{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9969230769230769,
  "eval_steps": 100,
  "global_step": 243,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0041025641025641026,
      "grad_norm": 210.73931315288382,
      "learning_rate": 8e-08,
      "loss": 18.1973,
      "step": 1
    },
    {
      "epoch": 0.020512820512820513,
      "grad_norm": 189.19214529123963,
      "learning_rate": 4e-07,
      "loss": 17.4849,
      "step": 5
    },
    {
      "epoch": 0.041025641025641026,
      "grad_norm": 50.75394357650169,
      "learning_rate": 8e-07,
      "loss": 9.526,
      "step": 10
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 9.909947462404205,
      "learning_rate": 1.2e-06,
      "loss": 2.0507,
      "step": 15
    },
    {
      "epoch": 0.08205128205128205,
      "grad_norm": 0.7113742863916499,
      "learning_rate": 1.6e-06,
      "loss": 0.8969,
      "step": 20
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 2.180981476959037,
      "learning_rate": 2e-06,
      "loss": 0.897,
      "step": 25
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": 0.48085194089542066,
      "learning_rate": 1.9974051702905273e-06,
      "loss": 0.8833,
      "step": 30
    },
    {
      "epoch": 0.14358974358974358,
      "grad_norm": 2.661525816178016,
      "learning_rate": 1.9896341474445524e-06,
      "loss": 0.866,
      "step": 35
    },
    {
      "epoch": 0.1641025641025641,
      "grad_norm": 0.8136770335920402,
      "learning_rate": 1.976727260423982e-06,
      "loss": 0.8408,
      "step": 40
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 1.8028564833465748,
      "learning_rate": 1.9587514915766123e-06,
      "loss": 0.8124,
      "step": 45
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.740114367291657,
      "learning_rate": 1.935800129020554e-06,
      "loss": 0.8566,
      "step": 50
    },
    {
      "epoch": 0.22564102564102564,
      "grad_norm": 1.2746735568513963,
      "learning_rate": 1.907992282510675e-06,
      "loss": 0.7979,
      "step": 55
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": 0.9149035709846786,
      "learning_rate": 1.8754722652995345e-06,
      "loss": 0.788,
      "step": 60
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.4175731136283647,
      "learning_rate": 1.8384088452007577e-06,
      "loss": 0.7389,
      "step": 65
    },
    {
      "epoch": 0.28717948717948716,
      "grad_norm": 0.9899809438913668,
      "learning_rate": 1.7969943687415575e-06,
      "loss": 0.7096,
      "step": 70
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 1.1985302229382249,
      "learning_rate": 1.751443762949772e-06,
      "loss": 0.7626,
      "step": 75
    },
    {
      "epoch": 0.3282051282051282,
      "grad_norm": 1.4478960916721024,
      "learning_rate": 1.7019934199557866e-06,
      "loss": 0.7437,
      "step": 80
    },
    {
      "epoch": 0.3487179487179487,
      "grad_norm": 1.124924256759073,
      "learning_rate": 1.6488999701978903e-06,
      "loss": 0.7166,
      "step": 85
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 1.0201534805284107,
      "learning_rate": 1.5924389505977035e-06,
      "loss": 0.7481,
      "step": 90
    },
    {
      "epoch": 0.38974358974358975,
      "grad_norm": 0.7378978575819284,
      "learning_rate": 1.5329033746173974e-06,
      "loss": 0.7239,
      "step": 95
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.948500844499939,
      "learning_rate": 1.4706022116196205e-06,
      "loss": 0.7029,
      "step": 100
    },
    {
      "epoch": 0.4307692307692308,
      "grad_norm": 0.8608325581781239,
      "learning_rate": 1.4058587834217354e-06,
      "loss": 0.7191,
      "step": 105
    },
    {
      "epoch": 0.4512820512820513,
      "grad_norm": 0.8398589604579024,
      "learning_rate": 1.3390090863657047e-06,
      "loss": 0.7254,
      "step": 110
    },
    {
      "epoch": 0.4717948717948718,
      "grad_norm": 1.0308467566906994,
      "learning_rate": 1.2704000476115078e-06,
      "loss": 0.6641,
      "step": 115
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": 0.8777882378326041,
      "learning_rate": 1.200387724703341e-06,
      "loss": 0.701,
      "step": 120
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.7515670727773807,
      "learning_rate": 1.1293354577522264e-06,
