{
  "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": 210.52482598709943,
      "learning_rate": 8e-08,
      "loss": 18.5684,
      "step": 1
    },
    {
      "epoch": 0.020512820512820513,
      "grad_norm": 186.8406143210285,
      "learning_rate": 4e-07,
      "loss": 17.1831,
      "step": 5
    },
    {
      "epoch": 0.041025641025641026,
      "grad_norm": 49.91185411718416,
      "learning_rate": 8e-07,
      "loss": 9.5085,
      "step": 10
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 9.332467552302559,
      "learning_rate": 1.2e-06,
      "loss": 2.0752,
      "step": 15
    },
    {
      "epoch": 0.08205128205128205,
      "grad_norm": 0.8297806389960246,
      "learning_rate": 1.6e-06,
      "loss": 0.9159,
      "step": 20
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 3.114341047106303,
      "learning_rate": 2e-06,
      "loss": 0.8841,
      "step": 25
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": 1.934423072293649,
      "learning_rate": 1.9974051702905273e-06,
      "loss": 0.8479,
      "step": 30
    },
    {
      "epoch": 0.14358974358974358,
      "grad_norm": 1.6875673048587294,
      "learning_rate": 1.9896341474445524e-06,
      "loss": 0.8417,
      "step": 35
    },
    {
      "epoch": 0.1641025641025641,
      "grad_norm": 1.7762270563382576,
      "learning_rate": 1.976727260423982e-06,
      "loss": 0.7891,
      "step": 40
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.9578157871381868,
      "learning_rate": 1.9587514915766123e-06,
      "loss": 0.8344,
      "step": 45
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 2.6943003842765423,
      "learning_rate": 1.935800129020554e-06,
      "loss": 0.7999,
      "step": 50
    },
    {
      "epoch": 0.22564102564102564,
      "grad_norm": 0.8483257920517897,
      "learning_rate": 1.907992282510675e-06,
      "loss": 0.7871,
      "step": 55
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": 1.355665613118592,
      "learning_rate": 1.8754722652995345e-06,
      "loss": 0.7603,
      "step": 60
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.3698034199623528,
      "learning_rate": 1.8384088452007577e-06,
      "loss": 0.7711,
      "step": 65
    },
    {
      "epoch": 0.28717948717948716,
      "grad_norm": 0.9973813732040485,
      "learning_rate": 1.7969943687415575e-06,
      "loss": 0.7702,
      "step": 70
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 2.067655192245599,
      "learning_rate": 1.751443762949772e-06,
      "loss": 0.7674,
      "step": 75
    },
    {
      "epoch": 0.3282051282051282,
      "grad_norm": 0.7664884814735945,
      "learning_rate": 1.7019934199557866e-06,
      "loss": 0.7411,
      "step": 80
    },
    {
      "epoch": 0.3487179487179487,
      "grad_norm": 1.0493906781125153,
      "learning_rate": 1.6488999701978903e-06,
      "loss": 0.7015,
      "step": 85
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.9938125483952975,
      "learning_rate": 1.5924389505977035e-06,
      "loss": 0.7287,
      "step": 90
    },
    {
      "epoch": 0.38974358974358975,
      "grad_norm": 1.0677317732124718,
      "learning_rate": 1.5329033746173974e-06,
      "loss": 0.7254,
      "step": 95
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.8122971279562344,
      "learning_rate": 1.4706022116196205e-06,
      "loss": 0.7475,
      "step": 100
    },
    {
      "epoch": 0.4307692307692308,
      "grad_norm": 0.7681446410916759,
      "learning_rate": 1.4058587834217354e-06,
      "loss": 0.7163,
      "step": 105
    },
    {
      "epoch": 0.4512820512820513,
      "grad_norm": 0.766906823065794,
      "learning_rate": 1.3390090863657047e-06,
      "loss": 0.7117,
      "step": 110
    },
    {
      "epoch": 0.4717948717948718,
      "grad_norm": 0.8487697397343301,
      "learning_rate": 1.2704000476115078e-06,
      "loss": 0.6475,
      "step": 115
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": 1.0050583245136004,
      "learning_rate": 1.200387724703341e-06,
      "loss": 0.7105,
      "step": 120
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.7426930539258657,
      "learning_rate": 1.1293354577522264e-06,
      "loss": 0.7158,
      "step": 125
