{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02663115845539281,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002663115845539281,
      "grad_norm": 1.3811781406402588,
      "learning_rate": 2e-05,
      "loss": 2.6938,
      "step": 1
    },
    {
      "epoch": 0.005326231691078562,
      "grad_norm": 0.8367151021957397,
      "learning_rate": 4e-05,
      "loss": 2.7719,
      "step": 2
    },
    {
      "epoch": 0.007989347536617843,
      "grad_norm": 0.8151127099990845,
      "learning_rate": 6e-05,
      "loss": 2.3049,
      "step": 3
    },
    {
      "epoch": 0.007989347536617843,
      "eval_loss": 2.1599280834198,
      "eval_runtime": 6.0673,
      "eval_samples_per_second": 26.206,
      "eval_steps_per_second": 13.185,
      "step": 3
    },
    {
      "epoch": 0.010652463382157125,
      "grad_norm": 0.8771814107894897,
      "learning_rate": 8e-05,
      "loss": 2.2616,
      "step": 4
    },
    {
      "epoch": 0.013315579227696404,
      "grad_norm": 1.110089898109436,
      "learning_rate": 0.0001,
      "loss": 2.2077,
      "step": 5
    },
    {
      "epoch": 0.015978695073235686,
      "grad_norm": 0.9266451001167297,
      "learning_rate": 0.00012,
      "loss": 2.286,
      "step": 6
    },
    {
      "epoch": 0.015978695073235686,
      "eval_loss": 2.1395297050476074,
      "eval_runtime": 7.9101,
      "eval_samples_per_second": 20.101,
      "eval_steps_per_second": 10.114,
      "step": 6
    },
    {
      "epoch": 0.018641810918774968,
      "grad_norm": 1.0165808200836182,
      "learning_rate": 0.00014,
      "loss": 2.7931,
      "step": 7
    },
    {
      "epoch": 0.02130492676431425,
      "grad_norm": 0.8093817234039307,
      "learning_rate": 0.00016,
      "loss": 2.3931,
      "step": 8
    },
    {
      "epoch": 0.023968042609853527,
      "grad_norm": 0.9739234447479248,
      "learning_rate": 0.00018,
      "loss": 1.8198,
      "step": 9
    },
    {
      "epoch": 0.023968042609853527,
      "eval_loss": 2.044184446334839,
      "eval_runtime": 7.9136,
      "eval_samples_per_second": 20.092,
      "eval_steps_per_second": 10.109,
      "step": 9
    },
    {
      "epoch": 0.02663115845539281,
      "grad_norm": 0.8706778883934021,
      "learning_rate": 0.0002,
      "loss": 1.5596,
      "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": 498794357587968.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}