{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.13778256189451,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0861141011840689,
      "grad_norm": 21.438983917236328,
      "learning_rate": 6.749999999999999e-06,
      "loss": 5.3584,
      "num_input_tokens_seen": 106432,
      "step": 10,
      "train_runtime": 108.6693,
      "train_tokens_per_second": 979.412
    },
    {
      "epoch": 0.1722282023681378,
      "grad_norm": 8.519647598266602,
      "learning_rate": 1.4249999999999999e-05,
      "loss": 4.8538,
      "num_input_tokens_seen": 213216,
      "step": 20,
      "train_runtime": 186.9434,
      "train_tokens_per_second": 1140.538
    },
    {
      "epoch": 0.25834230355220666,
      "grad_norm": 18.737985610961914,
      "learning_rate": 2.1749999999999997e-05,
      "loss": 3.6236,
      "num_input_tokens_seen": 319264,
      "step": 30,
      "train_runtime": 265.2215,
      "train_tokens_per_second": 1203.763
    },
    {
      "epoch": 0.3444564047362756,
      "grad_norm": 4.311729431152344,
      "learning_rate": 2.925e-05,
      "loss": 2.4654,
      "num_input_tokens_seen": 426464,
      "step": 40,
      "train_runtime": 343.9109,
      "train_tokens_per_second": 1240.042
    },
    {
      "epoch": 0.43057050592034446,
      "grad_norm": 2.5902934074401855,
      "learning_rate": 3.675e-05,
      "loss": 2.0086,
      "num_input_tokens_seen": 532576,
      "step": 50,
      "train_runtime": 421.9835,
      "train_tokens_per_second": 1262.078
    },
    {
      "epoch": 0.5166846071044133,
      "grad_norm": 3.0768535137176514,
      "learning_rate": 4.424999999999999e-05,
      "loss": 1.878,
      "num_input_tokens_seen": 639584,
      "step": 60,
      "train_runtime": 500.5067,
      "train_tokens_per_second": 1277.873
    },
    {
      "epoch": 0.6027987082884823,
      "grad_norm": 2.4493396282196045,
      "learning_rate": 5.174999999999999e-05,
      "loss": 1.8546,
      "num_input_tokens_seen": 747360,
      "step": 70,
      "train_runtime": 579.1392,
      "train_tokens_per_second": 1290.467
    },
    {
      "epoch": 0.6889128094725512,
      "grad_norm": 2.146406650543213,
      "learning_rate": 5.925e-05,
      "loss": 1.8364,
      "num_input_tokens_seen": 854304,
      "step": 80,
      "train_runtime": 657.8931,
      "train_tokens_per_second": 1298.545
    },
    {
      "epoch": 0.77502691065662,
      "grad_norm": 2.2075250148773193,
      "learning_rate": 6.675e-05,
      "loss": 1.8027,
      "num_input_tokens_seen": 962816,
      "step": 90,
      "train_runtime": 737.8649,
      "train_tokens_per_second": 1304.868
    },
    {
      "epoch": 0.8611410118406889,
      "grad_norm": 0.9837085008621216,
      "learning_rate": 7.424999999999999e-05,
      "loss": 1.7782,
      "num_input_tokens_seen": 1070240,
      "step": 100,
      "train_runtime": 817.3738,
      "train_tokens_per_second": 1309.364
    },
    {
      "epoch": 0.9472551130247578,
      "grad_norm": 3.0224859714508057,
      "learning_rate": 8.175e-05,
      "loss": 1.7681,
      "num_input_tokens_seen": 1175840,
      "step": 110,
      "train_runtime": 895.639,
      "train_tokens_per_second": 1312.85
    },
    {
      "epoch": 1.0258342303552206,
      "grad_norm": 1.015479326248169,
      "learning_rate": 8.924999999999999e-05,
      "loss": 1.5944,
      "num_input_tokens_seen": 1273184,
      "step": 120,
      "train_runtime": 967.2081,
      "train_tokens_per_second": 1316.35
    },
    {
      "epoch": 1.1119483315392895,
      "grad_norm": 1.2177729606628418,
      "learning_rate": 9.675e-05,
      "loss": 1.7489,
      "num_input_tokens_seen": 1380480,
      "step": 130,
      "train_runtime": 1045.876,
