{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021114864864864864,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008445945945945946,
      "grad_norm": 7.727255344390869,
      "learning_rate": 2e-05,
      "loss": 8.372,
      "step": 1
    },
    {
      "epoch": 0.0008445945945945946,
      "eval_loss": 8.063016891479492,
      "eval_runtime": 125.6054,
      "eval_samples_per_second": 3.973,
      "eval_steps_per_second": 1.99,
      "step": 1
    },
    {
      "epoch": 0.0016891891891891893,
      "grad_norm": 9.669200897216797,
      "learning_rate": 4e-05,
      "loss": 8.046,
      "step": 2
    },
    {
      "epoch": 0.002533783783783784,
      "grad_norm": 9.18079948425293,
      "learning_rate": 6e-05,
      "loss": 8.0321,
      "step": 3
    },
    {
      "epoch": 0.0033783783783783786,
      "grad_norm": 9.363329887390137,
      "learning_rate": 8e-05,
      "loss": 7.0182,
      "step": 4
    },
    {
      "epoch": 0.004222972972972973,
      "grad_norm": 9.816231727600098,
      "learning_rate": 0.0001,
      "loss": 7.7225,
      "step": 5
    },
    {
      "epoch": 0.005067567567567568,
      "grad_norm": 9.099088668823242,
      "learning_rate": 0.00012,
      "loss": 7.875,
      "step": 6
    },
    {
      "epoch": 0.0059121621621621625,
      "grad_norm": 9.296707153320312,
      "learning_rate": 0.00014,
      "loss": 5.6422,
      "step": 7
    },
    {
      "epoch": 0.006756756756756757,
      "grad_norm": 9.570911407470703,
      "learning_rate": 0.00016,
      "loss": 3.8105,
      "step": 8
    },
    {
      "epoch": 0.007601351351351352,
      "grad_norm": 8.131881713867188,
      "learning_rate": 0.00018,
      "loss": 2.0885,
      "step": 9
    },
    {
      "epoch": 0.008445945945945946,
      "grad_norm": 5.208433628082275,
      "learning_rate": 0.0002,
      "loss": 1.0562,
      "step": 10
    },
    {
      "epoch": 0.009290540540540541,
      "grad_norm": 10.91145133972168,
      "learning_rate": 0.0001999390827019096,
      "loss": 2.9782,
      "step": 11
    },
    {
      "epoch": 0.010135135135135136,
      "grad_norm": 17.846271514892578,
      "learning_rate": 0.00019975640502598244,
      "loss": 3.6074,
      "step": 12
    },
    {
      "epoch": 0.01097972972972973,
      "grad_norm": 8.735333442687988,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.805,
      "step": 13
    },
    {
      "epoch": 0.011824324324324325,
      "grad_norm": 6.351312637329102,
      "learning_rate": 0.00019902680687415705,
      "loss": 1.1463,
      "step": 14
    },
    {
      "epoch": 0.01266891891891892,
      "grad_norm": 2.7280004024505615,
      "learning_rate": 0.00019848077530122083,
      "loss": 0.2077,
      "step": 15
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 5.975780487060547,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.1476,
      "step": 16
    },
    {
      "epoch": 0.014358108108108109,
      "grad_norm": 5.841843605041504,
      "learning_rate": 0.00019702957262759965,
      "loss": 1.0156,
      "step": 17
    },
    {
      "epoch": 0.015202702702702704,
      "grad_norm": 6.997043132781982,
      "learning_rate": 0.0001961261695938319,
      "loss": 0.6625,
      "step": 18
    },
    {
      "epoch": 0.016047297297297296,
      "grad_norm": 7.254495620727539,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.8055,
      "step": 19
    },
    {
      "epoch": 0.016891891891891893,
      "grad_norm": 5.706070423126221,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.3771,
      "step": 20
    },
    {
      "epoch": 0.017736486486486486,
      "grad_norm": 3.621236801147461,
      "learning_rate": 0.00019271838545667876,
      "loss": 0.2341,
      "step": 21
    },
    {
      "epoch": 0.018581081081081082,
      "grad_norm": 1.3116642236709595,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0388,
      "step": 22
    },
    {
      "epoch": 0.019425675675675675,
      "grad_norm": 6.483520030975342,
      "learning_rate": 0.0001898794046299167,
      "loss": 0.7181,
      "step": 23
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 16.79340171813965,
      "learning_rate": 0.00018829475928589271,
      "loss": 1.0507,
      "step": 24
    },
    {
      "epoch": 0.021114864864864864,
      "grad_norm": 3.9302544593811035,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.8626,
      "step": 25
    },
    {
      "epoch": 0.021114864864864864,
      "eval_loss": 0.4980570375919342,
      "eval_runtime": 126.9443,
      "eval_samples_per_second": 3.931,
      "eval_steps_per_second": 1.969,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3054705844224e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}