 10
    },
    {
      "epoch": 2.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 1.585246205329895,
      "eval_runtime": 0.3111,
      "eval_samples_per_second": 147.877,
      "eval_steps_per_second": 9.644,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 1.539771556854248,
      "eval_runtime": 0.2925,
      "eval_samples_per_second": 157.267,
      "eval_steps_per_second": 10.257,
      "step": 14
    },
    {
      "epoch": 4.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 1.4947997331619263,
      "eval_runtime": 0.2826,
      "eval_samples_per_second": 162.793,
      "eval_steps_per_second": 10.617,
      "step": 17
    },
    {
      "epoch": 5.71,
      "learning_rate": 1.375e-05,
      "loss": 1.5162,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 1.434383749961853,
      "eval_runtime": 0.2591,
      "eval_samples_per_second": 177.566,
      "eval_steps_per_second": 11.58,
      "step": 21
    },
    {
      "epoch": 6.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 1.3878703117370605,
      "eval_runtime": 0.2371,
      "eval_samples_per_second": 194.049,
      "eval_steps_per_second": 12.655,
      "step": 24
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.17391304347826086,
      "eval_loss": 1.328822135925293,
      "eval_runtime": 0.2481,
      "eval_samples_per_second": 185.442,
      "eval_steps_per_second": 12.094,
      "step": 28
    },
    {
      "epoch": 8.57,
      "learning_rate": 1.3125e-05,
      "loss": 1.3459,
      "step": 30
    },
    {
      "epoch": 8.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2925546169281006,
      "eval_runtime": 0.2481,
      "eval_samples_per_second": 185.442,
      "eval_steps_per_second": 12.094,
      "step": 31
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2562181949615479,
      "eval_runtime": 0.2541,
      "eval_samples_per_second": 181.006,
      "eval_steps_per_second": 11.805,
      "step": 35
    },
    {
      "epoch": 10.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.238446593284607,
      "eval_runtime": 0.2411,
      "eval_samples_per_second": 190.828,
      "eval_steps_per_second": 12.445,
      "step": 38
    },
    {
      "epoch": 11.43,
      "learning_rate": 1.25e-05,
      "loss": 1.2384,
      "step": 40
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2205413579940796,
      "eval_runtime": 0.2537,
      "eval_samples_per_second": 181.326,
      "eval_steps_per_second": 11.826,
      "step": 42
    },
    {
      "epoch": 12.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2173599004745483,
      "eval_runtime": 0.2401,
      "eval_samples_per_second": 191.624,
      "eval_steps_per_second": 12.497,
      "step": 45
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2131370306015015,
      "eval_runtime": 0.2691,
      "eval_samples_per_second": 170.965,
      "eval_steps_per_second": 11.15,
      "step": 49
    },
    {
      "epoch": 14.29,
      "learning_rate": 1.1874999999999999e-05,
      "loss": 1.2049,
      "step": 50
    },
    {
      "epoch": 14.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2104469537734985,
      "eval_runtime": 0.2431,
      "eval_samples_per_second": 189.258,
      "eval_steps_per_second": 12.343,
      "step": 52
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.208552598953247,
      "eval_runtime": 0.2451,
      "eval_samples_per_second": 187.713,
      "eval_steps_per_second": 12.242,
      "step": 56
    },
    {
      "epoch": 16.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2076021432876587,
      "eval_runtime": 0.2556,
      "eval_samples_per_second": 179.993,
      "eval_steps_per_second": 11.739,
      "step": 59
    },
    {
      "epoch": 17.14,
      "learning_rate": 1.125e-05,
      "loss": 1.1815,
      "step": 60
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2051774263381958,
      "eval_runtime": 0.2431,
      "eval_samples_per_second": 189.258,
      "eval_steps_per_second": 12.343,
      "step": 63
    },
    {
      "epoch": 18.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.204942226409912,
      "eval_runtime": 0.3966,
      "eval_samples_per_second": 115.986,
      "eval_steps_per_second": 7.564,
      "step": 66
    },
    {
      "epoch": 20.0,
      "learning_rate": 1.0625e-05,
      "loss": 1.1826,
      "step": 70
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2018660306930542,
      "eval_runtime": 0.3121,
      "eval_samples_per_second": 147.402,
      "eval_steps_per_second": 9.613,
      "step": 70
    },
    {