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.8413604322965307,
      "learning_rate": 1.0576119838245842e-06,
      "loss": 0.6915,
      "step": 130
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.5752843532661515,
      "learning_rate": 9.85589523322443e-07,
      "loss": 0.7209,
      "step": 135
    },
    {
      "epoch": 0.5743589743589743,
      "grad_norm": 0.9645483285040541,
      "learning_rate": 9.136418482863228e-07,
      "loss": 0.6739,
      "step": 140
    },
    {
      "epoch": 0.5948717948717949,
      "grad_norm": 0.7607550081366585,
      "learning_rate": 8.42142342645646e-07,
      "loss": 0.6717,
      "step": 145
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.0589042706336858,
      "learning_rate": 7.714620644833109e-07,
      "loss": 0.6534,
      "step": 150
    },
    {
      "epoch": 0.6358974358974359,
      "grad_norm": 0.7089491583646673,
      "learning_rate": 7.019678203706163e-07,
      "loss": 0.6696,
      "step": 155
    },
    {
      "epoch": 0.6564102564102564,
      "grad_norm": 0.9341940371244601,
      "learning_rate": 6.340202617660841e-07,
      "loss": 0.6482,
      "step": 160
    },
    {
      "epoch": 0.676923076923077,
      "grad_norm": 0.7411098123857883,
      "learning_rate": 5.679720133572206e-07,
      "loss": 0.6187,
      "step": 165
    },
    {
      "epoch": 0.6974358974358974,
      "grad_norm": 0.8616495817851872,
      "learning_rate": 5.041658430584852e-07,
      "loss": 0.6386,
      "step": 170
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.7200165364613889,
      "learning_rate": 4.429328831625565e-07,
      "loss": 0.6567,
      "step": 175
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.6168896507164103,
      "learning_rate": 3.8459091187650726e-07,
      "loss": 0.6644,
      "step": 180
    },
    {
      "epoch": 0.7589743589743589,
      "grad_norm": 0.6719936032666863,
      "learning_rate": 3.294427041611425e-07,
      "loss": 0.6464,
      "step": 185
    },
    {
      "epoch": 0.7794871794871795,
      "grad_norm": 0.8824680726642901,
      "learning_rate": 2.777744604320705e-07,
      "loss": 0.6362,
      "step": 190
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7384901847927622,
      "learning_rate": 2.2985432127701941e-07,
      "loss": 0.6385,
      "step": 195
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.9346648012471711,
      "learning_rate": 1.8593097589751316e-07,
      "loss": 0.6423,
      "step": 200
    },
    {
      "epoch": 0.841025641025641,
      "grad_norm": 0.7741404463056779,
      "learning_rate": 1.4623237149661137e-07,
      "loss": 0.6425,
      "step": 205
    },
    {
      "epoch": 0.8615384615384616,
      "grad_norm": 0.7837940282138485,
      "learning_rate": 1.1096453031056264e-07,
      "loss": 0.5925,
      "step": 210
    },
    {
      "epoch": 0.882051282051282,
      "grad_norm": 0.6434405301070071,
      "learning_rate": 8.031048042356392e-08,
      "loss": 0.6155,
      "step": 215
    },
    {
      "epoch": 0.9025641025641026,
      "grad_norm": 0.6950331917340359,
      "learning_rate": 5.442930591433992e-08,
      "loss": 0.6336,
      "step": 220
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.7624734080498339,
      "learning_rate": 3.345532126395578e-08,
      "loss": 0.628,
      "step": 225
    },
    {
      "epoch": 0.9435897435897436,
      "grad_norm": 0.7335512264577648,
      "learning_rate": 1.7497374309405344e-08,
      "loss": 0.6125,
      "step": 230
    },
    {
      "epoch": 0.9641025641025641,
      "grad_norm": 0.7687162657729733,
      "learning_rate": 6.6382813604083375e-09,
      "loss": 0.6287,
      "step": 235
    },
    {
      "epoch": 0.9846153846153847,
      "grad_norm": 0.7525426453572169,
      "learning_rate": 9.343974109685682e-10,
      "loss": 0.6188,
      "step": 240
    },
    {
      "epoch": 0.9969230769230769,
      "step": 243,
      "total_flos": 82980012523520.0,
      "train_loss": 1.2597844002178176,
      "train_runtime": 2824.655,
      "train_samples_per_second": 11.046,
      "train_steps_per_second": 0.086
    }
  ],
  "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": 82980012523520.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}