{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 216,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004629629629629629,
      "grad_norm": 17.14967918395996,
      "learning_rate": 0.0,
      "loss": 3.3728,
      "step": 1
    },
    {
      "epoch": 0.023148148148148147,
      "grad_norm": 15.374231338500977,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 3.3769,
      "step": 5
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 6.152224540710449,
      "learning_rate": 8.181818181818183e-06,
      "loss": 3.0128,
      "step": 10
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 5.15545129776001,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 2.6223,
      "step": 15
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 8.587775230407715,
      "learning_rate": 1.7272727272727274e-05,
      "loss": 2.398,
      "step": 20
    },
    {
      "epoch": 0.11574074074074074,
      "grad_norm": 9.511617660522461,
      "learning_rate": 1.9994755690455154e-05,
      "loss": 2.2652,
      "step": 25
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 8.835038185119629,
      "learning_rate": 1.993582036030978e-05,
      "loss": 2.1412,
      "step": 30
    },
    {
      "epoch": 0.16203703703703703,
      "grad_norm": 7.89705228805542,
      "learning_rate": 1.9811781768982392e-05,
      "loss": 2.0107,
      "step": 35
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 6.195117473602295,
      "learning_rate": 1.9623452664340305e-05,
      "loss": 1.8743,
      "step": 40
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 4.751745700836182,
      "learning_rate": 1.937206705006344e-05,
      "loss": 1.8038,
      "step": 45
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 3.927769660949707,
      "learning_rate": 1.905927209998447e-05,
      "loss": 1.7567,
      "step": 50
    },
    {
      "epoch": 0.25462962962962965,
      "grad_norm": 4.062364101409912,
      "learning_rate": 1.8687117365181514e-05,
      "loss": 1.7709,
      "step": 55
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 2.570540189743042,
      "learning_rate": 1.8258041344542567e-05,
      "loss": 1.7229,
      "step": 60
    },
    {
      "epoch": 0.30092592592592593,
      "grad_norm": 1.9970929622650146,
      "learning_rate": 1.7774855506796497e-05,
      "loss": 1.7179,
      "step": 65
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 1.8299241065979004,
      "learning_rate": 1.7240725868704218e-05,
      "loss": 1.666,
      "step": 70
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 1.8000702857971191,
      "learning_rate": 1.665915225011681e-05,
      "loss": 1.6529,
      "step": 75
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.5835669040679932,
      "learning_rate": 1.603394534182925e-05,
      "loss": 1.6352,
      "step": 80
    },
    {
      "epoch": 0.39351851851851855,
      "grad_norm": 1.4376660585403442,
      "learning_rate": 1.536920173648984e-05,
      "loss": 1.6241,
      "step": 85
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 1.3085274696350098,
      "learning_rate": 1.4669277086172406e-05,
      "loss": 1.6178,
      "step": 90
    },
    {
      "epoch": 0.4398148148148148,
      "grad_norm": 1.3968168497085571,
      "learning_rate": 1.3938757562492873e-05,
      "loss": 1.6035,
      "step": 95
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 1.137740969657898,
      "learning_rate": 1.3182429806274442e-05,
      "loss": 1.5831,
      "step": 100
    },
    {
      "epoch": 0.46296296296296297,
      "eval_loss": 1.6092934608459473,
      "eval_runtime": 4.5262,
      "eval_samples_per_second": 172.332,
      "eval_steps_per_second": 5.523,
      "step": 100
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 1.4185782670974731,
      "learning_rate": 1.2405249563662539e-05,
      "loss": 1.5905,
      "step": 105
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 1.140097975730896,
      "learning_rate": 1.1612309214197599e-05,
      "loss": 1.5775,
      "step": 110
    },
    {
      "epoch": 0.5324074074074074,
