{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.018045112781955,
  "eval_steps": 50,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02406015037593985,
      "grad_norm": 9.00250244140625,
      "learning_rate": 2e-05,
      "loss": 25.3627,
      "step": 1
    },
    {
      "epoch": 0.02406015037593985,
      "eval_loss": 1.6399891376495361,
      "eval_runtime": 29.2525,
      "eval_samples_per_second": 4.786,
      "eval_steps_per_second": 1.196,
      "step": 1
    },
    {
      "epoch": 0.0481203007518797,
      "grad_norm": 9.322636604309082,
      "learning_rate": 4e-05,
      "loss": 25.5135,
      "step": 2
    },
    {
      "epoch": 0.07218045112781955,
      "grad_norm": 9.623148918151855,
      "learning_rate": 6e-05,
      "loss": 23.946,
      "step": 3
    },
    {
      "epoch": 0.0962406015037594,
      "grad_norm": 8.729375839233398,
      "learning_rate": 8e-05,
      "loss": 24.9221,
      "step": 4
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 8.351356506347656,
      "learning_rate": 0.0001,
      "loss": 25.0889,
      "step": 5
    },
    {
      "epoch": 0.1443609022556391,
      "grad_norm": 6.019646644592285,
      "learning_rate": 0.00012,
      "loss": 23.2186,
      "step": 6
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 10.014695167541504,
      "learning_rate": 0.00014,
      "loss": 23.2874,
      "step": 7
    },
    {
      "epoch": 0.1924812030075188,
      "grad_norm": 11.5293550491333,
      "learning_rate": 0.00016,
      "loss": 24.2037,
      "step": 8
    },
    {
      "epoch": 0.21654135338345865,
      "grad_norm": 9.74930477142334,
      "learning_rate": 0.00018,
      "loss": 22.0722,
      "step": 9
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 9.796451568603516,
      "learning_rate": 0.0002,
      "loss": 21.265,
      "step": 10
    },
    {
      "epoch": 0.2646616541353383,
      "grad_norm": 7.13716983795166,
      "learning_rate": 0.0001995184726672197,
      "loss": 21.5623,
      "step": 11
    },
    {
      "epoch": 0.2887218045112782,
      "grad_norm": 6.275375843048096,
      "learning_rate": 0.00019807852804032305,
      "loss": 21.1163,
      "step": 12
    },
    {
      "epoch": 0.31278195488721805,
      "grad_norm": 6.420385360717773,
      "learning_rate": 0.0001956940335732209,
      "loss": 20.9436,
      "step": 13
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 6.751258850097656,
      "learning_rate": 0.0001923879532511287,
      "loss": 21.3085,
      "step": 14
    },
    {
      "epoch": 0.3609022556390977,
      "grad_norm": 5.387437343597412,
      "learning_rate": 0.0001881921264348355,
      "loss": 21.1495,
      "step": 15
    },
    {
      "epoch": 0.3849624060150376,
      "grad_norm": 5.398016452789307,
      "learning_rate": 0.00018314696123025454,
      "loss": 20.6123,
      "step": 16
    },
    {
      "epoch": 0.40902255639097745,
      "grad_norm": 5.040699005126953,
      "learning_rate": 0.0001773010453362737,
      "loss": 20.4743,
      "step": 17
    },
    {
      "epoch": 0.4330827067669173,
      "grad_norm": 6.368396282196045,
      "learning_rate": 0.00017071067811865476,
      "loss": 20.1228,
      "step": 18
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 5.834798812866211,
      "learning_rate": 0.00016343932841636456,
      "loss": 20.5022,
      "step": 19
    },
    {
      "epoch": 0.48120300751879697,
      "grad_norm": 5.360933780670166,
      "learning_rate": 0.00015555702330196023,
      "loss": 20.245,
      "step": 20
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 5.43699836730957,
      "learning_rate": 0.0001471396736825998,
      "loss": 18.5126,