      "epoch": 20.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.1960418224334717,
      "eval_runtime": 0.3191,
      "eval_samples_per_second": 144.168,
      "eval_steps_per_second": 9.402,
      "step": 73
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.1926813125610352,
      "eval_runtime": 0.3096,
      "eval_samples_per_second": 148.592,
      "eval_steps_per_second": 9.691,
      "step": 77
    },
    {
      "epoch": 22.86,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.1647,
      "step": 80
    },
    {
      "epoch": 22.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.1927775144577026,
      "eval_runtime": 0.2491,
      "eval_samples_per_second": 184.697,
      "eval_steps_per_second": 12.045,
      "step": 80
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.1924192905426025,
      "eval_runtime": 0.2991,
      "eval_samples_per_second": 153.812,
      "eval_steps_per_second": 10.031,
      "step": 84
    },
    {
      "epoch": 24.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.1902908086776733,
      "eval_runtime": 0.3005,
      "eval_samples_per_second": 153.097,
      "eval_steps_per_second": 9.985,
      "step": 87
    },
    {
      "epoch": 25.71,
      "learning_rate": 9.375000000000001e-06,
      "loss": 1.1568,
      "step": 90
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.1878631114959717,
      "eval_runtime": 0.2861,
      "eval_samples_per_second": 160.803,
      "eval_steps_per_second": 10.487,
      "step": 91
    },
    {
      "epoch": 26.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.1913325786590576,
      "eval_runtime": 0.2806,
      "eval_samples_per_second": 163.951,
      "eval_steps_per_second": 10.692,
      "step": 94
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.4782608695652174,
      "eval_loss": 1.204640507698059,
      "eval_runtime": 0.2621,
      "eval_samples_per_second": 175.533,
      "eval_steps_per_second": 11.448,
      "step": 98
    },
    {
      "epoch": 28.57,
      "learning_rate": 8.750000000000001e-06,
      "loss": 1.1432,
      "step": 100
    },
    {
      "epoch": 28.86,
      "eval_accuracy": 0.4782608695652174,
      "eval_loss": 1.193393588066101,
      "eval_runtime": 0.2361,
      "eval_samples_per_second": 194.871,
      "eval_steps_per_second": 12.709,
      "step": 101
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.4782608695652174,
      "eval_loss": 1.166512131690979,
      "eval_runtime": 0.2421,
      "eval_samples_per_second": 190.04,
      "eval_steps_per_second": 12.394,
      "step": 105
    },
    {
      "epoch": 30.86,
      "eval_accuracy": 0.4782608695652174,
      "eval_loss": 1.1600818634033203,
      "eval_runtime": 0.2381,
      "eval_samples_per_second": 193.234,
      "eval_steps_per_second": 12.602,
      "step": 108
    },
    {
      "epoch": 31.43,
      "learning_rate": 8.125e-06,
      "loss": 1.1112,
      "step": 110
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.5,
      "eval_loss": 1.1623895168304443,
      "eval_runtime": 0.2801,
      "eval_samples_per_second": 164.249,
      "eval_steps_per_second": 10.712,
      "step": 112
    },
    {
      "epoch": 32.86,
      "eval_accuracy": 0.5217391304347826,
      "eval_loss": 1.1663668155670166,
      "eval_runtime": 0.3126,
      "eval_samples_per_second": 147.162,
      "eval_steps_per_second": 9.597,
      "step": 115
    },
    {
      "epoch": 34.0,
      "eval_accuracy": 0.5,
      "eval_loss": 1.1692047119140625,
      "eval_runtime": 0.2586,
      "eval_samples_per_second": 177.904,
      "eval_steps_per_second": 11.602,
      "step": 119
    },
    {
      "epoch": 34.29,
      "learning_rate": 7.5e-06,
      "loss": 1.1132,
      "step": 120
    },
    {
      "epoch": 34.86,
      "eval_accuracy": 0.5434782608695652,
      "eval_loss": 1.1513336896896362,
      "eval_runtime": 0.2416,
      "eval_samples_per_second": 190.427,
      "eval_steps_per_second": 12.419,
      "step": 122
    },
    {
      "epoch": 36.0,
      "eval_accuracy": 0.5869565217391305,
      "eval_loss": 1.1384443044662476,
      "eval_runtime": 0.2461,
      "eval_samples_per_second": 186.95,
      "eval_steps_per_second": 12.192,
      "step": 126
    },
    {
      "epoch": 36.86,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 1.127366542816162,
      "eval_runtime": 0.2446,
      "eval_samples_per_second": 188.091,
      "eval_steps_per_second": 12.267,
      "step": 129
    },
    {
      "epoch": 37.14,
      "learning_rate": 6.875e-06,
      "loss": 1.0642,
      "step": 130
    },
    {
      "epoch": 38.0,
