{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007769001683283698,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025896672277612325,
      "eval_loss": 1.5784790515899658,
      "eval_runtime": 207.9547,
      "eval_samples_per_second": 7.819,
      "eval_steps_per_second": 3.91,
      "step": 1
    },
    {
      "epoch": 0.0007769001683283698,
      "grad_norm": 2.280616283416748,
      "learning_rate": 6e-05,
      "loss": 1.65,
      "step": 3
    },
    {
      "epoch": 0.0015538003366567395,
      "grad_norm": 2.1446313858032227,
      "learning_rate": 0.00012,
      "loss": 1.5214,
      "step": 6
    },
    {
      "epoch": 0.002071733782208986,
      "eval_loss": 0.8108781576156616,
      "eval_runtime": 210.4472,
      "eval_samples_per_second": 7.726,
      "eval_steps_per_second": 3.863,
      "step": 8
    },
    {
      "epoch": 0.0023307005049851095,
      "grad_norm": 1.6328656673431396,
      "learning_rate": 0.00018,
      "loss": 0.8662,
      "step": 9
    },
    {
      "epoch": 0.003107600673313479,
      "grad_norm": 1.1344081163406372,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.5718,
      "step": 12
    },
    {
      "epoch": 0.003884500841641849,
      "grad_norm": 1.0098446607589722,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.3558,
      "step": 15
    },
    {
      "epoch": 0.004143467564417972,
      "eval_loss": 0.3522951006889343,
      "eval_runtime": 209.9502,
      "eval_samples_per_second": 7.745,
      "eval_steps_per_second": 3.872,
      "step": 16
    },
    {
      "epoch": 0.004661401009970219,
      "grad_norm": 0.8850109577178955,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.2797,
      "step": 18
    },
    {
      "epoch": 0.005438301178298589,
      "grad_norm": 1.3260667324066162,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.3583,
      "step": 21
    },
    {
      "epoch": 0.006215201346626958,
      "grad_norm": 1.1539181470870972,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.3132,
      "step": 24
    },
    {
      "epoch": 0.006215201346626958,
      "eval_loss": 0.2725517749786377,
      "eval_runtime": 209.9977,
      "eval_samples_per_second": 7.743,
      "eval_steps_per_second": 3.871,
      "step": 24
    },
    {
      "epoch": 0.006992101514955328,
      "grad_norm": 0.7530409097671509,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.2945,
      "step": 27
    },
    {
      "epoch": 0.007769001683283698,
      "grad_norm": 0.7379133105278015,
      "learning_rate": 0.0,
      "loss": 0.2486,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}