{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9855072463768115,
  "eval_steps": 500,
  "global_step": 274,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.036231884057971016,
      "grad_norm": 14.9375,
      "learning_rate": 7.6092814745757e-06,
      "loss": 2.5084,
      "step": 5
    },
    {
      "epoch": 0.07246376811594203,
      "grad_norm": 12.4375,
      "learning_rate": 1.7120883317795324e-05,
      "loss": 2.1352,
      "step": 10
    },
    {
      "epoch": 0.10869565217391304,
      "grad_norm": 9.9375,
      "learning_rate": 2.663248516101495e-05,
      "loss": 1.8228,
      "step": 15
    },
    {
      "epoch": 0.14492753623188406,
      "grad_norm": 6.8125,
      "learning_rate": 3.614408700423457e-05,
      "loss": 1.7731,
      "step": 20
    },
    {
      "epoch": 0.18115942028985507,
      "grad_norm": 9.0,
      "learning_rate": 4.56556888474542e-05,
      "loss": 1.7802,
      "step": 25
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 5.8125,
      "learning_rate": 5.5167290690673825e-05,
      "loss": 1.7023,
      "step": 30
    },
    {
      "epoch": 0.2536231884057971,
      "grad_norm": 7.8125,
      "learning_rate": 6.467889253389345e-05,
      "loss": 1.5471,
      "step": 35
    },
    {
      "epoch": 0.2898550724637681,
      "grad_norm": 6.46875,
      "learning_rate": 6.656748973090775e-05,
      "loss": 1.6252,
      "step": 40
    },
    {
      "epoch": 0.32608695652173914,
      "grad_norm": 6.8125,
      "learning_rate": 6.651176519947932e-05,
      "loss": 1.5479,
      "step": 45
    },
    {
      "epoch": 0.36231884057971014,
      "grad_norm": 7.125,
      "learning_rate": 6.641327724377154e-05,
      "loss": 1.597,
      "step": 50
    },
    {
      "epoch": 0.39855072463768115,
      "grad_norm": 6.3125,
      "learning_rate": 6.627219501779086e-05,
      "loss": 1.5158,
      "step": 55
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 5.3125,
      "learning_rate": 6.608876083161054e-05,
      "loss": 1.5186,
      "step": 60
    },
    {
      "epoch": 0.47101449275362317,
      "grad_norm": 5.09375,
      "learning_rate": 6.58632897352008e-05,
      "loss": 1.5481,
      "step": 65
    },
    {
      "epoch": 0.5072463768115942,
      "grad_norm": 6.96875,
      "learning_rate": 6.55961689773274e-05,
      "loss": 1.4859,
      "step": 70
    },
    {
      "epoch": 0.5434782608695652,
      "grad_norm": 5.34375,
      "learning_rate": 6.528785734044831e-05,
      "loss": 1.5245,
      "step": 75
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 5.75,
      "learning_rate": 6.493888435275035e-05,
      "loss": 1.4991,
      "step": 80
    },
    {
      "epoch": 0.6159420289855072,
      "grad_norm": 5.1875,
      "learning_rate": 6.45498493786795e-05,
      "loss": 1.4538,
      "step": 85
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 5.34375,
      "learning_rate": 6.412142058952673e-05,
      "loss": 1.4545,
      "step": 90
    },
    {
      "epoch": 0.6884057971014492,
      "grad_norm": 5.375,
      "learning_rate": 6.365433381583738e-05,
      "loss": 1.4556,
      "step": 95
    },
    {
      "epoch": 0.7246376811594203,
      "grad_norm": 5.8125,
      "learning_rate": 6.314939128361522e-05,
      "loss": 1.3423,
      "step": 100
    },
    {
      "epoch": 0.7608695652173914,
      "grad_norm": 4.75,
      "learning_rate": 6.260746023649154e-05,
      "loss": 1.4025,
      "step": 105
    },
    {
      "epoch": 0.7971014492753623,
      "grad_norm": 5.1875,
      "learning_rate": 6.202947144622597e-05,
      "loss": 1.4463,
      "step": 110
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 5.3125,
      "learning_rate": 6.141641761409703e-05,
      "loss": 1.3562,
      "step": 115
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 4.375,
      "learning_rate": 6.0769351665928224e-05,
      "loss": 1.2993,
      "step": 120
    },
    {
      "epoch": 0.9057971014492754,
      "grad_norm": 5.15625,
      "learning_rate": 6.0089384943677825e-05,
      "loss": 1.4187,
      "step": 125
    },
    {
      "epoch": 0.9420289855072463,
      "grad_norm": 6.25,
      "learning_rate": 5.9377685296698475e-05,
      "loss": 1.4398,
      "step": 130
    },
    {
      "epoch": 0.9782608695652174,
      "grad_norm": 4.875,
      "learning_rate": 5.863547507594469e-05,
      "loss": 1.3188,
      "step": 135
    },
    {
      "epoch": 0.9927536231884058,
      "eval_loss": 1.587249755859375,
      "eval_runtime": 7.0298,
      "eval_samples_per_second": 27.597,
      "eval_steps_per_second": 27.597,
      "step": 137
    },
    {
      "epoch": 1.0144927536231885,
