{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12048192771084337,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004819277108433735,
      "grad_norm": 1.0873982906341553,
      "learning_rate": 0.0,
      "loss": 1.2725,
      "step": 1
    },
    {
      "epoch": 0.00963855421686747,
      "grad_norm": 0.7578734755516052,
      "learning_rate": 4e-05,
      "loss": 0.9978,
      "step": 2
    },
    {
      "epoch": 0.014457831325301205,
      "grad_norm": 0.7068339586257935,
      "learning_rate": 8e-05,
      "loss": 0.8246,
      "step": 3
    },
    {
      "epoch": 0.01927710843373494,
      "grad_norm": 0.6248342990875244,
      "learning_rate": 0.00012,
      "loss": 0.7956,
      "step": 4
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 0.2963731288909912,
      "learning_rate": 0.00016,
      "loss": 0.7756,
      "step": 5
    },
    {
      "epoch": 0.02891566265060241,
      "grad_norm": 0.226631298661232,
      "learning_rate": 0.0002,
      "loss": 0.6459,
      "step": 6
    },
    {
      "epoch": 0.033734939759036145,
      "grad_norm": 0.2879922091960907,
      "learning_rate": 0.00019,
      "loss": 0.5224,
      "step": 7
    },
    {
      "epoch": 0.03855421686746988,
      "grad_norm": 0.30339133739471436,
      "learning_rate": 0.00018,
      "loss": 0.5523,
      "step": 8
    },
    {
      "epoch": 0.043373493975903614,
      "grad_norm": 0.2749564051628113,
      "learning_rate": 0.00017,
      "loss": 0.7496,
      "step": 9
    },
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 0.20403070747852325,
      "learning_rate": 0.00016,
      "loss": 0.6514,
      "step": 10
    },
    {
      "epoch": 0.05301204819277108,
      "grad_norm": 0.2553975582122803,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.6296,
      "step": 11
    },
    {
      "epoch": 0.05783132530120482,
      "grad_norm": 0.20366790890693665,
      "learning_rate": 0.00014,
      "loss": 0.5187,
      "step": 12
    },
    {
      "epoch": 0.06265060240963856,
      "grad_norm": 0.18309777975082397,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.5334,
      "step": 13
    },
    {
      "epoch": 0.06746987951807229,
      "grad_norm": 0.17828117311000824,
      "learning_rate": 0.00012,
      "loss": 0.515,
      "step": 14
    },
    {
      "epoch": 0.07228915662650602,
      "grad_norm": 0.22142553329467773,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.6641,
      "step": 15
    },
    {
      "epoch": 0.07710843373493977,
      "grad_norm": 0.1471155434846878,
      "learning_rate": 0.0001,
      "loss": 0.4286,
      "step": 16
    },
    {
      "epoch": 0.0819277108433735,
      "grad_norm": 0.21006067097187042,
      "learning_rate": 9e-05,
      "loss": 0.5471,
      "step": 17
    },
    {
      "epoch": 0.08674698795180723,
      "grad_norm": 0.1845540702342987,
      "learning_rate": 8e-05,
      "loss": 0.5242,
      "step": 18
    },
    {
      "epoch": 0.09156626506024096,
      "grad_norm": 0.16557849943637848,
      "learning_rate": 7e-05,
      "loss": 0.585,
      "step": 19
    },
    {
      "epoch": 0.0963855421686747,
      "grad_norm": 0.24527060985565186,
      "learning_rate": 6e-05,
      "loss": 0.55,
      "step": 20
    },
    {
      "epoch": 0.10120481927710843,
      "grad_norm": 0.16817006468772888,
      "learning_rate": 5e-05,
      "loss": 0.4271,
      "step": 21
    },
    {
      "epoch": 0.10602409638554217,
      "grad_norm": 0.1981966197490692,
      "learning_rate": 4e-05,
      "loss": 0.5959,
      "step": 22
    },
    {
      "epoch": 0.1108433734939759,
      "grad_norm": 0.18087905645370483,
      "learning_rate": 3e-05,
      "loss": 0.4993,
      "step": 23
    },
    {
      "epoch": 0.11566265060240964,
      "grad_norm": 0.197529137134552,
      "learning_rate": 2e-05,
      "loss": 0.5422,
      "step": 24
    },
    {
      "epoch": 0.12048192771084337,
      "grad_norm": 0.16518113017082214,
      "learning_rate": 1e-05,
      "loss": 0.4278,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0457486116962304e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}