{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.852216748768473,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19704433497536947,
      "grad_norm": 0.90673828125,
      "learning_rate": 0.00019980267284282717,
      "loss": 1.6839,
      "step": 10
    },
    {
      "epoch": 0.39408866995073893,
      "grad_norm": 0.7666015625,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.3775,
      "step": 20
    },
    {
      "epoch": 0.5911330049261084,
      "grad_norm": 1.26171875,
      "learning_rate": 0.0001982287250728689,
      "loss": 1.2362,
      "step": 30
    },
    {
      "epoch": 0.7881773399014779,
      "grad_norm": 0.51904296875,
      "learning_rate": 0.0001968583161128631,
      "loss": 1.1045,
      "step": 40
    },
    {
      "epoch": 0.9852216748768473,
      "grad_norm": 0.457763671875,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.0098,
      "step": 50
    },
    {
      "epoch": 1.1822660098522166,
      "grad_norm": 0.378173828125,
      "learning_rate": 0.00019297764858882514,
      "loss": 0.9158,
      "step": 60
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 0.385009765625,
      "learning_rate": 0.00019048270524660196,
      "loss": 0.8679,
      "step": 70
    },
    {
      "epoch": 1.5763546798029555,
      "grad_norm": 0.436279296875,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.8699,
      "step": 80
    },
    {
      "epoch": 1.7733990147783252,
      "grad_norm": 0.358154296875,
      "learning_rate": 0.00018443279255020152,
      "loss": 0.8928,
      "step": 90
    },
    {
      "epoch": 1.9704433497536946,
      "grad_norm": 0.353515625,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.8451,
      "step": 100
    },
    {
      "epoch": 2.167487684729064,
      "grad_norm": 0.344482421875,
      "learning_rate": 0.00017705132427757895,
      "loss": 0.8518,
      "step": 110
    },
    {
      "epoch": 2.3645320197044333,
      "grad_norm": 0.3330078125,
      "learning_rate": 0.00017289686274214118,
      "loss": 0.834,
      "step": 120
    },
    {
      "epoch": 2.561576354679803,
      "grad_norm": 0.33935546875,
      "learning_rate": 0.00016845471059286887,
      "loss": 0.8082,
      "step": 130
    },
    {
      "epoch": 2.7586206896551726,
      "grad_norm": 0.381103515625,
      "learning_rate": 0.000163742398974869,
      "loss": 0.8103,
      "step": 140
    },
    {
      "epoch": 2.955665024630542,
      "grad_norm": 0.371826171875,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.8405,
      "step": 150
    },
    {
      "epoch": 3.1527093596059115,
      "grad_norm": 0.4560546875,
      "learning_rate": 0.00015358267949789966,
      "loss": 0.8076,
      "step": 160
    },
    {
      "epoch": 3.3497536945812807,
      "grad_norm": 0.497314453125,
      "learning_rate": 0.00014817536741017152,
      "loss": 0.8112,
      "step": 170
    },
    {
      "epoch": 3.5467980295566504,
      "grad_norm": 0.3759765625,
      "learning_rate": 0.00014257792915650728,
      "loss": 0.7933,
      "step": 180
    },
    {
      "epoch": 3.7438423645320196,
      "grad_norm": 0.396484375,
      "learning_rate": 0.00013681245526846783,
      "loss": 0.7877,
      "step": 190
    },
    {
      "epoch": 3.9408866995073892,
      "grad_norm": 0.421630859375,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.8012,
      "step": 200
    },
    {
      "epoch": 4.137931034482759,
      "grad_norm": 0.4208984375,
      "learning_rate": 0.0001248689887164855,
      "loss": 0.799,
      "step": 210
    },
    {
      "epoch": 4.334975369458128,
      "grad_norm": 0.377685546875,
      "learning_rate": 0.00011873813145857249,
      "loss": 0.7942,
      "step": 220
    },
    {
      "epoch": 4.532019704433497,
      "grad_norm": 0.52880859375,
      "learning_rate": 0.00011253332335643043,
      "loss": 0.7658,
      "step": 230
    },
    {
      "epoch": 4.7290640394088665,
      "grad_norm": 0.462890625,
      "learning_rate": 0.00010627905195293135,
      "loss": 0.7761,
      "step": 240
    },
    {
      "epoch": 4.926108374384237,
      "grad_norm": 0.54638671875,
      "learning_rate": 0.0001,
      "loss": 0.789,
      "step": 250
    },
    {
      "epoch": 5.123152709359606,
      "grad_norm": 0.42822265625,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.7697,