      "train_tokens_per_second": 1319.927
    },
    {
      "epoch": 1.1980624327233584,
      "grad_norm": 1.6441470384597778,
      "learning_rate": 0.00010424999999999999,
      "loss": 1.7265,
      "num_input_tokens_seen": 1487520,
      "step": 140,
      "train_runtime": 1124.3621,
      "train_tokens_per_second": 1322.99
    },
    {
      "epoch": 1.2841765339074274,
      "grad_norm": 1.1657848358154297,
      "learning_rate": 0.00011174999999999999,
      "loss": 1.7386,
      "num_input_tokens_seen": 1593472,
      "step": 150,
      "train_runtime": 1202.4025,
      "train_tokens_per_second": 1325.24
    },
    {
      "epoch": 1.3702906350914963,
      "grad_norm": 1.1126108169555664,
      "learning_rate": 0.00011925,
      "loss": 1.7229,
      "num_input_tokens_seen": 1700288,
      "step": 160,
      "train_runtime": 1280.6844,
      "train_tokens_per_second": 1327.64
    },
    {
      "epoch": 1.456404736275565,
      "grad_norm": 1.3799711465835571,
      "learning_rate": 0.00012675,
      "loss": 1.7513,
      "num_input_tokens_seen": 1807488,
      "step": 170,
      "train_runtime": 1359.2569,
      "train_tokens_per_second": 1329.762
    },
    {
      "epoch": 1.542518837459634,
      "grad_norm": 1.2127066850662231,
      "learning_rate": 0.00013424999999999998,
      "loss": 1.7105,
      "num_input_tokens_seen": 1914272,
      "step": 180,
      "train_runtime": 1437.7985,
      "train_tokens_per_second": 1331.391
    },
    {
      "epoch": 1.6286329386437028,
      "grad_norm": 1.4629660844802856,
      "learning_rate": 0.00014174999999999998,
      "loss": 1.7081,
      "num_input_tokens_seen": 2019584,
      "step": 190,
      "train_runtime": 1515.7685,
      "train_tokens_per_second": 1332.383
    },
    {
      "epoch": 1.7147470398277718,
      "grad_norm": 0.9486769437789917,
      "learning_rate": 0.00014925,
      "loss": 1.7133,
      "num_input_tokens_seen": 2126016,
      "step": 200,
      "train_runtime": 1593.9754,
      "train_tokens_per_second": 1333.782
    },
    {
      "epoch": 1.8008611410118407,
      "grad_norm": 1.6725178956985474,
      "learning_rate": 0.00014992177254124345,
      "loss": 1.7217,
      "num_input_tokens_seen": 2233824,
      "step": 210,
      "train_runtime": 1672.6238,
      "train_tokens_per_second": 1335.521
    },
    {
      "epoch": 1.8869752421959096,
      "grad_norm": 1.5028326511383057,
      "learning_rate": 0.00014965156613602355,
      "loss": 1.7094,
      "num_input_tokens_seen": 2341536,
      "step": 220,
      "train_runtime": 1751.4804,
      "train_tokens_per_second": 1336.89
    },
    {
      "epoch": 1.9730893433799785,
      "grad_norm": 1.0816280841827393,
      "learning_rate": 0.0001491891107057639,
      "loss": 1.7178,
      "num_input_tokens_seen": 2447072,
      "step": 230,
      "train_runtime": 1829.8444,
      "train_tokens_per_second": 1337.312
    },
    {
      "epoch": 2.051668460710441,
      "grad_norm": 0.8403604030609131,
      "learning_rate": 0.00014853559720478995,
      "loss": 1.5203,
      "num_input_tokens_seen": 2544928,
      "step": 240,
      "train_runtime": 1901.5872,
      "train_tokens_per_second": 1338.318
    },
    {
      "epoch": 2.13778256189451,
      "grad_norm": 0.805606484413147,
      "learning_rate": 0.00014769270861632517,
      "loss": 1.684,
      "num_input_tokens_seen": 2652064,
      "step": 250,
      "train_runtime": 1980.3904,
      "train_tokens_per_second": 1339.162
    }
  ],
  "logging_steps": 10,
  "max_steps": 819,
  "num_input_tokens_seen": 2652064,
  "num_train_epochs": 7,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7835336666929664e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}