{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007283321194464676,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00024277737314882253,
      "eval_loss": NaN,
      "eval_runtime": 60.3166,
      "eval_samples_per_second": 28.765,
      "eval_steps_per_second": 14.391,
      "step": 1
    },
    {
      "epoch": 0.0007283321194464676,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0012138868657441126,
      "eval_loss": NaN,
      "eval_runtime": 60.2985,
      "eval_samples_per_second": 28.774,
      "eval_steps_per_second": 14.395,
      "step": 5
    },
    {
      "epoch": 0.0014566642388929353,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0021849963583394027,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0024277737314882253,
      "eval_loss": NaN,
      "eval_runtime": 60.1791,
      "eval_samples_per_second": 28.831,
      "eval_steps_per_second": 14.424,
      "step": 10
    },
    {
      "epoch": 0.0029133284777858705,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.003641660597232338,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.003641660597232338,
      "eval_loss": NaN,
      "eval_runtime": 60.6512,
      "eval_samples_per_second": 28.606,
      "eval_steps_per_second": 14.311,
      "step": 15
    },
    {
      "epoch": 0.004369992716678805,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.004855547462976451,
      "eval_loss": NaN,
      "eval_runtime": 60.5457,
      "eval_samples_per_second": 28.656,
      "eval_steps_per_second": 14.336,
      "step": 20
    },
    {
      "epoch": 0.005098324836125273,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.005826656955571741,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.006069434328720563,
      "eval_loss": NaN,
      "eval_runtime": 60.4965,
      "eval_samples_per_second": 28.679,
      "eval_steps_per_second": 14.348,
      "step": 25
    },
    {
      "epoch": 0.0065549890750182084,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.007283321194464676,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.007283321194464676,
      "eval_loss": NaN,
      "eval_runtime": 60.4207,
      "eval_samples_per_second": 28.715,
      "eval_steps_per_second": 14.366,
      "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": 221137866326016.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}