      "loss": 0.7077,
      "step": 125
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.9791903733522638,
      "learning_rate": 1.0576119838245842e-06,
      "loss": 0.6749,
      "step": 130
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.6693635053325145,
      "learning_rate": 9.85589523322443e-07,
      "loss": 0.6577,
      "step": 135
    },
    {
      "epoch": 0.5743589743589743,
      "grad_norm": 0.6833989798868547,
      "learning_rate": 9.136418482863228e-07,
      "loss": 0.7114,
      "step": 140
    },
    {
      "epoch": 0.5948717948717949,
      "grad_norm": 0.797013158279301,
      "learning_rate": 8.42142342645646e-07,
      "loss": 0.6783,
      "step": 145
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.8196141619706488,
      "learning_rate": 7.714620644833109e-07,
      "loss": 0.6819,
      "step": 150
    },
    {
      "epoch": 0.6358974358974359,
      "grad_norm": 0.6772830419809014,
      "learning_rate": 7.019678203706163e-07,
      "loss": 0.6921,
      "step": 155
    },
    {
      "epoch": 0.6564102564102564,
      "grad_norm": 0.7406301330967787,
      "learning_rate": 6.340202617660841e-07,
      "loss": 0.6728,
      "step": 160
    },
    {
      "epoch": 0.676923076923077,
      "grad_norm": 0.6830389115079865,
      "learning_rate": 5.679720133572206e-07,
      "loss": 0.6952,
      "step": 165
    },
    {
      "epoch": 0.6974358974358974,
      "grad_norm": 0.9726302939222433,
      "learning_rate": 5.041658430584852e-07,
      "loss": 0.628,
      "step": 170
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.768405576158193,
      "learning_rate": 4.429328831625565e-07,
      "loss": 0.672,
      "step": 175
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.6974413420308802,
      "learning_rate": 3.8459091187650726e-07,
      "loss": 0.6202,
      "step": 180
    },
    {
      "epoch": 0.7589743589743589,
      "grad_norm": 0.7432097523967477,
      "learning_rate": 3.294427041611425e-07,
      "loss": 0.6516,
      "step": 185
    },
    {
      "epoch": 0.7794871794871795,
      "grad_norm": 0.7704712087921601,
      "learning_rate": 2.777744604320705e-07,
      "loss": 0.6766,
      "step": 190
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7000311466001509,
      "learning_rate": 2.2985432127701941e-07,
      "loss": 0.6601,
      "step": 195
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.6344590391399256,
      "learning_rate": 1.8593097589751316e-07,
      "loss": 0.6668,
      "step": 200
    },
    {
      "epoch": 0.841025641025641,
      "grad_norm": 0.8068713449115361,
      "learning_rate": 1.4623237149661137e-07,
      "loss": 0.6372,
      "step": 205
    },
    {
      "epoch": 0.8615384615384616,
      "grad_norm": 0.7667845744181657,
      "learning_rate": 1.1096453031056264e-07,
      "loss": 0.6336,
      "step": 210
    },
    {
      "epoch": 0.882051282051282,
      "grad_norm": 0.6892199798165223,
      "learning_rate": 8.031048042356392e-08,
      "loss": 0.6524,
      "step": 215
    },
    {
      "epoch": 0.9025641025641026,
      "grad_norm": 0.9294089287613709,
      "learning_rate": 5.442930591433992e-08,
      "loss": 0.6226,
      "step": 220
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.6898179274224119,
      "learning_rate": 3.345532126395578e-08,
      "loss": 0.6303,
      "step": 225
    },
    {
      "epoch": 0.9435897435897436,
      "grad_norm": 0.8446395156543057,
      "learning_rate": 1.7497374309405344e-08,
      "loss": 0.69,
      "step": 230
    },
    {
      "epoch": 0.9641025641025641,
      "grad_norm": 0.8675398091030025,
      "learning_rate": 6.6382813604083375e-09,
      "loss": 0.6432,
      "step": 235
    },
    {
      "epoch": 0.9846153846153847,
      "grad_norm": 0.6706977696447584,
      "learning_rate": 9.343974109685682e-10,
      "loss": 0.6681,
      "step": 240
    },
    {
      "epoch": 0.9969230769230769,
      "step": 243,
      "total_flos": 84181718171648.0,
      "train_loss": 1.2716579986697851,
      "train_runtime": 2872.5846,
      "train_samples_per_second": 10.861,
      "train_steps_per_second": 0.085
    }
  ],
  "logging_steps": 5,
  "max_steps": 243,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 84181718171648.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}