{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03007518796992481,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0030075187969924814,
      "grad_norm": 1.391583800315857,
      "learning_rate": 2e-05,
      "loss": 2.4222,
      "step": 1
    },
    {
      "epoch": 0.0030075187969924814,
      "eval_loss": 2.4541714191436768,
      "eval_runtime": 6.8891,
      "eval_samples_per_second": 20.322,
      "eval_steps_per_second": 10.161,
      "step": 1
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 1.2627246379852295,
      "learning_rate": 4e-05,
      "loss": 2.4778,
      "step": 2
    },
    {
      "epoch": 0.009022556390977444,
      "grad_norm": 1.2318059206008911,
      "learning_rate": 6e-05,
      "loss": 1.9251,
      "step": 3
    },
    {
      "epoch": 0.009022556390977444,
      "eval_loss": 2.4492862224578857,
      "eval_runtime": 6.8269,
      "eval_samples_per_second": 20.507,
      "eval_steps_per_second": 10.254,
      "step": 3
    },
    {
      "epoch": 0.012030075187969926,
      "grad_norm": 0.9969855546951294,
      "learning_rate": 8e-05,
      "loss": 2.3824,
      "step": 4
    },
    {
      "epoch": 0.015037593984962405,
      "grad_norm": 1.173496127128601,
      "learning_rate": 0.0001,
      "loss": 1.9881,
      "step": 5
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 1.4690003395080566,
      "learning_rate": 0.00012,
      "loss": 2.3905,
      "step": 6
    },
    {
      "epoch": 0.01804511278195489,
      "eval_loss": 2.375659942626953,
      "eval_runtime": 6.9643,
      "eval_samples_per_second": 20.102,
      "eval_steps_per_second": 10.051,
      "step": 6
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 1.2729591131210327,
      "learning_rate": 0.00014,
      "loss": 2.1328,
      "step": 7
    },
    {
      "epoch": 0.02406015037593985,
      "grad_norm": 1.3297039270401,
      "learning_rate": 0.00016,
      "loss": 2.0779,
      "step": 8
    },
    {
      "epoch": 0.02706766917293233,
      "grad_norm": 1.8062524795532227,
      "learning_rate": 0.00018,
      "loss": 2.4263,
      "step": 9
    },
    {
      "epoch": 0.02706766917293233,
      "eval_loss": 2.2853009700775146,
      "eval_runtime": 6.8776,
      "eval_samples_per_second": 20.356,
      "eval_steps_per_second": 10.178,
      "step": 9
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 1.9650298357009888,
      "learning_rate": 0.0002,
      "loss": 2.159,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 500097330708480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}