{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18248175182481752,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036496350364963502,
      "eval_loss": 2.616699695587158,
      "eval_runtime": 6.2577,
      "eval_samples_per_second": 18.537,
      "eval_steps_per_second": 9.269,
      "step": 1
    },
    {
      "epoch": 0.01824817518248175,
      "grad_norm": 1.6869487762451172,
      "learning_rate": 5e-05,
      "loss": 2.5527,
      "step": 5
    },
    {
      "epoch": 0.0364963503649635,
      "grad_norm": 1.839852213859558,
      "learning_rate": 0.0001,
      "loss": 2.3494,
      "step": 10
    },
    {
      "epoch": 0.0364963503649635,
      "eval_loss": 1.9993141889572144,
      "eval_runtime": 6.2302,
      "eval_samples_per_second": 18.619,
      "eval_steps_per_second": 9.31,
      "step": 10
    },
    {
      "epoch": 0.05474452554744526,
      "grad_norm": 2.02532696723938,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7325,
      "step": 15
    },
    {
      "epoch": 0.072992700729927,
      "grad_norm": 2.6259419918060303,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1345,
      "step": 20
    },
    {
      "epoch": 0.072992700729927,
      "eval_loss": 0.8235381841659546,
      "eval_runtime": 6.2741,
      "eval_samples_per_second": 18.489,
      "eval_steps_per_second": 9.244,
      "step": 20
    },
    {
      "epoch": 0.09124087591240876,
      "grad_norm": 2.6322834491729736,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6636,
      "step": 25
    },
    {
      "epoch": 0.10948905109489052,
      "grad_norm": 2.5473804473876953,
      "learning_rate": 5e-05,
      "loss": 0.3124,
      "step": 30
    },
    {
      "epoch": 0.10948905109489052,
      "eval_loss": 0.1789940446615219,
      "eval_runtime": 6.3174,
      "eval_samples_per_second": 18.362,
      "eval_steps_per_second": 9.181,
      "step": 30
    },
    {
      "epoch": 0.12773722627737227,
      "grad_norm": 2.1772966384887695,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1365,
      "step": 35
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 1.1791236400604248,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0655,
      "step": 40
    },
    {
      "epoch": 0.145985401459854,
      "eval_loss": 0.045773398131132126,
      "eval_runtime": 6.3415,
      "eval_samples_per_second": 18.292,
      "eval_steps_per_second": 9.146,
      "step": 40
    },
    {
      "epoch": 0.16423357664233576,
      "grad_norm": 1.3011243343353271,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0399,
      "step": 45
    },
    {
      "epoch": 0.18248175182481752,
      "grad_norm": 0.8173432946205139,
      "learning_rate": 0.0,
      "loss": 0.0427,
      "step": 50
    },
    {
      "epoch": 0.18248175182481752,
      "eval_loss": 0.03340202569961548,
      "eval_runtime": 6.2937,
      "eval_samples_per_second": 18.431,
      "eval_steps_per_second": 9.216,
      "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": 2500486653542400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}