{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9905660377358491,
  "eval_steps": 10,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.9930094929529506e-05,
      "loss": 1.1464,
      "step": 1
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.827184371610511e-05,
      "loss": 1.1371,
      "step": 5
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.332629679574566e-05,
      "loss": 1.1426,
      "step": 10
    },
    {
      "epoch": 0.24,
      "eval_loss": 1.1187583208084106,
      "eval_runtime": 24.53,
      "eval_samples_per_second": 5.259,
      "eval_steps_per_second": 1.753,
      "step": 10
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.5847093477938956e-05,
      "loss": 1.1312,
      "step": 15
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.686825233966061e-05,
      "loss": 1.1231,
      "step": 20
    },
    {
      "epoch": 0.47,
      "eval_loss": 1.105903148651123,
      "eval_runtime": 24.5343,
      "eval_samples_per_second": 5.258,
      "eval_steps_per_second": 1.753,
      "step": 20
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.7631120639727393e-05,
      "loss": 1.1075,
      "step": 25
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.412754953531663e-06,
      "loss": 1.1179,
      "step": 30
    },
    {
      "epoch": 0.71,
      "eval_loss": 1.0980486869812012,
      "eval_runtime": 24.5445,
      "eval_samples_per_second": 5.256,
      "eval_steps_per_second": 1.752,
      "step": 30
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 1.1059,
      "step": 35
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.7922934437178695e-07,
      "loss": 1.0996,
      "step": 40
    },
    {
      "epoch": 0.94,
      "eval_loss": 1.0960252285003662,
      "eval_runtime": 24.5306,
      "eval_samples_per_second": 5.259,
      "eval_steps_per_second": 1.753,
      "step": 40
    },
    {
      "epoch": 0.99,
      "step": 42,
      "total_flos": 6.447644673468006e+16,
      "train_loss": 1.1202537786392939,
      "train_runtime": 3231.7229,
      "train_samples_per_second": 1.573,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 5,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "total_flos": 6.447644673468006e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}