{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9987760097919217,
  "eval_steps": 500,
  "global_step": 204,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004895960832313341,
      "grad_norm": 31.803168810817947,
      "learning_rate": 4.7619047619047623e-07,
      "loss": 1.3104,
      "step": 1
    },
    {
      "epoch": 0.02447980416156671,
      "grad_norm": 12.089208314037734,
      "learning_rate": 2.380952380952381e-06,
      "loss": 1.2864,
      "step": 5
    },
    {
      "epoch": 0.04895960832313342,
      "grad_norm": 3.734128443782965,
      "learning_rate": 4.761904761904762e-06,
      "loss": 1.0964,
      "step": 10
    },
    {
      "epoch": 0.07343941248470012,
      "grad_norm": 2.7685333081809613,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.9865,
      "step": 15
    },
    {
      "epoch": 0.09791921664626684,
      "grad_norm": 2.6618393187338545,
      "learning_rate": 9.523809523809525e-06,
      "loss": 0.9754,
      "step": 20
    },
    {
      "epoch": 0.12239902080783353,
      "grad_norm": 2.8219368109360556,
      "learning_rate": 9.988216158430033e-06,
      "loss": 0.9828,
      "step": 25
    },
    {
      "epoch": 0.14687882496940025,
      "grad_norm": 2.5325872032864996,
      "learning_rate": 9.940439480455386e-06,
      "loss": 0.9463,
      "step": 30
    },
    {
      "epoch": 0.17135862913096694,
      "grad_norm": 2.8908619331299925,
      "learning_rate": 9.856284997329158e-06,
      "loss": 0.9522,
      "step": 35
    },
    {
      "epoch": 0.19583843329253367,
      "grad_norm": 3.513186055584603,
      "learning_rate": 9.736372361493584e-06,
      "loss": 0.9812,
      "step": 40
    },
    {
      "epoch": 0.22031823745410037,
      "grad_norm": 2.425130546395649,
      "learning_rate": 9.581584522435025e-06,
      "loss": 0.97,
      "step": 45
    },
    {
      "epoch": 0.24479804161566707,
      "grad_norm": 2.7085014552252793,
      "learning_rate": 9.393061225285743e-06,
      "loss": 0.9428,
      "step": 50
    },
    {
      "epoch": 0.2692778457772338,
      "grad_norm": 2.5282305939205645,
      "learning_rate": 9.172190618569236e-06,
      "loss": 0.9455,
      "step": 55
    },
    {
      "epoch": 0.2937576499388005,
      "grad_norm": 2.6167693326627406,
      "learning_rate": 8.920599032883553e-06,
      "loss": 0.9291,
      "step": 60
    },
    {
      "epoch": 0.3182374541003672,
      "grad_norm": 2.4397467891197953,
      "learning_rate": 8.640139005784924e-06,
      "loss": 0.897,
      "step": 65
    },
    {
      "epoch": 0.3427172582619339,
      "grad_norm": 2.687082572276412,
      "learning_rate": 8.332875641047817e-06,
      "loss": 0.8971,
      "step": 70
    },
    {
      "epoch": 0.3671970624235006,
      "grad_norm": 2.464301621801395,
      "learning_rate": 8.001071402741843e-06,
      "loss": 0.9071,
      "step": 75
    },
    {
      "epoch": 0.39167686658506734,
      "grad_norm": 2.3157277119472557,
      "learning_rate": 7.647169456090925e-06,
      "loss": 0.8622,
      "step": 80
    },
    {
      "epoch": 0.41615667074663404,
      "grad_norm": 2.340548302385909,
      "learning_rate": 7.27377567778053e-06,
      "loss": 0.8368,
      "step": 85
    },
    {
      "epoch": 0.44063647490820074,
      "grad_norm": 2.434317748871704,
      "learning_rate": 6.883639468175926e-06,
      "loss": 0.871,
      "step": 90
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 2.9663953802110443,
      "learning_rate": 6.479633506736447e-06,
      "loss": 0.8407,
      "step": 95
    },
    {
      "epoch": 0.48959608323133413,
      "grad_norm": 2.5695792323184006,
      "learning_rate": 6.064732599692079e-06,
      "loss": 0.826,
      "step": 100
    },
    {
      "epoch": 0.5140758873929009,
      "grad_norm": 2.999056757416413,
      "learning_rate": 5.641991775732756e-06,
      "loss": 0.8457,
      "step": 105
