{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.986666666666667,
  "eval_steps": 500,
  "global_step": 336,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.43254968523979187,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.2512,
      "step": 10
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.24992488324642181,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.0734,
      "step": 20
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.27158254384994507,
      "learning_rate": 8.823529411764706e-05,
      "loss": 0.088,
      "step": 30
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.4510670006275177,
      "learning_rate": 9.990263847374976e-05,
      "loss": 0.0807,
      "step": 40
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.30015143752098083,
      "learning_rate": 9.930902394260747e-05,
      "loss": 0.0409,
      "step": 50
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.5191588401794434,
      "learning_rate": 9.818229479678158e-05,
      "loss": 0.0688,
      "step": 60
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.2607024013996124,
      "learning_rate": 9.653463289927411e-05,
      "loss": 0.0957,
      "step": 70
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.6277446150779724,
      "learning_rate": 9.438385228425938e-05,
      "loss": 0.0597,
      "step": 80
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7519625425338745,
      "learning_rate": 9.175320655700406e-05,
      "loss": 0.0597,
      "step": 90
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.4900517463684082,
      "learning_rate": 8.86711374827494e-05,
      "loss": 0.0873,
      "step": 100
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.30556386709213257,
      "learning_rate": 8.517096748273951e-05,
      "loss": 0.081,
      "step": 110
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.36547404527664185,
      "learning_rate": 8.129053936203687e-05,
      "loss": 0.0815,
      "step": 120
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 0.13520216941833496,
      "learning_rate": 7.707180716428237e-05,
      "loss": 0.0279,
      "step": 130
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 0.15246033668518066,
      "learning_rate": 7.256038257695687e-05,
      "loss": 0.0281,
      "step": 140
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.29794782400131226,
      "learning_rate": 6.780504179127734e-05,
      "loss": 0.0337,
      "step": 150
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.21146634221076965,
      "learning_rate": 6.28571981484123e-05,
      "loss": 0.0279,
      "step": 160
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 0.2917829751968384,
      "learning_rate": 5.7770346273610254e-05,
      "loss": 0.038,
      "step": 170
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.20041967928409576,
      "learning_rate": 5.2599483708099016e-05,
      "loss": 0.0277,
      "step": 180
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 0.17946018278598785,
      "learning_rate": 4.740051629190099e-05,
      "loss": 0.0274,
      "step": 190
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.24175235629081726,
      "learning_rate": 4.2229653726389765e-05,
      "loss": 0.0213,
      "step": 200
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.0971062108874321,
      "learning_rate": 3.714280185158771e-05,
      "loss": 0.0229,
      "step": 210
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 0.11246433854103088,
      "learning_rate": 3.219495820872265e-05,
      "loss": 0.0241,
      "step": 220
    },
    {
      "epoch": 2.0444444444444443,
      "grad_norm": 0.33047017455101013,
      "learning_rate": 2.7439617423043145e-05,
      "loss": 0.033,
      "step": 230
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.3295614719390869,
      "learning_rate": 2.2928192835717644e-05,
      "loss": 0.0076,
      "step": 240
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.058611124753952026,
      "learning_rate": 1.8709460637963123e-05,
      "loss": 0.0089,
      "step": 250
    },
    {
      "epoch": 2.311111111111111,
      "grad_norm": 0.13072353601455688,
      "learning_rate": 1.4829032517260489e-05,
      "loss": 0.0099,
      "step": 260
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.033569373190402985,
      "learning_rate": 1.132886251725061e-05,
      "loss": 0.0116,
      "step": 270
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.4310339689254761,
      "learning_rate": 8.246793442995954e-06,
      "loss": 0.0084,
      "step": 280
    },
    {
      "epoch": 2.5777777777777775,
      "grad_norm": 0.13345347344875336,
      "learning_rate": 5.616147715740611e-06,
      "loss": 0.0116,
      "step": 290
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.2788897752761841,
      "learning_rate": 3.465367100725908e-06,
      "loss": 0.0099,
      "step": 300
    },
    {
      "epoch": 2.7555555555555555,
      "grad_norm": 0.15625333786010742,
      "learning_rate": 1.8177052032184283e-06,
      "loss": 0.0089,
      "step": 310
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.31957411766052246,
      "learning_rate": 6.909760573925561e-07,
      "loss": 0.0072,
      "step": 320
    },
    {
      "epoch": 2.9333333333333336,
      "grad_norm": 0.21593359112739563,
      "learning_rate": 9.73615262502503e-08,
      "loss": 0.0072,
      "step": 330
    },
    {
      "epoch": 2.986666666666667,
      "step": 336,
      "total_flos": 5.092948553918054e+16,
      "train_loss": 0.043967162702409995,
      "train_runtime": 9286.9063,
      "train_samples_per_second": 0.291,
      "train_steps_per_second": 0.036
    }
  ],
  "logging_steps": 10,
  "max_steps": 336,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.092948553918054e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}