{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 549,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0546448087431694,
      "grad_norm": 9.216311123646195,
      "learning_rate": 5e-06,
      "loss": 1.0197,
      "step": 10
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 2.84822970052699,
      "learning_rate": 5e-06,
      "loss": 0.9201,
      "step": 20
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 1.1976026595489564,
      "learning_rate": 5e-06,
      "loss": 0.8893,
      "step": 30
    },
    {
      "epoch": 0.2185792349726776,
      "grad_norm": 0.7151750657967473,
      "learning_rate": 5e-06,
      "loss": 0.8686,
      "step": 40
    },
    {
      "epoch": 0.273224043715847,
      "grad_norm": 0.7178785706016054,
      "learning_rate": 5e-06,
      "loss": 0.8566,
      "step": 50
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 1.3738089444275707,
      "learning_rate": 5e-06,
      "loss": 0.8464,
      "step": 60
    },
    {
      "epoch": 0.3825136612021858,
      "grad_norm": 0.7307703509770203,
      "learning_rate": 5e-06,
      "loss": 0.837,
      "step": 70
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": 0.9793900236646151,
      "learning_rate": 5e-06,
      "loss": 0.834,
      "step": 80
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 0.6074469784310406,
      "learning_rate": 5e-06,
      "loss": 0.8239,
      "step": 90
    },
    {
      "epoch": 0.546448087431694,
      "grad_norm": 0.7581415259721198,
      "learning_rate": 5e-06,
      "loss": 0.8203,
      "step": 100
    },
    {
      "epoch": 0.6010928961748634,
      "grad_norm": 0.6207562995736402,
      "learning_rate": 5e-06,
      "loss": 0.8191,
      "step": 110
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.712118501956403,
      "learning_rate": 5e-06,
      "loss": 0.8148,
      "step": 120
    },
    {
      "epoch": 0.7103825136612022,
      "grad_norm": 0.5406181591483699,
      "learning_rate": 5e-06,
      "loss": 0.816,
      "step": 130
    },
    {
      "epoch": 0.7650273224043715,
      "grad_norm": 0.801157400991226,
      "learning_rate": 5e-06,
      "loss": 0.8084,
      "step": 140
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 1.3907122538264838,
      "learning_rate": 5e-06,
      "loss": 0.8101,
      "step": 150
    },
    {
      "epoch": 0.8743169398907104,
      "grad_norm": 0.9374210060236701,
      "learning_rate": 5e-06,
      "loss": 0.8095,
      "step": 160
    },
    {
      "epoch": 0.9289617486338798,
      "grad_norm": 0.7357026277429077,
      "learning_rate": 5e-06,
      "loss": 0.8056,
      "step": 170
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.6439903150890136,
      "learning_rate": 5e-06,
      "loss": 0.8067,
      "step": 180
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8027574419975281,
      "eval_runtime": 18.4703,
      "eval_samples_per_second": 266.536,
      "eval_steps_per_second": 1.083,
      "step": 183
    },
    {
      "epoch": 1.0382513661202186,
      "grad_norm": 0.9901943553002889,
      "learning_rate": 5e-06,
      "loss": 0.7796,
      "step": 190
    },
    {
      "epoch": 1.092896174863388,
      "grad_norm": 0.6647757287607619,
      "learning_rate": 5e-06,
      "loss": 0.7669,
      "step": 200
    },
    {
      "epoch": 1.1475409836065573,
      "grad_norm": 0.9580968284481025,
      "learning_rate": 5e-06,
      "loss": 0.7664,
      "step": 210
    },
    {
      "epoch": 1.2021857923497268,
      "grad_norm": 0.8889371423217748,
      "learning_rate": 5e-06,
      "loss": 0.7675,
      "step": 220
    },
    {
      "epoch": 1.2568306010928962,
      "grad_norm": 0.9247757328115808,
      "learning_rate": 5e-06,
      "loss": 0.7625,
      "step": 230
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 0.7030804123659421,
      "learning_rate": 5e-06,
      "loss": 0.7669,
      "step": 240
    },
    {
      "epoch": 1.366120218579235,
      "grad_norm": 0.6820492241392998,
      "learning_rate": 5e-06,
      "loss": 0.7679,
      "step": 250
    },
    {
      "epoch": 1.4207650273224044,
      "grad_norm": 0.5636718084741676,
      "learning_rate": 5e-06,
      "loss": 0.7606,
      "step": 260
    },
    {
      "epoch": 1.4754098360655736,
      "grad_norm": 0.639581027268557,
      "learning_rate": 5e-06,
      "loss": 0.7593,
      "step": 270
    },
    {
      "epoch": 1.530054644808743,
      "grad_norm": 0.6987258742060128,
      "learning_rate": 5e-06,
      "loss": 0.7612,
      "step": 280
    },
    {
      "epoch": 1.5846994535519126,
      "grad_norm": 0.6936443486720386,
      "learning_rate": 5e-06,
      "loss": 0.7582,
      "step": 290
    },
    {
