{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988649262202043,
  "eval_steps": 6,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05448354143019296,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.062,
      "step": 6
    },
    {
      "epoch": 0.10896708286038592,
      "grad_norm": 0.2376125305891037,
      "learning_rate": 0.001,
      "loss": 1.0224,
      "step": 12
    },
    {
      "epoch": 0.16345062429057888,
      "grad_norm": 0.30375346541404724,
      "learning_rate": 0.0016329931618554523,
      "loss": 1.009,
      "step": 18
    },
    {
      "epoch": 0.21793416572077184,
      "grad_norm": 0.2895285189151764,
      "learning_rate": 0.0009428090415820635,
      "loss": 0.8092,
      "step": 24
    },
    {
      "epoch": 0.2724177071509648,
      "grad_norm": 0.22418786585330963,
      "learning_rate": 0.0007559289460184544,
      "loss": 0.8055,
      "step": 30
    },
    {
      "epoch": 0.32690124858115777,
      "grad_norm": 0.21890012919902802,
      "learning_rate": 0.0006324555320336759,
      "loss": 0.7342,
      "step": 36
    },
    {
      "epoch": 0.3813847900113507,
      "grad_norm": 0.20965541899204254,
      "learning_rate": 0.0005547001962252292,
      "loss": 0.7073,
      "step": 42
    },
    {
      "epoch": 0.4358683314415437,
      "grad_norm": 0.23984524607658386,
      "learning_rate": 0.0005,
      "loss": 0.6812,
      "step": 48
    },
    {
      "epoch": 0.49035187287173665,
      "grad_norm": 0.2955872416496277,
      "learning_rate": 0.0004588314677411235,
      "loss": 0.699,
      "step": 54
    },
    {
      "epoch": 0.5448354143019296,
      "grad_norm": 0.1915532946586609,
      "learning_rate": 0.00042640143271122083,
      "loss": 0.6867,
      "step": 60
    },
    {
      "epoch": 0.5993189557321226,
      "grad_norm": 0.19135332107543945,
      "learning_rate": 0.0004,
      "loss": 0.6576,
      "step": 66
    },
    {
      "epoch": 0.6538024971623155,
      "grad_norm": 0.21214482188224792,
      "learning_rate": 0.0003779644730092272,
      "loss": 0.6421,
      "step": 72
    },
    {
      "epoch": 0.7082860385925085,
      "grad_norm": 0.1696617305278778,
      "learning_rate": 0.00035921060405354985,
      "loss": 0.6718,
      "step": 78
    },
    {
      "epoch": 0.7627695800227015,
      "grad_norm": 0.18742182850837708,
      "learning_rate": 0.00034299717028501764,
      "loss": 0.6636,
      "step": 84
    },
    {
      "epoch": 0.8172531214528944,
      "grad_norm": 0.19666869938373566,
      "learning_rate": 0.0003287979746107146,
      "loss": 0.6558,
      "step": 90
    },
    {
      "epoch": 0.8717366628830874,
      "grad_norm": 0.1772751361131668,
      "learning_rate": 0.00031622776601683794,
      "loss": 0.6604,
      "step": 96
    },
    {
      "epoch": 0.9262202043132803,
      "grad_norm": 0.23768457770347595,
      "learning_rate": 0.00030499714066520935,
      "loss": 0.6501,
      "step": 102
    },
    {
      "epoch": 0.9807037457434733,
      "grad_norm": 0.17372557520866394,
      "learning_rate": 0.0002948839123097943,
      "loss": 0.6645,
      "step": 108
    },
    {
      "epoch": 0.9988649262202043,
      "step": 110,
      "total_flos": 1.1172110162041242e+18,
      "train_loss": 0.7473254984075373,
      "train_runtime": 984.6579,
      "train_samples_per_second": 14.314,
      "train_steps_per_second": 0.112
    }
  ],
  "logging_steps": 6,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1172110162041242e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}