{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011389521640091117,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011389521640091116,
      "grad_norm": 0.705397367477417,
      "learning_rate": 2e-05,
      "loss": 44.4768,
      "step": 1
    },
    {
      "epoch": 0.0011389521640091116,
      "eval_loss": 11.115654945373535,
      "eval_runtime": 2.1259,
      "eval_samples_per_second": 174.043,
      "eval_steps_per_second": 87.022,
      "step": 1
    },
    {
      "epoch": 0.002277904328018223,
      "grad_norm": 0.7453666925430298,
      "learning_rate": 4e-05,
      "loss": 44.4532,
      "step": 2
    },
    {
      "epoch": 0.003416856492027335,
      "grad_norm": 0.7162854671478271,
      "learning_rate": 6e-05,
      "loss": 44.4722,
      "step": 3
    },
    {
      "epoch": 0.003416856492027335,
      "eval_loss": 11.115540504455566,
      "eval_runtime": 1.1988,
      "eval_samples_per_second": 308.646,
      "eval_steps_per_second": 154.323,
      "step": 3
    },
    {
      "epoch": 0.004555808656036446,
      "grad_norm": 0.7419840097427368,
      "learning_rate": 8e-05,
      "loss": 44.4458,
      "step": 4
    },
    {
      "epoch": 0.0056947608200455585,
      "grad_norm": 0.9602454900741577,
      "learning_rate": 0.0001,
      "loss": 44.479,
      "step": 5
    },
    {
      "epoch": 0.00683371298405467,
      "grad_norm": 0.700503945350647,
      "learning_rate": 0.00012,
      "loss": 44.4369,
      "step": 6
    },
    {
      "epoch": 0.00683371298405467,
      "eval_loss": 11.114104270935059,
      "eval_runtime": 1.2323,
      "eval_samples_per_second": 300.248,
      "eval_steps_per_second": 150.124,
      "step": 6
    },
    {
      "epoch": 0.007972665148063782,
      "grad_norm": 0.8146664500236511,
      "learning_rate": 0.00014,
      "loss": 44.4921,
      "step": 7
    },
    {
      "epoch": 0.009111617312072893,
      "grad_norm": 0.7042016983032227,
      "learning_rate": 0.00016,
      "loss": 44.4491,
      "step": 8
    },
    {
      "epoch": 0.010250569476082005,
      "grad_norm": 0.5749262571334839,
      "learning_rate": 0.00018,
      "loss": 44.4073,
      "step": 9
    },
    {
      "epoch": 0.010250569476082005,
      "eval_loss": 11.11139965057373,
      "eval_runtime": 1.2008,
      "eval_samples_per_second": 308.12,
      "eval_steps_per_second": 154.06,
      "step": 9
    },
    {
      "epoch": 0.011389521640091117,
      "grad_norm": 0.7122977375984192,
      "learning_rate": 0.0002,
      "loss": 44.4508,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 168784035840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}