      "grad_norm": 1.0888863801956177,
      "learning_rate": 1.0808804403614044e-05,
      "loss": 1.5804,
      "step": 115
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.0755336284637451,
      "learning_rate": 1e-05,
      "loss": 1.5582,
      "step": 120
    },
    {
      "epoch": 0.5787037037037037,
      "grad_norm": 2.2309999465942383,
      "learning_rate": 9.19119559638596e-06,
      "loss": 1.5673,
      "step": 125
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 1.0764739513397217,
      "learning_rate": 8.387690785802403e-06,
      "loss": 1.5524,
      "step": 130
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.9964112043380737,
      "learning_rate": 7.594750436337467e-06,
      "loss": 1.5419,
      "step": 135
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 1.22049880027771,
      "learning_rate": 6.8175701937255645e-06,
      "loss": 1.5623,
      "step": 140
    },
    {
      "epoch": 0.6712962962962963,
      "grad_norm": 1.0341013669967651,
      "learning_rate": 6.061242437507131e-06,
      "loss": 1.5363,
      "step": 145
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 1.0175600051879883,
      "learning_rate": 5.330722913827594e-06,
      "loss": 1.541,
      "step": 150
    },
    {
      "epoch": 0.7175925925925926,
      "grad_norm": 0.9816425442695618,
      "learning_rate": 4.630798263510162e-06,
      "loss": 1.5343,
      "step": 155
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.9579488039016724,
      "learning_rate": 3.966054658170754e-06,
      "loss": 1.5441,
      "step": 160
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 0.9483299851417542,
      "learning_rate": 3.3408477498831917e-06,
      "loss": 1.5334,
      "step": 165
    },
    {
      "epoch": 0.7870370370370371,
      "grad_norm": 0.9652431607246399,
      "learning_rate": 2.759274131295787e-06,
      "loss": 1.5286,
      "step": 170
    },
    {
      "epoch": 0.8101851851851852,
      "grad_norm": 0.9639863967895508,
      "learning_rate": 2.2251444932035094e-06,
      "loss": 1.5207,
      "step": 175
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.9372048377990723,
      "learning_rate": 1.7419586554574364e-06,
      "loss": 1.5318,
      "step": 180
    },
    {
      "epoch": 0.8564814814814815,
      "grad_norm": 0.938995897769928,
      "learning_rate": 1.3128826348184886e-06,
      "loss": 1.5329,
      "step": 185
    },
    {
      "epoch": 0.8796296296296297,
      "grad_norm": 0.9280312657356262,
      "learning_rate": 9.407279000155311e-07,
      "loss": 1.514,
      "step": 190
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 0.9297032952308655,
      "learning_rate": 6.279329499365649e-07,
      "loss": 1.5254,
      "step": 195
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.8736039400100708,
      "learning_rate": 3.7654733565969826e-07,
      "loss": 1.5043,
      "step": 200
    },
    {
      "epoch": 0.9259259259259259,
      "eval_loss": 1.530943751335144,
      "eval_runtime": 4.4836,
      "eval_samples_per_second": 173.966,
      "eval_steps_per_second": 5.576,
      "step": 200
    },
    {
      "epoch": 0.9490740740740741,
      "grad_norm": 0.9444804191589355,
      "learning_rate": 1.8821823101760949e-07,
      "loss": 1.5041,
      "step": 205
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 0.9190117716789246,
      "learning_rate": 6.417963969022389e-08,
      "loss": 1.5197,
      "step": 210
    },
    {
      "epoch": 0.9953703703703703,
      "grad_norm": 0.9011805653572083,
      "learning_rate": 5.2443095448506674e-09,
      "loss": 1.529,
      "step": 215
    },
    {
      "epoch": 1.0,
      "step": 216,
      "total_flos": 8.03524877305774e+16,
      "train_loss": 1.7498196733218652,
      "train_runtime": 326.8611,
      "train_samples_per_second": 42.278,
      "train_steps_per_second": 0.661
    }
  ],
  "logging_steps": 5,
  "max_steps": 216,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.03524877305774e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}