{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013505209634616553,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7010419269233105e-05,
      "eval_loss": 1.9662106037139893,
      "eval_runtime": 1635.063,
      "eval_samples_per_second": 9.534,
      "eval_steps_per_second": 4.767,
      "step": 1
    },
    {
      "epoch": 0.00013505209634616554,
      "grad_norm": 0.35768812894821167,
      "learning_rate": 5e-05,
      "loss": 1.9846,
      "step": 5
    },
    {
      "epoch": 0.0002701041926923311,
      "grad_norm": 0.5159976482391357,
      "learning_rate": 0.0001,
      "loss": 1.8767,
      "step": 10
    },
    {
      "epoch": 0.0002701041926923311,
      "eval_loss": 1.9220136404037476,
      "eval_runtime": 1653.5919,
      "eval_samples_per_second": 9.427,
      "eval_steps_per_second": 4.714,
      "step": 10
    },
    {
      "epoch": 0.0004051562890384966,
      "grad_norm": 0.6591143608093262,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9305,
      "step": 15
    },
    {
      "epoch": 0.0005402083853846621,
      "grad_norm": 0.3869290351867676,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9154,
      "step": 20
    },
    {
      "epoch": 0.0005402083853846621,
      "eval_loss": 1.71011483669281,
      "eval_runtime": 1651.2345,
      "eval_samples_per_second": 9.441,
      "eval_steps_per_second": 4.721,
      "step": 20
    },
    {
      "epoch": 0.0006752604817308277,
      "grad_norm": 0.880557656288147,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6707,
      "step": 25
    },
    {
      "epoch": 0.0008103125780769932,
      "grad_norm": 0.6931402087211609,
      "learning_rate": 5e-05,
      "loss": 1.7328,
      "step": 30
    },
    {
      "epoch": 0.0008103125780769932,
      "eval_loss": 1.6576857566833496,
      "eval_runtime": 1652.751,
      "eval_samples_per_second": 9.432,
      "eval_steps_per_second": 4.716,
      "step": 30
    },
    {
      "epoch": 0.0009453646744231588,
      "grad_norm": 0.855765163898468,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.7545,
      "step": 35
    },
    {
      "epoch": 0.0010804167707693243,
      "grad_norm": 0.9248588681221008,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.6355,
      "step": 40
    },
    {
      "epoch": 0.0010804167707693243,
      "eval_loss": 1.6368199586868286,
      "eval_runtime": 1652.5668,
      "eval_samples_per_second": 9.433,
      "eval_steps_per_second": 4.717,
      "step": 40
    },
    {
      "epoch": 0.0012154688671154898,
      "grad_norm": 0.5821701884269714,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.6566,
      "step": 45
    },
    {
      "epoch": 0.0013505209634616553,
      "grad_norm": 0.6669419407844543,
      "learning_rate": 0.0,
      "loss": 1.6922,
      "step": 50
    },
    {
      "epoch": 0.0013505209634616553,
      "eval_loss": 1.6337605714797974,
      "eval_runtime": 1652.6512,
      "eval_samples_per_second": 9.433,
      "eval_steps_per_second": 4.717,
      "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": 1.608389876514816e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}