{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005682439077696427,
  "eval_steps": 13,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004371106982843405,
      "grad_norm": 1.0720200538635254,
      "learning_rate": 2e-05,
      "loss": 12.2248,
      "step": 1
    },
    {
      "epoch": 0.0004371106982843405,
      "eval_loss": 3.090006113052368,
      "eval_runtime": 63.2698,
      "eval_samples_per_second": 15.236,
      "eval_steps_per_second": 7.618,
      "step": 1
    },
    {
      "epoch": 0.000874221396568681,
      "grad_norm": 1.0658981800079346,
      "learning_rate": 4e-05,
      "loss": 12.6966,
      "step": 2
    },
    {
      "epoch": 0.0013113320948530216,
      "grad_norm": 1.0887017250061035,
      "learning_rate": 6e-05,
      "loss": 11.9003,
      "step": 3
    },
    {
      "epoch": 0.001748442793137362,
      "grad_norm": 1.080330729484558,
      "learning_rate": 8e-05,
      "loss": 12.5687,
      "step": 4
    },
    {
      "epoch": 0.0021855534914217026,
      "grad_norm": 1.2502211332321167,
      "learning_rate": 0.0001,
      "loss": 13.564,
      "step": 5
    },
    {
      "epoch": 0.0026226641897060432,
      "grad_norm": 1.2538820505142212,
      "learning_rate": 0.00012,
      "loss": 11.9462,
      "step": 6
    },
    {
      "epoch": 0.0030597748879903834,
      "grad_norm": 1.472439169883728,
      "learning_rate": 0.00014,
      "loss": 11.4779,
      "step": 7
    },
    {
      "epoch": 0.003496885586274724,
      "grad_norm": 1.660061001777649,
      "learning_rate": 0.00016,
      "loss": 11.2724,
      "step": 8
    },
    {
      "epoch": 0.003933996284559064,
      "grad_norm": 1.9470425844192505,
      "learning_rate": 0.00018,
      "loss": 12.1637,
      "step": 9
    },
    {
      "epoch": 0.004371106982843405,
      "grad_norm": 2.017232656478882,
      "learning_rate": 0.0002,
      "loss": 11.3892,
      "step": 10
    },
    {
      "epoch": 0.004808217681127745,
      "grad_norm": 2.3584163188934326,
      "learning_rate": 0.0001996917333733128,
      "loss": 11.9319,
      "step": 11
    },
    {
      "epoch": 0.0052453283794120864,
      "grad_norm": 2.078613519668579,
      "learning_rate": 0.00019876883405951377,
      "loss": 10.9623,
      "step": 12
    },
    {
      "epoch": 0.005682439077696427,
      "grad_norm": 2.032031774520874,
      "learning_rate": 0.00019723699203976766,
      "loss": 9.7538,
      "step": 13
    },
    {
      "epoch": 0.005682439077696427,
      "eval_loss": 2.5488393306732178,
      "eval_runtime": 63.2629,
      "eval_samples_per_second": 15.238,
      "eval_steps_per_second": 7.619,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3745015047241728.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}