      "epoch": 1.639344262295082,
      "grad_norm": 0.5505691855153351,
      "learning_rate": 5e-06,
      "loss": 0.7625,
      "step": 300
    },
    {
      "epoch": 1.6939890710382515,
      "grad_norm": 0.5640162883535096,
      "learning_rate": 5e-06,
      "loss": 0.7626,
      "step": 310
    },
    {
      "epoch": 1.748633879781421,
      "grad_norm": 0.6321872003984678,
      "learning_rate": 5e-06,
      "loss": 0.764,
      "step": 320
    },
    {
      "epoch": 1.8032786885245902,
      "grad_norm": 0.6338738498810821,
      "learning_rate": 5e-06,
      "loss": 0.762,
      "step": 330
    },
    {
      "epoch": 1.8579234972677594,
      "grad_norm": 0.5229579892525594,
      "learning_rate": 5e-06,
      "loss": 0.7672,
      "step": 340
    },
    {
      "epoch": 1.9125683060109289,
      "grad_norm": 0.7287452929104943,
      "learning_rate": 5e-06,
      "loss": 0.7615,
      "step": 350
    },
    {
      "epoch": 1.9672131147540983,
      "grad_norm": 0.7034416943673282,
      "learning_rate": 5e-06,
      "loss": 0.7596,
      "step": 360
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7888949513435364,
      "eval_runtime": 18.3314,
      "eval_samples_per_second": 268.556,
      "eval_steps_per_second": 1.091,
      "step": 366
    },
    {
      "epoch": 2.021857923497268,
      "grad_norm": 1.0144238515169914,
      "learning_rate": 5e-06,
      "loss": 0.7482,
      "step": 370
    },
    {
      "epoch": 2.0765027322404372,
      "grad_norm": 0.8603434912719397,
      "learning_rate": 5e-06,
      "loss": 0.7216,
      "step": 380
    },
    {
      "epoch": 2.1311475409836067,
      "grad_norm": 0.7563179754120521,
      "learning_rate": 5e-06,
      "loss": 0.7175,
      "step": 390
    },
    {
      "epoch": 2.185792349726776,
      "grad_norm": 0.9559125673842068,
      "learning_rate": 5e-06,
      "loss": 0.7222,
      "step": 400
    },
    {
      "epoch": 2.240437158469945,
      "grad_norm": 0.769800549346291,
      "learning_rate": 5e-06,
      "loss": 0.7184,
      "step": 410
    },
    {
      "epoch": 2.2950819672131146,
      "grad_norm": 0.6419920496502396,
      "learning_rate": 5e-06,
      "loss": 0.7222,
      "step": 420
    },
    {
      "epoch": 2.349726775956284,
      "grad_norm": 0.7532650987823766,
      "learning_rate": 5e-06,
      "loss": 0.7246,
      "step": 430
    },
    {
      "epoch": 2.4043715846994536,
      "grad_norm": 0.5920199594002061,
      "learning_rate": 5e-06,
      "loss": 0.7228,
      "step": 440
    },
    {
      "epoch": 2.459016393442623,
      "grad_norm": 0.6161056536206126,
      "learning_rate": 5e-06,
      "loss": 0.722,
      "step": 450
    },
    {
      "epoch": 2.5136612021857925,
      "grad_norm": 0.7438641211945972,
      "learning_rate": 5e-06,
      "loss": 0.7215,
      "step": 460
    },
    {
      "epoch": 2.5683060109289615,
      "grad_norm": 0.6857540384247945,
      "learning_rate": 5e-06,
      "loss": 0.7255,
      "step": 470
    },
    {
      "epoch": 2.6229508196721314,
      "grad_norm": 0.5697372445993161,
      "learning_rate": 5e-06,
      "loss": 0.7231,
      "step": 480
    },
    {
      "epoch": 2.6775956284153004,
      "grad_norm": 0.868972289179613,
      "learning_rate": 5e-06,
      "loss": 0.7238,
      "step": 490
    },
    {
      "epoch": 2.73224043715847,
      "grad_norm": 0.6159867401214144,
      "learning_rate": 5e-06,
      "loss": 0.7208,
      "step": 500
    },
    {
      "epoch": 2.7868852459016393,
      "grad_norm": 0.584105759494615,
      "learning_rate": 5e-06,
      "loss": 0.7263,
      "step": 510
    },
    {
      "epoch": 2.841530054644809,
      "grad_norm": 0.5906676150264403,
      "learning_rate": 5e-06,
      "loss": 0.7221,
      "step": 520
    },
    {
      "epoch": 2.8961748633879782,
      "grad_norm": 0.5994810510441251,
      "learning_rate": 5e-06,
      "loss": 0.7266,
      "step": 530
    },
    {
      "epoch": 2.9508196721311473,
      "grad_norm": 0.7788656644195687,
      "learning_rate": 5e-06,
      "loss": 0.7194,
      "step": 540
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7868959903717041,
      "eval_runtime": 18.0047,
      "eval_samples_per_second": 273.428,
      "eval_steps_per_second": 1.111,
      "step": 549
    },
    {
      "epoch": 3.0,
      "step": 549,
      "total_flos": 919595447746560.0,
      "train_loss": 0.7765402672286459,
      "train_runtime": 3626.8952,
      "train_samples_per_second": 77.367,
      "train_steps_per_second": 0.151
    }
  ],
  "logging_steps": 10,
  "max_steps": 549,
  "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": 919595447746560.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}