{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.023820867079561697,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009528346831824678,
      "grad_norm": 1.3314216136932373,
      "learning_rate": 1e-05,
      "loss": 2.8561,
      "step": 1
    },
    {
      "epoch": 0.0009528346831824678,
      "eval_loss": 3.010896921157837,
      "eval_runtime": 194.9161,
      "eval_samples_per_second": 4.535,
      "eval_steps_per_second": 0.569,
      "step": 1
    },
    {
      "epoch": 0.0019056693663649356,
      "grad_norm": 1.108765721321106,
      "learning_rate": 2e-05,
      "loss": 2.8611,
      "step": 2
    },
    {
      "epoch": 0.0028585040495474035,
      "grad_norm": 1.0992165803909302,
      "learning_rate": 3e-05,
      "loss": 2.958,
      "step": 3
    },
    {
      "epoch": 0.003811338732729871,
      "grad_norm": 0.9974603652954102,
      "learning_rate": 4e-05,
      "loss": 2.8721,
      "step": 4
    },
    {
      "epoch": 0.004764173415912339,
      "grad_norm": 1.0912249088287354,
      "learning_rate": 5e-05,
      "loss": 2.8375,
      "step": 5
    },
    {
      "epoch": 0.005717008099094807,
      "grad_norm": 1.070563793182373,
      "learning_rate": 6e-05,
      "loss": 2.7195,
      "step": 6
    },
    {
      "epoch": 0.006669842782277275,
      "grad_norm": 1.2317885160446167,
      "learning_rate": 7e-05,
      "loss": 2.816,
      "step": 7
    },
    {
      "epoch": 0.007622677465459742,
      "grad_norm": 1.3422398567199707,
      "learning_rate": 8e-05,
      "loss": 2.6737,
      "step": 8
    },
    {
      "epoch": 0.00857551214864221,
      "grad_norm": 1.3986526727676392,
      "learning_rate": 9e-05,
      "loss": 2.7706,
      "step": 9
    },
    {
      "epoch": 0.00857551214864221,
      "eval_loss": 2.8102166652679443,
      "eval_runtime": 195.3531,
      "eval_samples_per_second": 4.525,
      "eval_steps_per_second": 0.568,
      "step": 9
    },
    {
      "epoch": 0.009528346831824679,
      "grad_norm": 1.2939263582229614,
      "learning_rate": 0.0001,
      "loss": 2.8952,
      "step": 10
    },
    {
      "epoch": 0.010481181515007145,
      "grad_norm": 1.1111377477645874,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.7657,
      "step": 11
    },
    {
      "epoch": 0.011434016198189614,
      "grad_norm": 1.2477428913116455,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.4967,
      "step": 12
    },
    {
      "epoch": 0.012386850881372083,
      "grad_norm": 1.0746080875396729,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.359,
      "step": 13
    },
    {
      "epoch": 0.01333968556455455,
      "grad_norm": 1.6572176218032837,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.608,
      "step": 14
    },
    {
      "epoch": 0.014292520247737018,
      "grad_norm": 1.4233778715133667,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4839,
      "step": 15
    },
    {
      "epoch": 0.015245354930919485,
      "grad_norm": 1.346785306930542,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.4763,
      "step": 16
    },
    {
      "epoch": 0.016198189614101955,
      "grad_norm": 1.2152442932128906,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.428,
      "step": 17
    },
    {
      "epoch": 0.01715102429728442,
      "grad_norm": 1.0687611103057861,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.4665,
      "step": 18
    },
    {
      "epoch": 0.01715102429728442,
      "eval_loss": 2.5243494510650635,
      "eval_runtime": 195.3053,
      "eval_samples_per_second": 4.526,
      "eval_steps_per_second": 0.568,
      "step": 18
    },
    {
      "epoch": 0.01810385898046689,
      "grad_norm": 1.1508054733276367,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3153,
      "step": 19
    },
    {
      "epoch": 0.019056693663649357,
      "grad_norm": 1.267975091934204,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.4924,
      "step": 20
    },
    {
      "epoch": 0.020009528346831826,
      "grad_norm": 1.2117677927017212,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.4421,
      "step": 21
    },
    {
      "epoch": 0.02096236303001429,
      "grad_norm": 1.7183105945587158,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.6475,
      "step": 22
    },
    {
      "epoch": 0.02191519771319676,
      "grad_norm": 1.2931954860687256,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.0165,
      "step": 23
    },
    {
      "epoch": 0.022868032396379228,
      "grad_norm": 1.4074746370315552,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.8582,
      "step": 24
    },
    {
      "epoch": 0.023820867079561697,
      "grad_norm": 1.149705410003662,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.2325,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.70943641780224e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}