{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00921942224953903,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030731407498463427,
      "eval_loss": 1.955762505531311,
      "eval_runtime": 80.8804,
      "eval_samples_per_second": 16.951,
      "eval_steps_per_second": 8.482,
      "step": 1
    },
    {
      "epoch": 0.0009219422249539029,
      "grad_norm": 6.676326751708984,
      "learning_rate": 6e-05,
      "loss": 1.965,
      "step": 3
    },
    {
      "epoch": 0.0018438844499078057,
      "grad_norm": 4.675253868103027,
      "learning_rate": 0.00012,
      "loss": 1.4344,
      "step": 6
    },
    {
      "epoch": 0.002458512599877074,
      "eval_loss": 0.9421961307525635,
      "eval_runtime": 79.293,
      "eval_samples_per_second": 17.29,
      "eval_steps_per_second": 8.651,
      "step": 8
    },
    {
      "epoch": 0.0027658266748617085,
      "grad_norm": 5.542921543121338,
      "learning_rate": 0.00018,
      "loss": 1.0874,
      "step": 9
    },
    {
      "epoch": 0.0036877688998156115,
      "grad_norm": 4.1071953773498535,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.7878,
      "step": 12
    },
    {
      "epoch": 0.004609711124769515,
      "grad_norm": 2.3877036571502686,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.5896,
      "step": 15
    },
    {
      "epoch": 0.004917025199754148,
      "eval_loss": 0.7264559864997864,
      "eval_runtime": 79.3607,
      "eval_samples_per_second": 17.276,
      "eval_steps_per_second": 8.644,
      "step": 16
    },
    {
      "epoch": 0.005531653349723417,
      "grad_norm": 3.1243112087249756,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.668,
      "step": 18
    },
    {
      "epoch": 0.00645359557467732,
      "grad_norm": 3.3473269939422607,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.7655,
      "step": 21
    },
    {
      "epoch": 0.007375537799631223,
      "grad_norm": 2.5187761783599854,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.7009,
      "step": 24
    },
    {
      "epoch": 0.007375537799631223,
      "eval_loss": 0.6398467421531677,
      "eval_runtime": 79.2879,
      "eval_samples_per_second": 17.291,
      "eval_steps_per_second": 8.652,
      "step": 24
    },
    {
      "epoch": 0.008297480024585127,
      "grad_norm": 2.4546871185302734,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.5937,
      "step": 27
    },
    {
      "epoch": 0.00921942224953903,
      "grad_norm": 2.4599387645721436,
      "learning_rate": 0.0,
      "loss": 0.5804,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}