{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 2.3208867715652532,
      "learning_rate": 0.0001,
      "loss": 0.6419,
      "step": 1
    },
    {
      "epoch": 0.17,
      "grad_norm": 3.9860672929128493,
      "learning_rate": 0.0002,
      "loss": 1.7609,
      "step": 2
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.5218853167370665,
      "learning_rate": 0.00019957341762950344,
      "loss": 0.2755,
      "step": 3
    },
    {
      "epoch": 0.33,
      "grad_norm": 2.4757099710342465,
      "learning_rate": 0.0001982973099683902,
      "loss": 0.5239,
      "step": 4
    },
    {
      "epoch": 0.42,
      "grad_norm": 2.276172663310605,
      "learning_rate": 0.00019618256431728194,
      "loss": 0.8284,
      "step": 5
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.0157395646130367,
      "learning_rate": 0.00019324722294043558,
      "loss": 0.9007,
      "step": 6
    },
    {
      "epoch": 0.58,
      "grad_norm": 2.1066254910890994,
      "learning_rate": 0.00018951632913550626,
      "loss": 0.2808,
      "step": 7
    },
    {
      "epoch": 0.67,
      "grad_norm": 2.3010925220102396,
      "learning_rate": 0.00018502171357296144,
      "loss": 0.5595,
      "step": 8
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.3134101621469307,
      "learning_rate": 0.000179801722728024,
      "loss": 0.1835,
      "step": 9
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.6534325687337386,
      "learning_rate": 0.00017390089172206592,
      "loss": 0.359,
      "step": 10
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.3135588503352662,
      "learning_rate": 0.00016736956436465573,
      "loss": 0.1781,
      "step": 11
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0,
      "learning_rate": 0.00016026346363792567,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.08,
      "grad_norm": 1.146201037238247,
      "learning_rate": 0.0001526432162877356,
      "loss": 0.1308,
      "step": 13
    },
    {
      "epoch": 1.17,
      "grad_norm": 2.372313237793861,
      "learning_rate": 0.00014457383557765386,
      "loss": 0.6192,
      "step": 14
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.092432177989885,
      "learning_rate": 0.00013612416661871533,
      "loss": 0.138,
      "step": 15
    },
    {
      "epoch": 1.33,
      "grad_norm": 1.1294704122522843,
      "learning_rate": 0.0001273662990072083,
      "loss": 0.1128,
      "step": 16
    },
    {
      "epoch": 1.42,
      "grad_norm": 1.0132866129792448,
      "learning_rate": 0.00011837495178165706,
      "loss": 0.1337,
      "step": 17
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.6395498990357573,
      "learning_rate": 0.00010922683594633021,
      "loss": 0.2742,
      "step": 18
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.0,
      "learning_rate": 9.077316405366981e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.75,
      "grad_norm": 2.3561969051397496,
      "learning_rate": 8.162504821834295e-05,
      "loss": 0.5952,
      "step": 21
    },
    {
      "epoch": 1.83,
      "grad_norm": 1.5708899764007838,
      "learning_rate": 7.263370099279172e-05,
      "loss": 0.274,
      "step": 22
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.4599456482507043,
      "learning_rate": 6.387583338128471e-05,
      "loss": 0.1962,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7761124580034275,
      "learning_rate": 5.542616442234618e-05,
      "loss": 0.3381,
      "step": 24
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.6310401213232668,
      "learning_rate": 4.735678371226441e-05,
      "loss": 0.2213,
      "step": 25
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.9528069569171689,
      "learning_rate": 3.973653636207437e-05,
      "loss": 0.1281,
      "step": 26
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.0,
      "learning_rate": 3.263043563534428e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 2.33,
      "grad_norm": 1.3255101045937951,
      "learning_rate": 2.6099108277934103e-05,
      "loss": 0.241,
      "step": 28
    },
    {
      "epoch": 2.42,
      "grad_norm": 1.2875238527014208,
      "learning_rate": 2.0198277271976052e-05,
      "loss": 0.1119,
      "step": 29
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.8877844960332283,
      "learning_rate": 1.4978286427038601e-05,
      "loss": 0.0801,
      "step": 30
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.8352399168858301,
      "learning_rate": 1.0483670864493778e-05,
      "loss": 0.0476,
      "step": 31
    },
    {
      "epoch": 2.67,
      "grad_norm": 1.5306237269980234,
      "learning_rate": 6.75277705956443e-06,
      "loss": 0.1747,
      "step": 32
    },
    {
      "epoch": 2.75,
      "grad_norm": 1.4240052476126552,
      "learning_rate": 3.817435682718096e-06,
      "loss": 0.1708,
      "step": 33
    },
    {
      "epoch": 2.83,
      "grad_norm": 0.0,
      "learning_rate": 1.7026900316098215e-06,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 2.92,
      "grad_norm": 1.354110832571316,
      "learning_rate": 4.2658237049655323e-07,
      "loss": 0.1707,
      "step": 35
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.5718747557345578,
      "learning_rate": 0.0,
      "loss": 0.2786,
      "step": 36
    },
    {
      "epoch": 3.0,
      "step": 36,
      "total_flos": 0.0,
      "train_loss": 0.3035856561942233,
      "train_runtime": 624.7499,
      "train_samples_per_second": 0.461,
      "train_steps_per_second": 0.058
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}