      "step": 21
    },
    {
      "epoch": 0.5293233082706766,
      "grad_norm": 5.862579345703125,
      "learning_rate": 0.000138268343236509,
      "loss": 19.5588,
      "step": 22
    },
    {
      "epoch": 0.5533834586466165,
      "grad_norm": 5.211700439453125,
      "learning_rate": 0.00012902846772544624,
      "loss": 19.6664,
      "step": 23
    },
    {
      "epoch": 0.5774436090225564,
      "grad_norm": 5.469019889831543,
      "learning_rate": 0.00011950903220161285,
      "loss": 19.5394,
      "step": 24
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 5.546566009521484,
      "learning_rate": 0.0001098017140329561,
      "loss": 19.9018,
      "step": 25
    },
    {
      "epoch": 0.6255639097744361,
      "grad_norm": 4.911322593688965,
      "learning_rate": 0.0001,
      "loss": 19.5437,
      "step": 26
    },
    {
      "epoch": 0.649624060150376,
      "grad_norm": 5.401342391967773,
      "learning_rate": 9.019828596704394e-05,
      "loss": 19.2188,
      "step": 27
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 5.744024753570557,
      "learning_rate": 8.049096779838719e-05,
      "loss": 19.4305,
      "step": 28
    },
    {
      "epoch": 0.6977443609022557,
      "grad_norm": 4.69623327255249,
      "learning_rate": 7.097153227455379e-05,
      "loss": 19.9173,
      "step": 29
    },
    {
      "epoch": 0.7218045112781954,
      "grad_norm": 5.057282447814941,
      "learning_rate": 6.173165676349103e-05,
      "loss": 19.5849,
      "step": 30
    },
    {
      "epoch": 0.7458646616541353,
      "grad_norm": 6.046416759490967,
      "learning_rate": 5.286032631740023e-05,
      "loss": 19.2762,
      "step": 31
    },
    {
      "epoch": 0.7699248120300752,
      "grad_norm": 4.617074489593506,
      "learning_rate": 4.444297669803981e-05,
      "loss": 18.5243,
      "step": 32
    },
    {
      "epoch": 0.793984962406015,
      "grad_norm": 4.758453369140625,
      "learning_rate": 3.6560671583635467e-05,
      "loss": 19.9209,
      "step": 33
    },
    {
      "epoch": 0.8180451127819549,
      "grad_norm": 5.196866512298584,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 19.5214,
      "step": 34
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 5.4060797691345215,
      "learning_rate": 2.26989546637263e-05,
      "loss": 20.2216,
      "step": 35
    },
    {
      "epoch": 0.8661654135338346,
      "grad_norm": 4.7935285568237305,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 18.7556,
      "step": 36
    },
    {
      "epoch": 0.8902255639097745,
      "grad_norm": 6.893577575683594,
      "learning_rate": 1.1807873565164506e-05,
      "loss": 18.1903,
      "step": 37
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 5.185873508453369,
      "learning_rate": 7.612046748871327e-06,
      "loss": 19.422,
      "step": 38
    },
    {
      "epoch": 0.9383458646616541,
      "grad_norm": 5.145367622375488,
      "learning_rate": 4.305966426779118e-06,
      "loss": 19.4979,
      "step": 39
    },
    {
      "epoch": 0.9624060150375939,
      "grad_norm": 4.932560920715332,
      "learning_rate": 1.921471959676957e-06,
      "loss": 19.1882,
      "step": 40
    },
    {
      "epoch": 0.9864661654135338,
      "grad_norm": 5.070599555969238,
      "learning_rate": 4.815273327803182e-07,
      "loss": 19.8154,
      "step": 41
    },
    {
      "epoch": 1.018045112781955,
      "grad_norm": 4.737176895141602,
      "learning_rate": 0.0,
      "loss": 19.7032,
      "step": 42
    }
  ],
  "logging_steps": 1,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.8655039966806016e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}