{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 13.654970760233919,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 2.111288547515869,
      "learning_rate": 4.997482666353287e-05,
      "loss": 1.3663,
      "num_input_tokens_seen": 63680,
      "step": 10
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 0.9560565948486328,
      "learning_rate": 4.988787280635038e-05,
      "loss": 0.1793,
      "num_input_tokens_seen": 127456,
      "step": 20
    },
    {
      "epoch": 1.3742690058479532,
      "grad_norm": 0.4774836599826813,
      "learning_rate": 4.973904377598443e-05,
      "loss": 0.1703,
      "num_input_tokens_seen": 187344,
      "step": 30
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 0.5011305809020996,
      "learning_rate": 4.952870958485432e-05,
      "loss": 0.1523,
      "num_input_tokens_seen": 250096,
      "step": 40
    },
    {
      "epoch": 2.280701754385965,
      "grad_norm": 0.7100902795791626,
      "learning_rate": 4.925739315689991e-05,
      "loss": 0.1379,
      "num_input_tokens_seen": 309944,
      "step": 50
    },
    {
      "epoch": 2.7485380116959064,
      "grad_norm": 0.9586629867553711,
      "learning_rate": 4.892576902751031e-05,
      "loss": 0.1148,
      "num_input_tokens_seen": 373928,
      "step": 60
    },
    {
      "epoch": 3.1871345029239766,
      "grad_norm": 0.4181136190891266,
      "learning_rate": 4.8534661666522584e-05,
      "loss": 0.095,
      "num_input_tokens_seen": 432904,
      "step": 70
    },
    {
      "epoch": 3.654970760233918,
      "grad_norm": 0.349086731672287,
      "learning_rate": 4.808504342845986e-05,
      "loss": 0.0974,
      "num_input_tokens_seen": 495944,
      "step": 80
    },
    {
      "epoch": 4.093567251461988,
      "grad_norm": 0.45979073643684387,
      "learning_rate": 4.7578032135104796e-05,
      "loss": 0.0904,
      "num_input_tokens_seen": 556408,
      "step": 90
    },
    {
      "epoch": 4.56140350877193,
      "grad_norm": 0.5125895142555237,
      "learning_rate": 4.701488829641845e-05,
      "loss": 0.0845,
      "num_input_tokens_seen": 619608,
      "step": 100
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5893365144729614,
      "learning_rate": 4.639701197671397e-05,
      "loss": 0.0888,
      "num_input_tokens_seen": 679200,
      "step": 110
    },
    {
      "epoch": 5.4678362573099415,
      "grad_norm": 0.4436362683773041,
      "learning_rate": 4.572593931387604e-05,
      "loss": 0.0783,
      "num_input_tokens_seen": 743424,
      "step": 120
    },
    {
      "epoch": 5.935672514619883,
      "grad_norm": 0.7025277018547058,
      "learning_rate": 4.500333870028016e-05,
      "loss": 0.0786,
      "num_input_tokens_seen": 806384,
      "step": 130
    },
    {
      "epoch": 6.374269005847953,
      "grad_norm": 0.4325951039791107,
      "learning_rate": 4.4231006634906224e-05,
      "loss": 0.071,
      "num_input_tokens_seen": 866528,
      "step": 140
    },
    {
      "epoch": 6.842105263157895,
      "grad_norm": 0.5969815254211426,
      "learning_rate": 4.341086325695905e-05,
      "loss": 0.0677,
      "num_input_tokens_seen": 929744,
      "step": 150
    },
    {
      "epoch": 7.280701754385965,
      "grad_norm": 0.5520203709602356,
      "learning_rate": 4.254494757209979e-05,
      "loss": 0.0609,
      "num_input_tokens_seen": 989904,
      "step": 160
    },
    {
      "epoch": 7.748538011695906,
      "grad_norm": 0.5631939172744751,
      "learning_rate": 4.163541238315653e-05,
      "loss": 0.0669,
      "num_input_tokens_seen": 1053440,
      "step": 170
    },
    {
      "epoch": 8.187134502923977,
      "grad_norm": 0.39443930983543396,
      "learning_rate": 4.0684518937917315e-05,
      "loss": 0.0627,
      "num_input_tokens_seen": 1112544,
      "step": 180
    },
    {
      "epoch": 8.654970760233919,
      "grad_norm": 0.3650754988193512,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.0571,
      "num_input_tokens_seen": 1176672,
      "step": 190
    },
    {
      "epoch": 9.093567251461987,
      "grad_norm": 0.4774751365184784,
      "learning_rate": 3.866821050795859e-05,
      "loss": 0.0585,
      "num_input_tokens_seen": 1236216,
      "step": 200
    },
    {
      "epoch": 9.56140350877193,
      "grad_norm": 0.4063754677772522,
      "learning_rate": 3.7607808383689856e-05,
      "loss": 0.0553,
      "num_input_tokens_seen": 1299928,
      "step": 210
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.6216735243797302,
      "learning_rate": 3.651606126126581e-05,
      "loss": 0.0559,
      "num_input_tokens_seen": 1359344,
      "step": 220
    },
    {
      "epoch": 10.46783625730994,
      "grad_norm": 0.3396362364292145,
      "learning_rate": 3.5395683396050825e-05,
      "loss": 0.0543,
      "num_input_tokens_seen": 1422304,
      "step": 230
    },
    {
      "epoch": 10.935672514619883,
      "grad_norm": 0.37560704350471497,
      "learning_rate": 3.4249460223946975e-05,
      "loss": 0.0541,
      "num_input_tokens_seen": 1486624,
      "step": 240
    },
    {
      "epoch": 11.374269005847953,
      "grad_norm": 0.38224905729293823,
      "learning_rate": 3.3080241436361506e-05,
      "loss": 0.052,
      "num_input_tokens_seen": 1545648,
      "step": 250
    },
    {
      "epoch": 11.842105263157894,
      "grad_norm": 0.42291998863220215,
      "learning_rate": 3.1890933895424976e-05,
      "loss": 0.0454,
      "num_input_tokens_seen": 1610448,
      "step": 260
    },
    {
      "epoch": 12.280701754385966,
      "grad_norm": 0.5299489498138428,
      "learning_rate": 3.068449440707404e-05,
      "loss": 0.0493,
      "num_input_tokens_seen": 1668864,
      "step": 270
    },
    {
      "epoch": 12.748538011695906,
      "grad_norm": 0.45459693670272827,
      "learning_rate": 2.9463922369965917e-05,
      "loss": 0.0473,
      "num_input_tokens_seen": 1732048,
      "step": 280
    },
    {
      "epoch": 13.187134502923977,
      "grad_norm": 0.454479455947876,
      "learning_rate": 2.8232252318500834e-05,
      "loss": 0.0498,
      "num_input_tokens_seen": 1791864,
      "step": 290
    },
    {
      "epoch": 13.654970760233919,
      "grad_norm": 0.40513795614242554,
      "learning_rate": 2.6992546378491318e-05,
      "loss": 0.047,
      "num_input_tokens_seen": 1855496,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 630,
  "num_input_tokens_seen": 1855496,
  "num_train_epochs": 30,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.962975855129395e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}