{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012099213551119177,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00024198427102238354,
      "eval_loss": 1.701642632484436,
      "eval_runtime": 65.8495,
      "eval_samples_per_second": 26.424,
      "eval_steps_per_second": 13.212,
      "step": 1
    },
    {
      "epoch": 0.0012099213551119178,
      "grad_norm": 1.5044355392456055,
      "learning_rate": 5e-05,
      "loss": 6.4975,
      "step": 5
    },
    {
      "epoch": 0.0024198427102238356,
      "grad_norm": 1.8346918821334839,
      "learning_rate": 0.0001,
      "loss": 6.6052,
      "step": 10
    },
    {
      "epoch": 0.0024198427102238356,
      "eval_loss": 1.6462026834487915,
      "eval_runtime": 65.8084,
      "eval_samples_per_second": 26.44,
      "eval_steps_per_second": 13.22,
      "step": 10
    },
    {
      "epoch": 0.003629764065335753,
      "grad_norm": 3.3966145515441895,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.3546,
      "step": 15
    },
    {
      "epoch": 0.004839685420447671,
      "grad_norm": 3.8680999279022217,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.5683,
      "step": 20
    },
    {
      "epoch": 0.004839685420447671,
      "eval_loss": 1.5566834211349487,
      "eval_runtime": 65.9304,
      "eval_samples_per_second": 26.391,
      "eval_steps_per_second": 13.196,
      "step": 20
    },
    {
      "epoch": 0.006049606775559589,
      "grad_norm": 3.255913019180298,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.4739,
      "step": 25
    },
    {
      "epoch": 0.007259528130671506,
      "grad_norm": 3.2383882999420166,
      "learning_rate": 5e-05,
      "loss": 6.1798,
      "step": 30
    },
    {
      "epoch": 0.007259528130671506,
      "eval_loss": 1.5152812004089355,
      "eval_runtime": 65.6178,
      "eval_samples_per_second": 26.517,
      "eval_steps_per_second": 13.259,
      "step": 30
    },
    {
      "epoch": 0.008469449485783424,
      "grad_norm": 3.7061190605163574,
      "learning_rate": 3.086582838174551e-05,
      "loss": 5.9487,
      "step": 35
    },
    {
      "epoch": 0.009679370840895343,
      "grad_norm": 4.990902900695801,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 6.1513,
      "step": 40
    },
    {
      "epoch": 0.009679370840895343,
      "eval_loss": 1.4963432550430298,
      "eval_runtime": 65.6257,
      "eval_samples_per_second": 26.514,
      "eval_steps_per_second": 13.257,
      "step": 40
    },
    {
      "epoch": 0.010889292196007259,
      "grad_norm": 4.028073310852051,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 5.4428,
      "step": 45
    },
    {
      "epoch": 0.012099213551119177,
      "grad_norm": 4.228430271148682,
      "learning_rate": 0.0,
      "loss": 5.9249,
      "step": 50
    },
    {
      "epoch": 0.012099213551119177,
      "eval_loss": 1.4931994676589966,
      "eval_runtime": 65.4925,
      "eval_samples_per_second": 26.568,
      "eval_steps_per_second": 13.284,
      "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": 1910863162245120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}