{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3071895424836601,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16339869281045752,
      "grad_norm": 4.712534427642822,
      "learning_rate": 2.20959595959596e-05,
      "loss": 4.2463,
      "step": 25
    },
    {
      "epoch": 0.32679738562091504,
      "grad_norm": 2.7064566612243652,
      "learning_rate": 1.893939393939394e-05,
      "loss": 1.4818,
      "step": 50
    },
    {
      "epoch": 0.49019607843137253,
      "grad_norm": 2.3799028396606445,
      "learning_rate": 1.5782828282828283e-05,
      "loss": 0.8581,
      "step": 75
    },
    {
      "epoch": 0.6535947712418301,
      "grad_norm": 12.720088958740234,
      "learning_rate": 1.2626262626262628e-05,
      "loss": 0.6736,
      "step": 100
    },
    {
      "epoch": 0.6535947712418301,
      "eval_loss": 0.7411167621612549,
      "eval_runtime": 48.3052,
      "eval_samples_per_second": 6.335,
      "eval_steps_per_second": 0.807,
      "step": 100
    },
    {
      "epoch": 0.8169934640522876,
      "grad_norm": 1.2977323532104492,
      "learning_rate": 9.46969696969697e-06,
      "loss": 0.7944,
      "step": 125
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 1.5648150444030762,
      "learning_rate": 6.313131313131314e-06,
      "loss": 0.7894,
      "step": 150
    },
    {
      "epoch": 1.1437908496732025,
      "grad_norm": 1.2993278503417969,
      "learning_rate": 3.156565656565657e-06,
      "loss": 0.7378,
      "step": 175
    },
    {
      "epoch": 1.3071895424836601,
      "grad_norm": 1.6554691791534424,
      "learning_rate": 0.0,
      "loss": 0.7763,
      "step": 200
    },
    {
      "epoch": 1.3071895424836601,
      "eval_loss": 0.7024445533752441,
      "eval_runtime": 48.623,
      "eval_samples_per_second": 6.293,
      "eval_steps_per_second": 0.802,
      "step": 200
    }
  ],
  "logging_steps": 25,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 901115687731200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}