{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.024390243902439,
  "eval_steps": 5,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04878048780487805,
      "eval_loss": 2.5376439094543457,
      "eval_runtime": 1.4281,
      "eval_samples_per_second": 6.302,
      "eval_steps_per_second": 3.501,
      "step": 1
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 3.1540420055389404,
      "learning_rate": 6e-05,
      "loss": 2.5493,
      "step": 3
    },
    {
      "epoch": 0.24390243902439024,
      "eval_loss": 2.1000916957855225,
      "eval_runtime": 0.8941,
      "eval_samples_per_second": 10.066,
      "eval_steps_per_second": 5.592,
      "step": 5
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 2.584702491760254,
      "learning_rate": 0.00012,
      "loss": 2.4298,
      "step": 6
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 2.2489476203918457,
      "learning_rate": 0.00018,
      "loss": 1.7872,
      "step": 9
    },
    {
      "epoch": 0.4878048780487805,
      "eval_loss": 1.3452816009521484,
      "eval_runtime": 0.8983,
      "eval_samples_per_second": 10.019,
      "eval_steps_per_second": 5.566,
      "step": 10
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 2.2389755249023438,
      "learning_rate": 0.00018412535328311814,
      "loss": 1.4023,
      "step": 12
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 1.7021565437316895,
      "learning_rate": 0.00011423148382732853,
      "loss": 1.212,
      "step": 15
    },
    {
      "epoch": 0.7317073170731707,
      "eval_loss": 1.0455703735351562,
      "eval_runtime": 1.8834,
      "eval_samples_per_second": 4.779,
      "eval_steps_per_second": 2.655,
      "step": 15
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 1.394986867904663,
      "learning_rate": 3.45139266054715e-05,
      "loss": 1.1363,
      "step": 18
    },
    {
      "epoch": 0.975609756097561,
      "eval_loss": 0.9808509349822998,
      "eval_runtime": 1.8786,
      "eval_samples_per_second": 4.791,
      "eval_steps_per_second": 2.662,
      "step": 20
    },
    {
      "epoch": 1.024390243902439,
      "grad_norm": 1.889438509941101,
      "learning_rate": 0.0,
      "loss": 1.3178,
      "step": 21
    }
  ],
  "logging_steps": 3,
  "max_steps": 21,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7789820705243136.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}