      "step": 260
    },
    {
      "epoch": 5.320197044334975,
      "grad_norm": 0.4482421875,
      "learning_rate": 8.746667664356956e-05,
      "loss": 0.7713,
      "step": 270
    },
    {
      "epoch": 5.517241379310345,
      "grad_norm": 0.45361328125,
      "learning_rate": 8.126186854142752e-05,
      "loss": 0.7812,
      "step": 280
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 0.4521484375,
      "learning_rate": 7.513101128351454e-05,
      "loss": 0.7549,
      "step": 290
    },
    {
      "epoch": 5.911330049261084,
      "grad_norm": 0.45703125,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.7387,
      "step": 300
    },
    {
      "epoch": 6.108374384236453,
      "grad_norm": 0.433837890625,
      "learning_rate": 6.318754473153221e-05,
      "loss": 0.759,
      "step": 310
    },
    {
      "epoch": 6.305418719211823,
      "grad_norm": 0.492431640625,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.7572,
      "step": 320
    },
    {
      "epoch": 6.502463054187192,
      "grad_norm": 0.45068359375,
      "learning_rate": 5.182463258982846e-05,
      "loss": 0.7507,
      "step": 330
    },
    {
      "epoch": 6.699507389162561,
      "grad_norm": 0.476806640625,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 0.7483,
      "step": 340
    },
    {
      "epoch": 6.896551724137931,
      "grad_norm": 0.464599609375,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.7618,
      "step": 350
    },
    {
      "epoch": 7.093596059113301,
      "grad_norm": 0.44970703125,
      "learning_rate": 3.6257601025131026e-05,
      "loss": 0.7294,
      "step": 360
    },
    {
      "epoch": 7.29064039408867,
      "grad_norm": 0.50390625,
      "learning_rate": 3.154528940713113e-05,
      "loss": 0.7575,
      "step": 370
    },
    {
      "epoch": 7.487684729064039,
      "grad_norm": 0.45751953125,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.7349,
      "step": 380
    },
    {
      "epoch": 7.684729064039409,
      "grad_norm": 0.51123046875,
      "learning_rate": 2.2948675722421086e-05,
      "loss": 0.7431,
      "step": 390
    },
    {
      "epoch": 7.8817733990147785,
      "grad_norm": 0.442138671875,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.7429,
      "step": 400
    },
    {
      "epoch": 8.078817733990148,
      "grad_norm": 0.4794921875,
      "learning_rate": 1.5567207449798515e-05,
      "loss": 0.7386,
      "step": 410
    },
    {
      "epoch": 8.275862068965518,
      "grad_norm": 0.49609375,
      "learning_rate": 1.2369331995613665e-05,
      "loss": 0.7209,
      "step": 420
    },
    {
      "epoch": 8.472906403940886,
      "grad_norm": 0.453369140625,
      "learning_rate": 9.517294753398064e-06,
      "loss": 0.7379,
      "step": 430
    },
    {
      "epoch": 8.669950738916256,
      "grad_norm": 0.461181640625,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.7192,
      "step": 440
    },
    {
      "epoch": 8.866995073891626,
      "grad_norm": 0.4892578125,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.7553,
      "step": 450
    },
    {
      "epoch": 9.064039408866995,
      "grad_norm": 0.52685546875,
      "learning_rate": 3.1416838871368924e-06,
      "loss": 0.7381,
      "step": 460
    },
    {
      "epoch": 9.261083743842365,
      "grad_norm": 0.490234375,
      "learning_rate": 1.771274927131139e-06,
      "loss": 0.733,
      "step": 470
    },
    {
      "epoch": 9.458128078817733,
      "grad_norm": 0.46240234375,
      "learning_rate": 7.885298685522235e-07,
      "loss": 0.7257,
      "step": 480
    },
    {
      "epoch": 9.655172413793103,
      "grad_norm": 0.5029296875,
      "learning_rate": 1.973271571728441e-07,
      "loss": 0.7418,
      "step": 490
    },
    {
      "epoch": 9.852216748768473,
      "grad_norm": 0.447021484375,
      "learning_rate": 0.0,
      "loss": 0.7347,
      "step": 500
    },
    {
      "epoch": 9.852216748768473,
      "step": 500,
      "total_flos": 2.4398694187008e+16,
      "train_loss": 0.8303789939880372,
      "train_runtime": 437.9863,
      "train_samples_per_second": 4.635,
      "train_steps_per_second": 1.142
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 2.4398694187008e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}