{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010314595152140279,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010314595152140279,
      "grad_norm": 1.1879026889801025,
      "learning_rate": 2e-05,
      "loss": 9.1156,
      "step": 1
    },
    {
      "epoch": 0.0010314595152140279,
      "eval_loss": 2.375784158706665,
      "eval_runtime": 26.4578,
      "eval_samples_per_second": 15.459,
      "eval_steps_per_second": 7.748,
      "step": 1
    },
    {
      "epoch": 0.0020629190304280558,
      "grad_norm": 1.1289355754852295,
      "learning_rate": 4e-05,
      "loss": 8.4767,
      "step": 2
    },
    {
      "epoch": 0.0030943785456420837,
      "grad_norm": 1.3906314373016357,
      "learning_rate": 6e-05,
      "loss": 9.347,
      "step": 3
    },
    {
      "epoch": 0.0030943785456420837,
      "eval_loss": 2.3746674060821533,
      "eval_runtime": 26.5729,
      "eval_samples_per_second": 15.392,
      "eval_steps_per_second": 7.715,
      "step": 3
    },
    {
      "epoch": 0.0041258380608561115,
      "grad_norm": 1.349333643913269,
      "learning_rate": 8e-05,
      "loss": 10.0079,
      "step": 4
    },
    {
      "epoch": 0.005157297576070139,
      "grad_norm": 1.281437873840332,
      "learning_rate": 0.0001,
      "loss": 8.5314,
      "step": 5
    },
    {
      "epoch": 0.006188757091284167,
      "grad_norm": 1.709563136100769,
      "learning_rate": 0.00012,
      "loss": 9.3063,
      "step": 6
    },
    {
      "epoch": 0.006188757091284167,
      "eval_loss": 2.3554344177246094,
      "eval_runtime": 26.7838,
      "eval_samples_per_second": 15.27,
      "eval_steps_per_second": 7.654,
      "step": 6
    },
    {
      "epoch": 0.007220216606498195,
      "grad_norm": 2.2861104011535645,
      "learning_rate": 0.00014,
      "loss": 9.3737,
      "step": 7
    },
    {
      "epoch": 0.008251676121712223,
      "grad_norm": 1.7694536447525024,
      "learning_rate": 0.00016,
      "loss": 8.6882,
      "step": 8
    },
    {
      "epoch": 0.009283135636926251,
      "grad_norm": 2.2282848358154297,
      "learning_rate": 0.00018,
      "loss": 9.6363,
      "step": 9
    },
    {
      "epoch": 0.009283135636926251,
      "eval_loss": 2.259730339050293,
      "eval_runtime": 26.7711,
      "eval_samples_per_second": 15.278,
      "eval_steps_per_second": 7.658,
      "step": 9
    },
    {
      "epoch": 0.010314595152140279,
      "grad_norm": 2.077700614929199,
      "learning_rate": 0.0002,
      "loss": 9.2005,
      "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": 3652169918054400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}