{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.802937576499388,
  "eval_steps": 500,
  "global_step": 328,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02447980416156671,
      "grad_norm": 6.0,
      "learning_rate": 4.5e-07,
      "loss": 2.0334224700927734,
      "step": 10
    },
    {
      "epoch": 0.04895960832313342,
      "grad_norm": 4.9375,
      "learning_rate": 4.990124606538042e-07,
      "loss": 2.123665428161621,
      "step": 20
    },
    {
      "epoch": 0.07343941248470012,
      "grad_norm": 13.875,
      "learning_rate": 4.956087596148824e-07,
      "loss": 2.0373281478881835,
      "step": 30
    },
    {
      "epoch": 0.09791921664626684,
      "grad_norm": 12.3125,
      "learning_rate": 4.898098898861766e-07,
      "loss": 2.0780839920043945,
      "step": 40
    },
    {
      "epoch": 0.12239902080783353,
      "grad_norm": 11.6875,
      "learning_rate": 4.816724018579583e-07,
      "loss": 2.168250846862793,
      "step": 50
    },
    {
      "epoch": 0.14687882496940025,
      "grad_norm": 27.5,
      "learning_rate": 4.7127565205061093e-07,
      "loss": 2.0774251937866213,
      "step": 60
    },
    {
      "epoch": 0.17135862913096694,
      "grad_norm": 14.6875,
      "learning_rate": 4.587210292324061e-07,
      "loss": 2.2656288146972656,
      "step": 70
    },
    {
      "epoch": 0.19583843329253367,
      "grad_norm": 13.3125,
      "learning_rate": 4.441309656795106e-07,
      "loss": 1.990157699584961,
      "step": 80
    },
    {
      "epoch": 0.22031823745410037,
      "grad_norm": 5.3125,
      "learning_rate": 4.2764774322038486e-07,
      "loss": 2.2658514022827148,
      "step": 90
    },
    {
      "epoch": 0.24479804161566707,
      "grad_norm": 24.375,
      "learning_rate": 4.094321057079873e-07,
      "loss": 2.0881725311279298,
      "step": 100
    },
    {
      "epoch": 0.2692778457772338,
      "grad_norm": 5.5625,
      "learning_rate": 3.896616914509131e-07,
      "loss": 2.186654281616211,
      "step": 110
    },
    {
      "epoch": 0.2937576499388005,
      "grad_norm": 15.5,
      "learning_rate": 3.6852930089034707e-07,
      "loss": 2.238821601867676,
      "step": 120
    },
    {
      "epoch": 0.3182374541003672,
      "grad_norm": 14.1875,
      "learning_rate": 3.4624101641638926e-07,
      "loss": 2.05932559967041,
      "step": 130
    },
    {
      "epoch": 0.3427172582619339,
      "grad_norm": 10.875,
      "learning_rate": 3.2301419265924393e-07,
      "loss": 2.070750617980957,
      "step": 140
    },
    {
      "epoch": 0.3671970624235006,
      "grad_norm": 10.75,
      "learning_rate": 2.9907533685388716e-07,
      "loss": 2.12088565826416,
      "step": 150
    },
    {
      "epoch": 0.39167686658506734,
      "grad_norm": 5.15625,
      "learning_rate": 2.7465789994882794e-07,
      "loss": 1.9712303161621094,
      "step": 160
    },
    {
      "epoch": 0.41615667074663404,
      "grad_norm": 9.625,
      "learning_rate": 2.5e-07,
      "loss": 2.1383413314819335,
      "step": 170
    },
    {
      "epoch": 0.44063647490820074,
      "grad_norm": 7.34375,
      "learning_rate": 2.2534210005117207e-07,
      "loss": 2.009996032714844,
      "step": 180
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 10.0,
      "learning_rate": 2.0092466314611287e-07,
      "loss": 2.076437759399414,
      "step": 190
    },
    {
      "epoch": 0.48959608323133413,
      "grad_norm": 9.6875,
      "learning_rate": 1.7698580734075607e-07,
      "loss": 2.1122467041015627,
      "step": 200
    },
    {
      "epoch": 0.5140758873929009,
      "grad_norm": 7.53125,
      "learning_rate": 1.5375898358361077e-07,
      "loss": 1.956191062927246,
      "step": 210
    },
    {
      "epoch": 0.5385556915544676,
      "grad_norm": 10.3125,
      "learning_rate": 1.3147069910965296e-07,
      "loss": 1.944639015197754,
      "step": 220
    },
    {
      "epoch": 0.5630354957160343,
      "grad_norm": 13.3125,
      "learning_rate": 1.1033830854908691e-07,
      "loss": 2.2447561264038085,
      "step": 230
    },
    {
      "epoch": 0.587515299877601,
      "grad_norm": 11.1875,
      "learning_rate": 9.05678942920127e-08,
      "loss": 2.1660913467407226,
      "step": 240
    },
    {
      "epoch": 0.6119951040391677,
      "grad_norm": 18.5,
      "learning_rate": 7.235225677961512e-08,
      "loss": 2.3716936111450195,
      "step": 250
    },
    {
      "epoch": 0.6364749082007344,
      "grad_norm": 8.3125,
      "learning_rate": 5.586903432048942e-08,
      "loss": 2.1261455535888674,
      "step": 260
    },
    {
      "epoch": 0.6609547123623011,
      "grad_norm": 8.8125,
      "learning_rate": 4.127897076759399e-08,
      "loss": 2.064971923828125,
      "step": 270
    },
    {
      "epoch": 0.6854345165238678,
      "grad_norm": 14.5625,
      "learning_rate": 2.8724347949389048e-08,
      "loss": 2.085330009460449,
      "step": 280
    },
    {
      "epoch": 0.7099143206854345,
      "grad_norm": 17.25,
      "learning_rate": 1.8327598142041656e-08,
      "loss": 2.1130571365356445,
      "step": 290
    },
    {
      "epoch": 0.7343941248470012,
      "grad_norm": 10.625,
      "learning_rate": 1.0190110113823425e-08,
      "loss": 2.056776428222656,
      "step": 300
    },
    {
      "epoch": 0.758873929008568,
      "grad_norm": 13.75,
      "learning_rate": 4.391240385117623e-09,
      "loss": 2.13861141204834,
      "step": 310
    },
    {
      "epoch": 0.7833537331701347,
      "grad_norm": 14.8125,
      "learning_rate": 9.87539346195776e-10,
      "loss": 2.129196357727051,
      "step": 320
    },
    {
      "epoch": 0.802937576499388,
      "step": 328,
      "total_flos": 1.5578264772983194e+17,
      "train_loss": 2.1087728360804117,
      "train_runtime": 2487.2809,
      "train_samples_per_second": 0.526,
      "train_steps_per_second": 0.132
    }
  ],
  "logging_steps": 10,
  "max_steps": 328,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5578264772983194e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}