    },
    {
      "epoch": 0.5385556915544676,
      "grad_norm": 2.9168664674153466,
      "learning_rate": 5.214523790997773e-06,
      "loss": 0.8173,
      "step": 110
    },
    {
      "epoch": 0.5630354957160343,
      "grad_norm": 2.418710961036661,
      "learning_rate": 4.7854762090022274e-06,
      "loss": 0.8217,
      "step": 115
    },
    {
      "epoch": 0.587515299877601,
      "grad_norm": 2.324625674148865,
      "learning_rate": 4.358008224267245e-06,
      "loss": 0.8186,
      "step": 120
    },
    {
      "epoch": 0.6119951040391677,
      "grad_norm": 2.354640178196254,
      "learning_rate": 3.9352674003079225e-06,
      "loss": 0.7969,
      "step": 125
    },
    {
      "epoch": 0.6364749082007344,
      "grad_norm": 2.4349410812593524,
      "learning_rate": 3.520366493263554e-06,
      "loss": 0.7996,
      "step": 130
    },
    {
      "epoch": 0.6609547123623011,
      "grad_norm": 2.415118649892107,
      "learning_rate": 3.116360531824074e-06,
      "loss": 0.8086,
      "step": 135
    },
    {
      "epoch": 0.6854345165238678,
      "grad_norm": 2.369315986332015,
      "learning_rate": 2.7262243222194728e-06,
      "loss": 0.7904,
      "step": 140
    },
    {
      "epoch": 0.7099143206854345,
      "grad_norm": 2.8408105027248056,
      "learning_rate": 2.3528305439090744e-06,
      "loss": 0.7711,
      "step": 145
    },
    {
      "epoch": 0.7343941248470012,
      "grad_norm": 2.277003258633081,
      "learning_rate": 1.9989285972581595e-06,
      "loss": 0.7928,
      "step": 150
    },
    {
      "epoch": 0.758873929008568,
      "grad_norm": 2.398404156603122,
      "learning_rate": 1.667124358952184e-06,
      "loss": 0.7668,
      "step": 155
    },
    {
      "epoch": 0.7833537331701347,
      "grad_norm": 2.3139627873668664,
      "learning_rate": 1.3598609942150765e-06,
      "loss": 0.7646,
      "step": 160
    },
    {
      "epoch": 0.8078335373317014,
      "grad_norm": 2.322258534353416,
      "learning_rate": 1.0794009671164484e-06,
      "loss": 0.7782,
      "step": 165
    },
    {
      "epoch": 0.8323133414932681,
      "grad_norm": 2.253023482934021,
      "learning_rate": 8.278093814307637e-07,
      "loss": 0.7425,
      "step": 170
    },
    {
      "epoch": 0.8567931456548348,
      "grad_norm": 2.2625430444178223,
      "learning_rate": 6.069387747142591e-07,
      "loss": 0.7393,
      "step": 175
    },
    {
      "epoch": 0.8812729498164015,
      "grad_norm": 2.474019483415415,
      "learning_rate": 4.184154775649768e-07,
      "loss": 0.7243,
      "step": 180
    },
    {
      "epoch": 0.9057527539779682,
      "grad_norm": 2.318789387417803,
      "learning_rate": 2.636276385064157e-07,
      "loss": 0.7528,
      "step": 185
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 2.2755119405821054,
      "learning_rate": 1.4371500267084337e-07,
      "loss": 0.755,
      "step": 190
    },
    {
      "epoch": 0.9547123623011016,
      "grad_norm": 2.1830710176964283,
      "learning_rate": 5.9560519544614725e-08,
      "loss": 0.7424,
      "step": 195
    },
    {
      "epoch": 0.9791921664626683,
      "grad_norm": 2.437291192873111,
      "learning_rate": 1.1783841569968368e-08,
      "loss": 0.7208,
      "step": 200
    },
    {
      "epoch": 0.9987760097919217,
      "eval_loss": 0.9913554787635803,
      "eval_runtime": 1210.5452,
      "eval_samples_per_second": 3.159,
      "eval_steps_per_second": 0.79,
      "step": 204
    },
    {
      "epoch": 0.9987760097919217,
      "step": 204,
      "total_flos": 42661104844800.0,
      "train_loss": 0.8604376099857629,
      "train_runtime": 5992.0788,
      "train_samples_per_second": 1.091,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 5,
  "max_steps": 204,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 42661104844800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}