{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 20,
  "global_step": 135,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 2e-05,
      "loss": 0.9768,
      "step": 1
    },
    {
      "epoch": 0.07,
      "learning_rate": 4e-05,
      "loss": 1.0553,
      "step": 2
    },
    {
      "epoch": 0.11,
      "learning_rate": 6e-05,
      "loss": 0.9074,
      "step": 3
    },
    {
      "epoch": 0.15,
      "learning_rate": 8e-05,
      "loss": 1.0351,
      "step": 4
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 0.9918,
      "step": 5
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00012,
      "loss": 0.9872,
      "step": 6
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00014,
      "loss": 0.9573,
      "step": 7
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016,
      "loss": 1.0466,
      "step": 8
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018,
      "loss": 0.8995,
      "step": 9
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.9041,
      "step": 10
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019996841892833,
      "loss": 0.936,
      "step": 11
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019987369566060176,
      "loss": 0.8254,
      "step": 12
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001997158900260614,
      "loss": 0.9508,
      "step": 13
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019949510169813003,
      "loss": 0.929,
      "step": 14
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.9618,
      "step": 15
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001988651744737914,
      "loss": 0.9317,
      "step": 16
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019845643345292054,
      "loss": 0.9399,
      "step": 17
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001979855052384247,
      "loss": 0.9377,
      "step": 18
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019745268727865774,
      "loss": 0.9048,
      "step": 19
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001968583161128631,
      "loss": 0.9311,
      "step": 20
    },
    {
      "epoch": 0.74,
      "eval_loss": 0.8045752644538879,
      "eval_runtime": 2.684,
      "eval_samples_per_second": 1.118,
      "eval_steps_per_second": 0.745,
      "step": 20
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001962027671586086,
      "loss": 0.9376,
      "step": 21
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019548645447466431,
      "loss": 0.8598,
      "step": 22
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019470983049947444,
      "loss": 0.991,
      "step": 23
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019387338576538744,
      "loss": 0.8472,
      "step": 24
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00019297764858882514,
      "loss": 0.8818,
      "step": 25
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00019202318473658705,
      "loss": 0.8879,
      "step": 26
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019101059706849957,
      "loss": 0.8483,
      "step": 27
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001899405251566371,
      "loss": 0.9505,
      "step": 28
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018881364488135448,
      "loss": 0.9116,
      "step": 29
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.8575,
      "step": 30
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00018639234171928353,
      "loss": 0.8093,
      "step": 31
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00018509944817946922,
      "loss": 0.7966,
      "step": 32
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001837528040042142,
      "loss": 0.8263,
      "step": 33
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00018235325976284275,
      "loss": 0.7951,
      "step": 34
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.849,
      "step": 35
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017939903986478355,
      "loss": 0.863,
      "step": 36
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017784623015670238,
      "loss": 0.8144,
      "step": 37
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001762442511011448,
      "loss": 0.8078,
      "step": 38
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00017459411454241822,
      "loss": 0.7997,
      "step": 39
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00017289686274214118,
      "loss": 0.9322,
      "step": 40
    },
    {
      "epoch": 1.48,
      "eval_loss": 0.7793169617652893,
      "eval_runtime": 2.6811,
      "eval_samples_per_second": 1.119,
      "eval_steps_per_second": 0.746,
      "step": 40
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00017115356772092857,
      "loss": 0.8279,
      "step": 41
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001693653305812805,
      "loss": 0.8759,
      "step": 42
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00016753328081210245,
      "loss": 0.8748,
      "step": 43
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00016565857557529566,
      "loss": 0.7638,
      "step": 44
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.000163742398974869,
      "loss": 0.7941,
      "step": 45
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00016178596130903344,
      "loss": 0.8321,
      "step": 46
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001597904983057519,
      "loss": 0.894,
      "step": 47
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00015775727034222675,
