{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001069741817812271,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.139483635624542e-05,
      "eval_loss": 3.5064687728881836,
      "eval_runtime": 1313.719,
      "eval_samples_per_second": 14.981,
      "eval_steps_per_second": 7.491,
      "step": 1
    },
    {
      "epoch": 0.0001069741817812271,
      "grad_norm": 3.9627699851989746,
      "learning_rate": 5e-05,
      "loss": 3.4034,
      "step": 5
    },
    {
      "epoch": 0.0002139483635624542,
      "grad_norm": 4.111531734466553,
      "learning_rate": 0.0001,
      "loss": 2.8548,
      "step": 10
    },
    {
      "epoch": 0.0002139483635624542,
      "eval_loss": 1.7997324466705322,
      "eval_runtime": 1311.2175,
      "eval_samples_per_second": 15.01,
      "eval_steps_per_second": 7.505,
      "step": 10
    },
    {
      "epoch": 0.0003209225453436813,
      "grad_norm": 3.4243643283843994,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1567,
      "step": 15
    },
    {
      "epoch": 0.0004278967271249084,
      "grad_norm": 3.6547865867614746,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2111,
      "step": 20
    },
    {
      "epoch": 0.0004278967271249084,
      "eval_loss": 0.11550228297710419,
      "eval_runtime": 1312.2394,
      "eval_samples_per_second": 14.998,
      "eval_steps_per_second": 7.499,
      "step": 20
    },
    {
      "epoch": 0.0005348709089061355,
      "grad_norm": 3.4264965057373047,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.097,
      "step": 25
    },
    {
      "epoch": 0.0006418450906873626,
      "grad_norm": 3.2755022048950195,
      "learning_rate": 5e-05,
      "loss": 0.1013,
      "step": 30
    },
    {
      "epoch": 0.0006418450906873626,
      "eval_loss": 0.10277899354696274,
      "eval_runtime": 1320.27,
      "eval_samples_per_second": 14.907,
      "eval_steps_per_second": 7.454,
      "step": 30
    },
    {
      "epoch": 0.0007488192724685898,
      "grad_norm": 2.4465465545654297,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0793,
      "step": 35
    },
    {
      "epoch": 0.0008557934542498168,
      "grad_norm": 1.246980905532837,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.09,
      "step": 40
    },
    {
      "epoch": 0.0008557934542498168,
      "eval_loss": 0.08215479552745819,
      "eval_runtime": 1314.9991,
      "eval_samples_per_second": 14.967,
      "eval_steps_per_second": 7.484,
      "step": 40
    },
    {
      "epoch": 0.0009627676360310439,
      "grad_norm": 3.9636285305023193,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1373,
      "step": 45
    },
    {
      "epoch": 0.001069741817812271,
      "grad_norm": 2.096292734146118,
      "learning_rate": 0.0,
      "loss": 0.0698,
      "step": 50
    },
    {
      "epoch": 0.001069741817812271,
      "eval_loss": 0.08028090745210648,
      "eval_runtime": 1320.7868,
      "eval_samples_per_second": 14.901,
      "eval_steps_per_second": 7.451,
      "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": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}