{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004524375070693361,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015081250235644535,
      "eval_loss": 1.5639430284500122,
      "eval_runtime": 167.8592,
      "eval_samples_per_second": 16.633,
      "eval_steps_per_second": 8.316,
      "step": 1
    },
    {
      "epoch": 0.00045243750706933604,
      "grad_norm": 0.7134446501731873,
      "learning_rate": 6e-05,
      "loss": 1.4625,
      "step": 3
    },
    {
      "epoch": 0.0009048750141386721,
      "grad_norm": 0.8166648149490356,
      "learning_rate": 0.00012,
      "loss": 1.4642,
      "step": 6
    },
    {
      "epoch": 0.0012065000188515628,
      "eval_loss": 1.3007512092590332,
      "eval_runtime": 166.0066,
      "eval_samples_per_second": 16.819,
      "eval_steps_per_second": 8.409,
      "step": 8
    },
    {
      "epoch": 0.0013573125212080082,
      "grad_norm": 0.5553706884384155,
      "learning_rate": 0.00018,
      "loss": 1.4434,
      "step": 9
    },
    {
      "epoch": 0.0018097500282773442,
      "grad_norm": 0.6511344909667969,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.2293,
      "step": 12
    },
    {
      "epoch": 0.0022621875353466803,
      "grad_norm": 0.5849931240081787,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.2202,
      "step": 15
    },
    {
      "epoch": 0.0024130000377031256,
      "eval_loss": 1.19452965259552,
      "eval_runtime": 166.408,
      "eval_samples_per_second": 16.778,
      "eval_steps_per_second": 8.389,
      "step": 16
    },
    {
      "epoch": 0.0027146250424160165,
      "grad_norm": 0.5092917680740356,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2651,
      "step": 18
    },
    {
      "epoch": 0.003167062549485352,
      "grad_norm": 0.45209425687789917,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.0584,
      "step": 21
    },
    {
      "epoch": 0.0036195000565546883,
      "grad_norm": 0.6036216616630554,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.1131,
      "step": 24
    },
    {
      "epoch": 0.0036195000565546883,
      "eval_loss": 1.1596405506134033,
      "eval_runtime": 166.0649,
      "eval_samples_per_second": 16.813,
      "eval_steps_per_second": 8.406,
      "step": 24
    },
    {
      "epoch": 0.0040719375636240245,
      "grad_norm": 0.45558610558509827,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.0708,
      "step": 27
    },
    {
      "epoch": 0.004524375070693361,
      "grad_norm": 0.5339828133583069,
      "learning_rate": 0.0,
      "loss": 1.0913,
      "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": 1.032959557632e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}