      "loss": 0.9176,
      "step": 48
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00015568756164881882,
      "loss": 0.8286,
      "step": 49
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00015358267949789966,
      "loss": 0.9328,
      "step": 50
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00015144395337815064,
      "loss": 0.8644,
      "step": 51
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014927273415482915,
      "loss": 0.7769,
      "step": 52
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001470703932165333,
      "loss": 0.8,
      "step": 53
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00014483832160900326,
      "loss": 0.7781,
      "step": 54
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00014257792915650728,
      "loss": 0.7852,
      "step": 55
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00014029064357136628,
      "loss": 0.7796,
      "step": 56
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00013797790955218014,
      "loss": 0.8287,
      "step": 57
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00013564118787132506,
      "loss": 0.6845,
      "step": 58
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00013328195445229868,
      "loss": 0.7821,
      "step": 59
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.708,
      "step": 60
    },
    {
      "epoch": 2.22,
      "eval_loss": 0.7880761027336121,
      "eval_runtime": 2.6843,
      "eval_samples_per_second": 1.118,
      "eval_steps_per_second": 0.745,
      "step": 60
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0001285019262469976,
      "loss": 0.8098,
      "step": 61
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00012608415062898972,
      "loss": 0.82,
      "step": 62
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00012364989970237248,
      "loss": 0.7187,
      "step": 63
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00012120071099220549,
      "loss": 0.7802,
      "step": 64
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011873813145857249,
      "loss": 0.6834,
      "step": 65
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00011626371651948838,
      "loss": 0.6808,
      "step": 66
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001137790290684638,
      "loss": 0.7881,
      "step": 67
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00011128563848734816,
      "loss": 0.7281,
      "step": 68
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00010878511965507434,
      "loss": 0.7231,
      "step": 69
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00010627905195293135,
      "loss": 0.6938,
      "step": 70
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00010376901826699348,
      "loss": 0.7633,
      "step": 71
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00010125660398833528,
      "loss": 0.8253,
      "step": 72
    },
    {
      "epoch": 2.7,
      "learning_rate": 9.874339601166473e-05,
      "loss": 0.8197,
      "step": 73
    },
    {
      "epoch": 2.74,
      "learning_rate": 9.623098173300654e-05,
      "loss": 0.7403,
      "step": 74
    },
    {
      "epoch": 2.78,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.8175,
      "step": 75
    },
    {
      "epoch": 2.81,
      "learning_rate": 9.121488034492569e-05,
      "loss": 0.7249,
      "step": 76
    },
    {
      "epoch": 2.85,
      "learning_rate": 8.871436151265184e-05,
      "loss": 0.7029,
      "step": 77
    },
    {
      "epoch": 2.89,
      "learning_rate": 8.62209709315362e-05,
      "loss": 0.8081,
      "step": 78
    },
    {
      "epoch": 2.93,
      "learning_rate": 8.373628348051165e-05,
      "loss": 0.7087,
      "step": 79
    },
    {
      "epoch": 2.96,
      "learning_rate": 8.126186854142752e-05,
      "loss": 0.762,
      "step": 80
    },
    {
      "epoch": 2.96,
      "eval_loss": 0.7806326746940613,
      "eval_runtime": 2.6841,
      "eval_samples_per_second": 1.118,
      "eval_steps_per_second": 0.745,
      "step": 80
    },
    {
      "epoch": 3.0,
      "learning_rate": 7.879928900779456e-05,
      "loss": 0.6724,
      "step": 81
    },
    {
      "epoch": 3.04,
      "learning_rate": 7.635010029762756e-05,
      "loss": 0.578,
      "step": 82
    },
    {
      "epoch": 3.07,
      "learning_rate": 7.391584937101033e-05,
      "loss": 0.6599,
      "step": 83
    },
    {
      "epoch": 3.11,
      "learning_rate": 7.149807375300239e-05,
      "loss": 0.732,
      "step": 84
    },
    {
      "epoch": 3.15,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6144,
      "step": 85
    },
    {
      "epoch": 3.19,
      "learning_rate": 6.671804554770135e-05,
      "loss": 0.6812,
      "step": 86
    },
    {
      "epoch": 3.22,
      "learning_rate": 6.435881212867493e-05,
      "loss": 0.6753,
      "step": 87
    },
    {
      "epoch": 3.26,
      "learning_rate": 6.20220904478199e-05,
      "loss": 0.6341,
      "step": 88
    },
    {
      "epoch": 3.3,
      "learning_rate": 5.9709356428633746e-05,
      "loss": 0.6752,
      "step": 89
    },
    {
      "epoch": 3.33,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.6995,
      "step": 90
    },
    {
      "epoch": 3.37,
      "learning_rate": 5.5161678390996796e-05,
      "loss": 0.6411,
      "step": 91
    },
    {
      "epoch": 3.41,
      "learning_rate": 5.292960678346675e-05,
      "loss": 0.6527,
      "step": 92
    },
    {
      "epoch": 3.44,
      "learning_rate": 5.072726584517086e-05,
      "loss": 0.7026,