      "grad_norm": 4.28125,
      "learning_rate": 5.786402903457346e-05,
      "loss": 1.1541,
      "step": 140
    },
    {
      "epoch": 1.0507246376811594,
      "grad_norm": 5.59375,
      "learning_rate": 5.7064672138543405e-05,
      "loss": 0.8612,
      "step": 145
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 4.3125,
      "learning_rate": 5.6238777290973176e-05,
      "loss": 0.8598,
      "step": 150
    },
    {
      "epoch": 1.1231884057971016,
      "grad_norm": 4.625,
      "learning_rate": 5.538776297416715e-05,
      "loss": 0.8893,
      "step": 155
    },
    {
      "epoch": 1.1594202898550725,
      "grad_norm": 4.5,
      "learning_rate": 5.451309081335849e-05,
      "loss": 0.8668,
      "step": 160
    },
    {
      "epoch": 1.1956521739130435,
      "grad_norm": 5.71875,
      "learning_rate": 5.361626306635384e-05,
      "loss": 0.8703,
      "step": 165
    },
    {
      "epoch": 1.2318840579710144,
      "grad_norm": 4.53125,
      "learning_rate": 5.269882004339117e-05,
      "loss": 0.9089,
      "step": 170
    },
    {
      "epoch": 1.2681159420289856,
      "grad_norm": 5.15625,
      "learning_rate": 5.176233746164218e-05,
      "loss": 0.8584,
      "step": 175
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 5.0,
      "learning_rate": 5.0808423738902994e-05,
      "loss": 0.889,
      "step": 180
    },
    {
      "epoch": 1.3405797101449275,
      "grad_norm": 5.21875,
      "learning_rate": 4.983871723112121e-05,
      "loss": 0.8875,
      "step": 185
    },
    {
      "epoch": 1.3768115942028984,
      "grad_norm": 4.78125,
      "learning_rate": 4.885488341850385e-05,
      "loss": 0.7813,
      "step": 190
    },
    {
      "epoch": 1.4130434782608696,
      "grad_norm": 4.53125,
      "learning_rate": 4.785861204503921e-05,
      "loss": 0.8475,
      "step": 195
    },
    {
      "epoch": 1.4492753623188406,
      "grad_norm": 4.5625,
      "learning_rate": 4.6851614216345356e-05,
      "loss": 0.8209,
      "step": 200
    },
    {
      "epoch": 1.4855072463768115,
      "grad_norm": 4.71875,
      "learning_rate": 4.583561946082986e-05,
      "loss": 0.8562,
      "step": 205
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 4.5625,
      "learning_rate": 4.48123727592082e-05,
      "loss": 0.8679,
      "step": 210
    },
    {
      "epoch": 1.5579710144927537,
      "grad_norm": 4.71875,
      "learning_rate": 4.378363154748271e-05,
      "loss": 0.7851,
      "step": 215
    },
    {
      "epoch": 1.5942028985507246,
      "grad_norm": 4.71875,
      "learning_rate": 4.2751162698529384e-05,
      "loss": 0.7965,
      "step": 220
    },
    {
      "epoch": 1.6304347826086958,
      "grad_norm": 4.8125,
      "learning_rate": 4.171673948747689e-05,
      "loss": 0.7851,
      "step": 225
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 4.21875,
      "learning_rate": 4.0682138546089384e-05,
      "loss": 0.7677,
      "step": 230
    },
    {
      "epoch": 1.7028985507246377,
      "grad_norm": 4.71875,
      "learning_rate": 3.964913681138471e-05,
      "loss": 0.7773,
      "step": 235
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 4.34375,
      "learning_rate": 3.861950847372783e-05,
      "loss": 0.7753,
      "step": 240
    },
    {
      "epoch": 1.7753623188405796,
      "grad_norm": 4.40625,
      "learning_rate": 3.7595021929642044e-05,
      "loss": 0.7799,
      "step": 245
    },
    {
      "epoch": 1.8115942028985508,
      "grad_norm": 4.375,
      "learning_rate": 3.657743674457098e-05,
      "loss": 0.7457,
      "step": 250
    },
    {
      "epoch": 1.8478260869565217,
      "grad_norm": 4.5,
      "learning_rate": 3.556850063080809e-05,
      "loss": 0.7378,
      "step": 255
    },
    {
      "epoch": 1.8840579710144927,
      "grad_norm": 5.0625,
      "learning_rate": 3.456994644578412e-05,
      "loss": 0.837,
      "step": 260
    },
    {
      "epoch": 1.9202898550724639,
      "grad_norm": 4.65625,
      "learning_rate": 3.358348921586782e-05,
      "loss": 0.7719,
      "step": 265
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 4.96875,
      "learning_rate": 3.261082319079179e-05,
      "loss": 0.7676,
      "step": 270
    },
    {
      "epoch": 1.9855072463768115,
      "eval_loss": 1.4368990659713745,
      "eval_runtime": 6.9084,
      "eval_samples_per_second": 28.082,
      "eval_steps_per_second": 28.082,
      "step": 274
    }
  ],
  "logging_steps": 5,
  "max_steps": 414,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6864003280181658e+17,
  "train_batch_size": 140,
  "trial_name": null,
  "trial_params": null
}