{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.033819488480236734,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001690974424011837,
      "eval_loss": 0.6405579447746277,
      "eval_runtime": 117.9843,
      "eval_samples_per_second": 21.105,
      "eval_steps_per_second": 10.552,
      "step": 1
    },
    {
      "epoch": 0.0016909744240118367,
      "grad_norm": 0.44157806038856506,
      "learning_rate": 0.00019967573081342103,
      "loss": 0.5424,
      "step": 10
    },
    {
      "epoch": 0.0033819488480236735,
      "grad_norm": 0.3633825480937958,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.5173,
      "step": 20
    },
    {
      "epoch": 0.0050729232720355105,
      "grad_norm": 0.3791579008102417,
      "learning_rate": 0.00019199794436588243,
      "loss": 0.444,
      "step": 30
    },
    {
      "epoch": 0.006763897696047347,
      "grad_norm": 0.36207354068756104,
      "learning_rate": 0.0001845190085543795,
      "loss": 0.4301,
      "step": 40
    },
    {
      "epoch": 0.008454872120059184,
      "grad_norm": 0.39383989572525024,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.4671,
      "step": 50
    },
    {
      "epoch": 0.008454872120059184,
      "eval_loss": 0.4415309727191925,
      "eval_runtime": 116.7728,
      "eval_samples_per_second": 21.323,
      "eval_steps_per_second": 10.662,
      "step": 50
    },
    {
      "epoch": 0.010145846544071021,
      "grad_norm": 0.4221698045730591,
      "learning_rate": 0.00016324453755953773,
      "loss": 0.4641,
      "step": 60
    },
    {
      "epoch": 0.011836820968082858,
      "grad_norm": 0.3870465159416199,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.452,
      "step": 70
    },
    {
      "epoch": 0.013527795392094694,
      "grad_norm": 0.4294101893901825,
      "learning_rate": 0.00013546048870425356,
      "loss": 0.4407,
      "step": 80
    },
    {
      "epoch": 0.015218769816106531,
      "grad_norm": 0.371154248714447,
      "learning_rate": 0.00012000256937760445,
      "loss": 0.4334,
      "step": 90
    },
    {
      "epoch": 0.016909744240118367,
      "grad_norm": 0.3693440854549408,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.4044,
      "step": 100
    },
    {
      "epoch": 0.016909744240118367,
      "eval_loss": 0.42293068766593933,
      "eval_runtime": 116.7511,
      "eval_samples_per_second": 21.327,
      "eval_steps_per_second": 10.664,
      "step": 100
    },
    {
      "epoch": 0.018600718664130204,
      "grad_norm": 0.41696932911872864,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.4133,
      "step": 110
    },
    {
      "epoch": 0.020291693088142042,
      "grad_norm": 0.43103691935539246,
      "learning_rate": 7.217825360835473e-05,
      "loss": 0.3906,
      "step": 120
    },
    {
      "epoch": 0.02198266751215388,
      "grad_norm": 0.42548608779907227,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.4235,
      "step": 130
    },
    {
      "epoch": 0.023673641936165717,
      "grad_norm": 0.4845651090145111,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 0.4203,
      "step": 140
    },
    {
      "epoch": 0.025364616360177554,
      "grad_norm": 0.5156506896018982,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.3934,
      "step": 150
    },
    {
      "epoch": 0.025364616360177554,
      "eval_loss": 0.41098639369010925,
      "eval_runtime": 116.7215,
      "eval_samples_per_second": 21.333,
      "eval_steps_per_second": 10.666,
      "step": 150
    },
    {
      "epoch": 0.027055590784189388,
      "grad_norm": 0.3687255382537842,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 0.4163,
      "step": 160
    },
    {
      "epoch": 0.028746565208201225,
      "grad_norm": 0.47959253191947937,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 0.3972,
      "step": 170
    },
    {
      "epoch": 0.030437539632213063,
      "grad_norm": 0.412997841835022,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.4189,
      "step": 180
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": 0.45186105370521545,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 0.4152,
      "step": 190
    },
    {
      "epoch": 0.033819488480236734,
      "grad_norm": 0.3915037512779236,
      "learning_rate": 0.0,
      "loss": 0.4748,
      "step": 200
    },
    {
      "epoch": 0.033819488480236734,
      "eval_loss": 0.4083862006664276,
      "eval_runtime": 116.8635,
      "eval_samples_per_second": 21.307,
      "eval_steps_per_second": 10.653,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.839999113520742e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}