      "step": 93
    },
    {
      "epoch": 3.48,
      "learning_rate": 4.8556046621849346e-05,
      "loss": 0.6603,
      "step": 94
    },
    {
      "epoch": 3.52,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 0.6798,
      "step": 95
    },
    {
      "epoch": 3.56,
      "learning_rate": 4.431243835118124e-05,
      "loss": 0.623,
      "step": 96
    },
    {
      "epoch": 3.59,
      "learning_rate": 4.224272965777326e-05,
      "loss": 0.685,
      "step": 97
    },
    {
      "epoch": 3.63,
      "learning_rate": 4.020950169424815e-05,
      "loss": 0.7674,
      "step": 98
    },
    {
      "epoch": 3.67,
      "learning_rate": 3.821403869096658e-05,
      "loss": 0.7068,
      "step": 99
    },
    {
      "epoch": 3.7,
      "learning_rate": 3.6257601025131026e-05,
      "loss": 0.6724,
      "step": 100
    },
    {
      "epoch": 3.7,
      "eval_loss": 0.811485767364502,
      "eval_runtime": 2.6837,
      "eval_samples_per_second": 1.118,
      "eval_steps_per_second": 0.745,
      "step": 100
    },
    {
      "epoch": 3.74,
      "learning_rate": 3.4341424424704375e-05,
      "loss": 0.7169,
      "step": 101
    },
    {
      "epoch": 3.78,
      "learning_rate": 3.246671918789755e-05,
      "loss": 0.6499,
      "step": 102
    },
    {
      "epoch": 3.81,
      "learning_rate": 3.063466941871952e-05,
      "loss": 0.7342,
      "step": 103
    },
    {
      "epoch": 3.85,
      "learning_rate": 2.8846432279071467e-05,
      "loss": 0.6587,
      "step": 104
    },
    {
      "epoch": 3.89,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.6042,
      "step": 105
    },
    {
      "epoch": 3.93,
      "learning_rate": 2.540588545758179e-05,
      "loss": 0.6507,
      "step": 106
    },
    {
      "epoch": 3.96,
      "learning_rate": 2.37557488988552e-05,
      "loss": 0.6646,
      "step": 107
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.2153769843297667e-05,
      "loss": 0.6783,
      "step": 108
    },
    {
      "epoch": 4.04,
      "learning_rate": 2.0600960135216462e-05,
      "loss": 0.6036,
      "step": 109
    },
    {
      "epoch": 4.07,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.6631,
      "step": 110
    },
    {
      "epoch": 4.11,
      "learning_rate": 1.7646740237157256e-05,
      "loss": 0.5743,
      "step": 111
    },
    {
      "epoch": 4.15,
      "learning_rate": 1.6247195995785837e-05,
      "loss": 0.6115,
      "step": 112
    },
    {
      "epoch": 4.19,
      "learning_rate": 1.4900551820530828e-05,
      "loss": 0.6387,
      "step": 113
    },
    {
      "epoch": 4.22,
      "learning_rate": 1.3607658280716473e-05,
      "loss": 0.6785,
      "step": 114
    },
    {
      "epoch": 4.26,
      "learning_rate": 1.2369331995613665e-05,
      "loss": 0.6049,
      "step": 115
    },
    {
      "epoch": 4.3,
      "learning_rate": 1.1186355118645554e-05,
      "loss": 0.5745,
      "step": 116
    },
    {
      "epoch": 4.33,
      "learning_rate": 1.0059474843362892e-05,
      "loss": 0.5218,
      "step": 117
    },
    {
      "epoch": 4.37,
      "learning_rate": 8.989402931500434e-06,
      "loss": 0.5492,
      "step": 118
    },
    {
      "epoch": 4.41,
      "learning_rate": 7.976815263412963e-06,
      "loss": 0.6314,
      "step": 119
    },
    {
      "epoch": 4.44,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.6404,
      "step": 120
    },
    {
      "epoch": 4.44,
      "eval_loss": 0.830319344997406,
      "eval_runtime": 2.6841,
      "eval_samples_per_second": 1.118,
      "eval_steps_per_second": 0.745,
      "step": 120
    },
    {
      "epoch": 4.48,
      "learning_rate": 6.126614234612593e-06,
      "loss": 0.6818,
      "step": 121
    },
    {
      "epoch": 4.52,
      "learning_rate": 5.290169500525577e-06,
      "loss": 0.6437,
      "step": 122
    },
    {
      "epoch": 4.56,
      "learning_rate": 4.513545525335705e-06,
      "loss": 0.6208,
      "step": 123
    },
    {
      "epoch": 4.59,
      "learning_rate": 3.797232841391407e-06,
      "loss": 0.5599,
      "step": 124
    },
    {
      "epoch": 4.63,
      "learning_rate": 3.1416838871368924e-06,
      "loss": 0.6858,
      "step": 125
    },
    {
      "epoch": 4.67,
      "learning_rate": 2.5473127213422763e-06,
      "loss": 0.7139,
      "step": 126
    },
    {
      "epoch": 4.7,
      "learning_rate": 2.014494761575314e-06,
      "loss": 0.6138,
      "step": 127
    },
    {
      "epoch": 4.74,
      "learning_rate": 1.543566547079467e-06,
      "loss": 0.631,
      "step": 128
    },
    {
      "epoch": 4.78,
      "learning_rate": 1.134825526208605e-06,
      "loss": 0.5295,
      "step": 129
    },
    {
      "epoch": 4.81,
      "learning_rate": 7.885298685522235e-07,
      "loss": 0.6071,
      "step": 130
    },
    {
      "epoch": 4.85,
      "learning_rate": 5.048983018699827e-07,
      "loss": 0.665,
      "step": 131
    },
    {
      "epoch": 4.89,
      "learning_rate": 2.841099739386066e-07,
      "loss": 0.6381,
      "step": 132
    },
    {
      "epoch": 4.93,
      "learning_rate": 1.2630433939825327e-07,
      "loss": 0.6353,
      "step": 133
    },
    {
      "epoch": 4.96,
      "learning_rate": 3.1581071670006015e-08,
      "loss": 0.7291,
      "step": 134
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.6235,
      "step": 135
    }
  ],
  "logging_steps": 1,
  "max_steps": 135,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.638301223755776e+17,
  "trial_name": null,
  "trial_params": null
}