{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 246,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04065040650406504,
      "grad_norm": 14.707608222961426,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.9613,
      "step": 10
    },
    {
      "epoch": 0.08130081300813008,
      "grad_norm": 12.035386085510254,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.8509,
      "step": 20
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 18.44657325744629,
      "learning_rate": 2.9e-06,
      "loss": 0.9369,
      "step": 30
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 12.941998481750488,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.896,
      "step": 40
    },
    {
      "epoch": 0.2032520325203252,
      "grad_norm": 15.150432586669922,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.9821,
      "step": 50
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 18.638032913208008,
      "learning_rate": 5.9e-06,
      "loss": 0.9666,
      "step": 60
    },
    {
      "epoch": 0.2845528455284553,
      "grad_norm": 15.954939842224121,
      "learning_rate": 6.9e-06,
      "loss": 0.9019,
      "step": 70
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 11.114273071289062,
      "learning_rate": 7.9e-06,
      "loss": 0.8321,
      "step": 80
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 15.285880088806152,
      "learning_rate": 8.900000000000001e-06,
      "loss": 0.7198,
      "step": 90
    },
    {
      "epoch": 0.4065040650406504,
      "grad_norm": 17.8586483001709,
      "learning_rate": 9.9e-06,
      "loss": 0.7806,
      "step": 100
    },
    {
      "epoch": 0.44715447154471544,
      "grad_norm": 11.217978477478027,
      "learning_rate": 9.961864406779662e-06,
      "loss": 1.0024,
      "step": 110
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 7.002477169036865,
      "learning_rate": 9.91949152542373e-06,
      "loss": 0.8086,
      "step": 120
    },
    {
      "epoch": 0.5284552845528455,
      "grad_norm": 13.211562156677246,
      "learning_rate": 9.877118644067798e-06,
      "loss": 0.8958,
      "step": 130
    },
    {
      "epoch": 0.5691056910569106,
      "grad_norm": 11.169763565063477,
      "learning_rate": 9.834745762711865e-06,
      "loss": 0.8316,
      "step": 140
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 15.369425773620605,
      "learning_rate": 9.792372881355933e-06,
      "loss": 0.675,
      "step": 150
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 11.003032684326172,
      "learning_rate": 9.75e-06,
      "loss": 0.7512,
      "step": 160
    },
    {
      "epoch": 0.6910569105691057,
      "grad_norm": 16.466957092285156,
      "learning_rate": 9.707627118644068e-06,
      "loss": 0.8546,
      "step": 170
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 13.067832946777344,
      "learning_rate": 9.665254237288136e-06,
      "loss": 0.7497,
      "step": 180
    },
    {
      "epoch": 0.7723577235772358,
      "grad_norm": 9.530882835388184,
      "learning_rate": 9.622881355932205e-06,
      "loss": 0.6136,
      "step": 190
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 15.063409805297852,
      "learning_rate": 9.580508474576273e-06,
      "loss": 0.6073,
      "step": 200
    },
    {
      "epoch": 0.8536585365853658,
      "grad_norm": 9.07528305053711,
      "learning_rate": 9.53813559322034e-06,
      "loss": 0.7295,
      "step": 210
    },
    {
      "epoch": 0.8943089430894309,
      "grad_norm": 14.199564933776855,
      "learning_rate": 9.495762711864408e-06,
      "loss": 0.596,
      "step": 220
    },
    {
      "epoch": 0.9349593495934959,
      "grad_norm": 16.03732681274414,
      "learning_rate": 9.453389830508474e-06,
      "loss": 0.6922,
      "step": 230
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 17.533695220947266,
      "learning_rate": 9.411016949152543e-06,
      "loss": 0.7484,
      "step": 240
    },
    {
      "epoch": 1.0,
      "eval_general_loss": 0.754059910774231,
      "eval_general_runtime": 254.3068,
      "eval_general_samples_per_second": 3.598,
      "eval_general_steps_per_second": 0.9,
      "step": 246
    },
    {
      "epoch": 1.0,
      "eval_code_loss": 0.7234187722206116,
      "eval_code_runtime": 296.8568,
      "eval_code_samples_per_second": 3.092,
      "eval_code_steps_per_second": 0.775,
      "step": 246
    },
    {
      "epoch": 1.0,
      "eval_stem_loss": 0.7939386367797852,
      "eval_stem_runtime": 250.6578,
      "eval_stem_samples_per_second": 3.646,
      "eval_stem_steps_per_second": 0.914,
      "step": 246
    }
  ],
  "logging_steps": 10,
  "max_steps": 2460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.083912914835866e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}