      "eval_accuracy": 0.5869565217391305,
      "eval_loss": 1.1442575454711914,
      "eval_runtime": 0.2586,
      "eval_samples_per_second": 177.903,
      "eval_steps_per_second": 11.602,
      "step": 133
    },
    {
      "epoch": 38.86,
      "eval_accuracy": 0.5,
      "eval_loss": 1.1651057004928589,
      "eval_runtime": 0.2496,
      "eval_samples_per_second": 184.324,
      "eval_steps_per_second": 12.021,
      "step": 136
    },
    {
      "epoch": 40.0,
      "learning_rate": 6.25e-06,
      "loss": 1.0439,
      "step": 140
    },
    {
      "epoch": 40.0,
      "eval_accuracy": 0.5,
      "eval_loss": 1.149288296699524,
      "eval_runtime": 0.2441,
      "eval_samples_per_second": 188.478,
      "eval_steps_per_second": 12.292,
      "step": 140
    },
    {
      "epoch": 40.86,
      "eval_accuracy": 0.5217391304347826,
      "eval_loss": 1.1330839395523071,
      "eval_runtime": 0.2811,
      "eval_samples_per_second": 163.664,
      "eval_steps_per_second": 10.674,
      "step": 143
    },
    {
      "epoch": 42.0,
      "eval_accuracy": 0.5869565217391305,
      "eval_loss": 1.1032251119613647,
      "eval_runtime": 0.2521,
      "eval_samples_per_second": 182.499,
      "eval_steps_per_second": 11.902,
      "step": 147
    },
    {
      "epoch": 42.86,
      "learning_rate": 5.625e-06,
      "loss": 1.0362,
      "step": 150
    },
    {
      "epoch": 42.86,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 1.0988132953643799,
      "eval_runtime": 0.2916,
      "eval_samples_per_second": 157.767,
      "eval_steps_per_second": 10.289,
      "step": 150
    },
    {
      "epoch": 44.0,
      "eval_accuracy": 0.5869565217391305,
      "eval_loss": 1.1092532873153687,
      "eval_runtime": 0.2506,
      "eval_samples_per_second": 183.583,
      "eval_steps_per_second": 11.973,
      "step": 154
    },
    {
      "epoch": 44.86,
      "eval_accuracy": 0.5869565217391305,
      "eval_loss": 1.1101136207580566,
      "eval_runtime": 0.22,
      "eval_samples_per_second": 209.044,
      "eval_steps_per_second": 13.633,
      "step": 157
    },
    {
      "epoch": 45.71,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 1.0177,
      "step": 160
    },
    {
      "epoch": 46.0,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 1.0903021097183228,
      "eval_runtime": 0.3931,
      "eval_samples_per_second": 117.022,
      "eval_steps_per_second": 7.632,
      "step": 161
    },
    {
      "epoch": 46.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.069130301475525,
      "eval_runtime": 0.4281,
      "eval_samples_per_second": 107.447,
      "eval_steps_per_second": 7.007,
      "step": 164
    },
    {
      "epoch": 48.0,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 1.0509947538375854,
      "eval_runtime": 0.2701,
      "eval_samples_per_second": 170.332,
      "eval_steps_per_second": 11.109,
      "step": 168
    },
    {
      "epoch": 48.57,
      "learning_rate": 4.3750000000000005e-06,
      "loss": 1.0,
      "step": 170
    },
    {
      "epoch": 48.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.0451492071151733,
      "eval_runtime": 0.2466,
      "eval_samples_per_second": 186.563,
      "eval_steps_per_second": 12.167,
      "step": 171
    },
    {
      "epoch": 50.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.0425117015838623,
      "eval_runtime": 0.2591,
      "eval_samples_per_second": 177.566,
      "eval_steps_per_second": 11.58,
      "step": 175
    },
    {
      "epoch": 50.86,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 1.0512455701828003,
      "eval_runtime": 0.2671,
      "eval_samples_per_second": 172.246,
      "eval_steps_per_second": 11.233,
      "step": 178
    },
    {
      "epoch": 51.43,
      "learning_rate": 3.75e-06,
      "loss": 0.9636,
      "step": 180
    },
    {
      "epoch": 52.0,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 1.044124722480774,
      "eval_runtime": 0.2541,
      "eval_samples_per_second": 181.062,
      "eval_steps_per_second": 11.808,
      "step": 182
    },
    {
      "epoch": 52.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.0401920080184937,
      "eval_runtime": 0.2676,
      "eval_samples_per_second": 171.917,
      "eval_steps_per_second": 11.212,
      "step": 185
    },
    {
      "epoch": 54.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.0161322355270386,
      "eval_runtime": 0.2421,
      "eval_samples_per_second": 190.039,
      "eval_steps_per_second": 12.394,
      "step": 189
    },
    {
      "epoch": 54.29,
