{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9991993594875901,
  "eval_steps": 4,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.051240992794235385,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.2591,
      "step": 4
    },
    {
      "epoch": 0.10248198558847077,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.2358,
      "step": 8
    },
    {
      "epoch": 0.15372297838270615,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.2336,
      "step": 12
    },
    {
      "epoch": 0.20496397117694154,
      "grad_norm": 0.3318765163421631,
      "learning_rate": 0.0011547005383792518,
      "loss": 1.2052,
      "step": 16
    },
    {
      "epoch": 0.2562049639711769,
      "grad_norm": 0.871834933757782,
      "learning_rate": 0.0008164965809277262,
      "loss": 1.1247,
      "step": 20
    },
    {
      "epoch": 0.3074459567654123,
      "grad_norm": 0.44025564193725586,
      "learning_rate": 0.0006324555320336759,
      "loss": 0.9757,
      "step": 24
    },
    {
      "epoch": 0.3586869495596477,
      "grad_norm": 0.3040187656879425,
      "learning_rate": 0.0005345224838248488,
      "loss": 0.9053,
      "step": 28
    },
    {
      "epoch": 0.4099279423538831,
      "grad_norm": 0.2234366089105606,
      "learning_rate": 0.00047140452079103175,
      "loss": 0.8848,
      "step": 32
    },
    {
      "epoch": 0.4611689351481185,
      "grad_norm": 0.23592019081115723,
      "learning_rate": 0.00042640143271122083,
      "loss": 0.8373,
      "step": 36
    },
    {
      "epoch": 0.5124099279423538,
      "grad_norm": 0.2808322310447693,
      "learning_rate": 0.0003922322702763681,
      "loss": 0.8558,
      "step": 40
    },
    {
      "epoch": 0.5636509207365893,
      "grad_norm": 0.22603166103363037,
      "learning_rate": 0.00036514837167011074,
      "loss": 0.8877,
      "step": 44
    },
    {
      "epoch": 0.6148919135308246,
      "grad_norm": 0.2617782950401306,
      "learning_rate": 0.00034299717028501764,
      "loss": 0.8343,
      "step": 48
    },
    {
      "epoch": 0.6661329063250601,
      "grad_norm": 0.24344013631343842,
      "learning_rate": 0.0003244428422615251,
      "loss": 0.8267,
      "step": 52
    },
    {
      "epoch": 0.7173738991192954,
      "grad_norm": 0.31763675808906555,
      "learning_rate": 0.00030860669992418383,
      "loss": 0.8111,
      "step": 56
    },
    {
      "epoch": 0.7686148919135308,
      "grad_norm": 0.33552709221839905,
      "learning_rate": 0.0002948839123097943,
      "loss": 0.826,
      "step": 60
    },
    {
      "epoch": 0.8198558847077662,
      "grad_norm": 0.21605852246284485,
      "learning_rate": 0.000282842712474619,
      "loss": 0.8314,
      "step": 64
    },
    {
      "epoch": 0.8710968775020016,
      "grad_norm": 0.2202538549900055,
      "learning_rate": 0.0002721655269759087,
      "loss": 0.829,
      "step": 68
    },
    {
      "epoch": 0.922337870296237,
      "grad_norm": 0.21023687720298767,
      "learning_rate": 0.0002626128657194451,
      "loss": 0.813,
      "step": 72
    },
    {
      "epoch": 0.9735788630904724,
      "grad_norm": 0.22085361182689667,
      "learning_rate": 0.000254000254000381,
      "loss": 0.8169,
      "step": 76
    },
    {
      "epoch": 0.9991993594875901,
      "step": 78,
      "total_flos": 7.922041751265608e+17,
      "train_loss": 0.944701231442965,
      "train_runtime": 774.0926,
      "train_samples_per_second": 12.905,
      "train_steps_per_second": 0.101
    }
  ],
  "logging_steps": 4,
  "max_steps": 78,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.922041751265608e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}