{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013823610727121925,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.607870242373975e-05,
      "eval_loss": 1.6102041006088257,
      "eval_runtime": 1242.2325,
      "eval_samples_per_second": 7.356,
      "eval_steps_per_second": 3.678,
      "step": 1
    },
    {
      "epoch": 0.00013823610727121925,
      "grad_norm": 0.8831824064254761,
      "learning_rate": 4e-05,
      "loss": 5.9381,
      "step": 3
    },
    {
      "epoch": 0.00023039351211869873,
      "eval_loss": 1.5882604122161865,
      "eval_runtime": 1246.126,
      "eval_samples_per_second": 7.333,
      "eval_steps_per_second": 3.667,
      "step": 5
    },
    {
      "epoch": 0.0002764722145424385,
      "grad_norm": 1.0897746086120605,
      "learning_rate": 8e-05,
      "loss": 5.26,
      "step": 6
    },
    {
      "epoch": 0.0004147083218136577,
      "grad_norm": 1.1137936115264893,
      "learning_rate": 0.00012,
      "loss": 5.9993,
      "step": 9
    },
    {
      "epoch": 0.00046078702423739745,
      "eval_loss": 1.4089840650558472,
      "eval_runtime": 1245.8334,
      "eval_samples_per_second": 7.335,
      "eval_steps_per_second": 3.667,
      "step": 10
    },
    {
      "epoch": 0.000552944429084877,
      "grad_norm": 1.1472383737564087,
      "learning_rate": 0.00016,
      "loss": 5.9979,
      "step": 12
    },
    {
      "epoch": 0.0006911805363560963,
      "grad_norm": 0.7887614965438843,
      "learning_rate": 0.0002,
      "loss": 5.3875,
      "step": 15
    },
    {
      "epoch": 0.0006911805363560963,
      "eval_loss": 1.2726045846939087,
      "eval_runtime": 1245.3567,
      "eval_samples_per_second": 7.338,
      "eval_steps_per_second": 3.669,
      "step": 15
    },
    {
      "epoch": 0.0008294166436273154,
      "grad_norm": 1.062957763671875,
      "learning_rate": 0.00018090169943749476,
      "loss": 5.2179,
      "step": 18
    },
    {
      "epoch": 0.0009215740484747949,
      "eval_loss": 1.2275902032852173,
      "eval_runtime": 1246.2045,
      "eval_samples_per_second": 7.333,
      "eval_steps_per_second": 3.666,
      "step": 20
    },
    {
      "epoch": 0.0009676527508985347,
      "grad_norm": 0.8761299848556519,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.7563,
      "step": 21
    },
    {
      "epoch": 0.001105888858169754,
      "grad_norm": 0.9032831192016602,
      "learning_rate": 6.909830056250527e-05,
      "loss": 4.4314,
      "step": 24
    },
    {
      "epoch": 0.0011519675605934938,
      "eval_loss": 1.2096927165985107,
      "eval_runtime": 1245.7257,
      "eval_samples_per_second": 7.335,
      "eval_steps_per_second": 3.668,
      "step": 25
    },
    {
      "epoch": 0.0012441249654409731,
      "grad_norm": 1.0080879926681519,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 4.7194,
      "step": 27
    },
    {
      "epoch": 0.0013823610727121925,
      "grad_norm": 0.8476549983024597,
      "learning_rate": 0.0,
      "loss": 5.2062,
      "step": 30
    },
    {
      "epoch": 0.0013823610727121925,
      "eval_loss": 1.2064721584320068,
      "eval_runtime": 1245.4272,
      "eval_samples_per_second": 7.337,
      "eval_steps_per_second": 3.669,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.094783887572992e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}