      "learning_rate": 3.125e-06,
      "loss": 0.9744,
      "step": 190
    },
    {
      "epoch": 54.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.0072776079177856,
      "eval_runtime": 0.3861,
      "eval_samples_per_second": 119.144,
      "eval_steps_per_second": 7.77,
      "step": 192
    },
    {
      "epoch": 56.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.0047576427459717,
      "eval_runtime": 0.2431,
      "eval_samples_per_second": 189.257,
      "eval_steps_per_second": 12.343,
      "step": 196
    },
    {
      "epoch": 56.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9993048310279846,
      "eval_runtime": 0.2251,
      "eval_samples_per_second": 204.398,
      "eval_steps_per_second": 13.33,
      "step": 199
    },
    {
      "epoch": 57.14,
      "learning_rate": 2.4999999999999998e-06,
      "loss": 0.9233,
      "step": 200
    },
    {
      "epoch": 58.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9939430952072144,
      "eval_runtime": 0.2431,
      "eval_samples_per_second": 189.258,
      "eval_steps_per_second": 12.343,
      "step": 203
    },
    {
      "epoch": 58.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9938895106315613,
      "eval_runtime": 0.2396,
      "eval_samples_per_second": 192.017,
      "eval_steps_per_second": 12.523,
      "step": 206
    },
    {
      "epoch": 60.0,
      "learning_rate": 1.875e-06,
      "loss": 0.9452,
      "step": 210
    },
    {
      "epoch": 60.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9975183010101318,
      "eval_runtime": 0.2521,
      "eval_samples_per_second": 182.499,
      "eval_steps_per_second": 11.902,
      "step": 210
    },
    {
      "epoch": 60.86,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 0.998058557510376,
      "eval_runtime": 0.2471,
      "eval_samples_per_second": 186.193,
      "eval_steps_per_second": 12.143,
      "step": 213
    },
    {
      "epoch": 62.0,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 0.9985237121582031,
      "eval_runtime": 0.2421,
      "eval_samples_per_second": 190.04,
      "eval_steps_per_second": 12.394,
      "step": 217
    },
    {
      "epoch": 62.86,
      "learning_rate": 1.2499999999999999e-06,
      "loss": 0.9183,
      "step": 220
    },
    {
      "epoch": 62.86,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 0.9968777298927307,
      "eval_runtime": 0.2391,
      "eval_samples_per_second": 192.425,
      "eval_steps_per_second": 12.549,
      "step": 220
    },
    {
      "epoch": 64.0,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 0.99575275182724,
      "eval_runtime": 0.2351,
      "eval_samples_per_second": 195.701,
      "eval_steps_per_second": 12.763,
      "step": 224
    },
    {
      "epoch": 64.86,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 0.9928344488143921,
      "eval_runtime": 0.2406,
      "eval_samples_per_second": 191.216,
      "eval_steps_per_second": 12.471,
      "step": 227
    },
    {
      "epoch": 65.71,
      "learning_rate": 6.249999999999999e-07,
      "loss": 0.9449,
      "step": 230
    },
    {
      "epoch": 66.0,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 0.9906012415885925,
      "eval_runtime": 0.2456,
      "eval_samples_per_second": 187.316,
      "eval_steps_per_second": 12.216,
      "step": 231
    },
    {
      "epoch": 66.86,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 0.9892796874046326,
      "eval_runtime": 0.2501,
      "eval_samples_per_second": 183.959,
      "eval_steps_per_second": 11.997,
      "step": 234
    },
    {
      "epoch": 68.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9880576133728027,
      "eval_runtime": 0.2471,
      "eval_samples_per_second": 186.193,
      "eval_steps_per_second": 12.143,
      "step": 238
    },
    {
      "epoch": 68.57,
      "learning_rate": 0.0,
      "loss": 0.9154,
      "step": 240
    },
    {
      "epoch": 68.57,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9880411028862,
      "eval_runtime": 0.2566,
      "eval_samples_per_second": 179.291,
      "eval_steps_per_second": 11.693,
      "step": 240
    },
    {
      "epoch": 68.57,
      "step": 240,
      "total_flos": 4.754181186964685e+17,
      "train_loss": 1.113492695490519,
      "train_runtime": 374.3307,
      "train_samples_per_second": 45.521,
      "train_steps_per_second": 0.641
    }
  ],
  "logging_steps": 10,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 80,
  "save_steps": 500,
  "total_flos": 4.754181186964685e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}