{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010900705750821046,
  "eval_steps": 13,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002795052756620781,
      "eval_loss": 4.3518385887146,
      "eval_runtime": 74.1893,
      "eval_samples_per_second": 20.313,
      "eval_steps_per_second": 10.163,
      "step": 1
    },
    {
      "epoch": 0.0027950527566207813,
      "grad_norm": 4.335495471954346,
      "learning_rate": 0.00019396926207859084,
      "loss": 3.6101,
      "step": 10
    },
    {
      "epoch": 0.003633568583607016,
      "eval_loss": 1.1593981981277466,
      "eval_runtime": 73.1648,
      "eval_samples_per_second": 20.597,
      "eval_steps_per_second": 10.306,
      "step": 13
    },
    {
      "epoch": 0.005590105513241563,
      "grad_norm": 2.148371696472168,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1865,
      "step": 20
    },
    {
      "epoch": 0.007267137167214032,
      "eval_loss": 0.6191197037696838,
      "eval_runtime": 73.1399,
      "eval_samples_per_second": 20.604,
      "eval_steps_per_second": 10.309,
      "step": 26
    },
    {
      "epoch": 0.008385158269862344,
      "grad_norm": 2.1668341159820557,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.7354,
      "step": 30
    },
    {
      "epoch": 0.010900705750821046,
      "eval_loss": 0.48577263951301575,
      "eval_runtime": 73.1489,
      "eval_samples_per_second": 20.602,
      "eval_steps_per_second": 10.308,
      "step": 39
    }
  ],
  "logging_steps": 10,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.234820118085632e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}