{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.96,
  "eval_steps": 500,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.533811092376709,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.9694,
      "num_input_tokens_seen": 2097152,
      "step": 1
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.42341282963752747,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.944,
      "num_input_tokens_seen": 4194304,
      "step": 2
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.34744787216186523,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.9218,
      "num_input_tokens_seen": 6291456,
      "step": 3
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.2852979898452759,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 0.9197,
      "num_input_tokens_seen": 8388608,
      "step": 4
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.249860018491745,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.8964,
      "num_input_tokens_seen": 10485760,
      "step": 5
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.21876861155033112,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.9233,
      "num_input_tokens_seen": 12582912,
      "step": 6
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 0.20452448725700378,
      "learning_rate": 5.848888922025553e-06,
      "loss": 0.8714,
      "num_input_tokens_seen": 14680064,
      "step": 7
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.20002137124538422,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 0.9046,
      "num_input_tokens_seen": 16777216,
      "step": 8
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.191678985953331,
      "learning_rate": 0.0,
      "loss": 0.8776,
      "num_input_tokens_seen": 18874368,
      "step": 9
    },
    {
      "epoch": 0.96,
      "num_input_tokens_seen": 18874368,
      "step": 9,
      "total_flos": 8.352389743383675e+17,
      "train_loss": 0.9142353534698486,
      "train_runtime": 994.2403,
      "train_samples_per_second": 4.782,
      "train_steps_per_second": 0.009
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 9,
  "num_input_tokens_seen": 18874368,
  "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": 8.352389743383675e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}