{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03422899195618689,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006845798391237378,
      "eval_loss": 0.8494592308998108,
      "eval_runtime": 50.2846,
      "eval_samples_per_second": 12.23,
      "eval_steps_per_second": 6.125,
      "step": 1
    },
    {
      "epoch": 0.003422899195618689,
      "grad_norm": 0.6318883299827576,
      "learning_rate": 5e-05,
      "loss": 0.7891,
      "step": 5
    },
    {
      "epoch": 0.006845798391237378,
      "grad_norm": 0.6044836044311523,
      "learning_rate": 0.0001,
      "loss": 0.6592,
      "step": 10
    },
    {
      "epoch": 0.006845798391237378,
      "eval_loss": 0.7864668965339661,
      "eval_runtime": 50.5621,
      "eval_samples_per_second": 12.163,
      "eval_steps_per_second": 6.092,
      "step": 10
    },
    {
      "epoch": 0.010268697586856067,
      "grad_norm": 0.6784713268280029,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.6191,
      "step": 15
    },
    {
      "epoch": 0.013691596782474755,
      "grad_norm": 0.6248471736907959,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5597,
      "step": 20
    },
    {
      "epoch": 0.013691596782474755,
      "eval_loss": 0.652756929397583,
      "eval_runtime": 50.6611,
      "eval_samples_per_second": 12.139,
      "eval_steps_per_second": 6.08,
      "step": 20
    },
    {
      "epoch": 0.017114495978093443,
      "grad_norm": 0.559581995010376,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.601,
      "step": 25
    },
    {
      "epoch": 0.020537395173712135,
      "grad_norm": 0.9632827639579773,
      "learning_rate": 5e-05,
      "loss": 0.609,
      "step": 30
    },
    {
      "epoch": 0.020537395173712135,
      "eval_loss": 0.622657060623169,
      "eval_runtime": 50.7462,
      "eval_samples_per_second": 12.119,
      "eval_steps_per_second": 6.069,
      "step": 30
    },
    {
      "epoch": 0.023960294369330823,
      "grad_norm": 0.5321747660636902,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5539,
      "step": 35
    },
    {
      "epoch": 0.02738319356494951,
      "grad_norm": 0.49816638231277466,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5579,
      "step": 40
    },
    {
      "epoch": 0.02738319356494951,
      "eval_loss": 0.6132375597953796,
      "eval_runtime": 50.8294,
      "eval_samples_per_second": 12.099,
      "eval_steps_per_second": 6.059,
      "step": 40
    },
    {
      "epoch": 0.030806092760568202,
      "grad_norm": 0.6280885934829712,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.5663,
      "step": 45
    },
    {
      "epoch": 0.03422899195618689,
      "grad_norm": 0.6226765513420105,
      "learning_rate": 0.0,
      "loss": 0.4916,
      "step": 50
    },
    {
      "epoch": 0.03422899195618689,
      "eval_loss": 0.6118356585502625,
      "eval_runtime": 50.4851,
      "eval_samples_per_second": 12.182,
      "eval_steps_per_second": 6.101,
      "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": 1.1929689400541184e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}