{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02897291032884253,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005794582065768506,
      "eval_loss": 1.7492520809173584,
      "eval_runtime": 96.1798,
      "eval_samples_per_second": 7.559,
      "eval_steps_per_second": 3.785,
      "step": 1
    },
    {
      "epoch": 0.0028972910328842532,
      "grad_norm": 4.406979560852051,
      "learning_rate": 5e-05,
      "loss": 7.0567,
      "step": 5
    },
    {
      "epoch": 0.0057945820657685065,
      "grad_norm": 4.842049598693848,
      "learning_rate": 0.0001,
      "loss": 6.3354,
      "step": 10
    },
    {
      "epoch": 0.0057945820657685065,
      "eval_loss": 1.4696853160858154,
      "eval_runtime": 100.8819,
      "eval_samples_per_second": 7.206,
      "eval_steps_per_second": 3.608,
      "step": 10
    },
    {
      "epoch": 0.008691873098652759,
      "grad_norm": 5.034236431121826,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.9785,
      "step": 15
    },
    {
      "epoch": 0.011589164131537013,
      "grad_norm": 4.192923069000244,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.48,
      "step": 20
    },
    {
      "epoch": 0.011589164131537013,
      "eval_loss": 0.9877359867095947,
      "eval_runtime": 101.3086,
      "eval_samples_per_second": 7.176,
      "eval_steps_per_second": 3.593,
      "step": 20
    },
    {
      "epoch": 0.014486455164421265,
      "grad_norm": 4.4164533615112305,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.9514,
      "step": 25
    },
    {
      "epoch": 0.017383746197305518,
      "grad_norm": 3.467801570892334,
      "learning_rate": 5e-05,
      "loss": 3.3408,
      "step": 30
    },
    {
      "epoch": 0.017383746197305518,
      "eval_loss": 0.8875389695167542,
      "eval_runtime": 101.3257,
      "eval_samples_per_second": 7.175,
      "eval_steps_per_second": 3.592,
      "step": 30
    },
    {
      "epoch": 0.020281037230189772,
      "grad_norm": 3.919318199157715,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.9499,
      "step": 35
    },
    {
      "epoch": 0.023178328263074026,
      "grad_norm": 5.339483737945557,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.6152,
      "step": 40
    },
    {
      "epoch": 0.023178328263074026,
      "eval_loss": 0.8557589054107666,
      "eval_runtime": 101.3172,
      "eval_samples_per_second": 7.175,
      "eval_steps_per_second": 3.593,
      "step": 40
    },
    {
      "epoch": 0.02607561929595828,
      "grad_norm": 4.450899124145508,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.743,
      "step": 45
    },
    {
      "epoch": 0.02897291032884253,
      "grad_norm": 4.0835089683532715,
      "learning_rate": 0.0,
      "loss": 3.4918,
      "step": 50
    },
    {
      "epoch": 0.02897291032884253,
      "eval_loss": 0.8489733934402466,
      "eval_runtime": 101.3195,
      "eval_samples_per_second": 7.175,
      "eval_steps_per_second": 3.593,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4264026791936e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}