{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020595201318092886,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004119040263618577,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0004119040263618577,
      "eval_loss": NaN,
      "eval_runtime": 84.9359,
      "eval_samples_per_second": 12.044,
      "eval_steps_per_second": 6.028,
      "step": 1
    },
    {
      "epoch": 0.0008238080527237154,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.001235712079085573,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0016476161054474307,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0020595201318092883,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.002471424158171146,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002883328184533004,
      "grad_norm": NaN,
      "learning_rate": 3.5e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0032952322108948614,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0037071362372567192,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.004119040263618577,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.004530944289980435,
      "grad_norm": NaN,
      "learning_rate": 4.99229333433282e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.004942848316342292,
      "grad_norm": NaN,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00535475234270415,
      "grad_norm": NaN,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 0.2457,
      "step": 13
    },
    {
      "epoch": 0.00535475234270415,
      "eval_loss": NaN,
      "eval_runtime": 83.3613,
      "eval_samples_per_second": 12.272,
      "eval_steps_per_second": 6.142,
      "step": 13
    },
    {
      "epoch": 0.005766656369066008,
      "grad_norm": NaN,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.3037,
      "step": 14
    },
    {
      "epoch": 0.006178560395427865,
      "grad_norm": NaN,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.7354,
      "step": 15
    },
    {
      "epoch": 0.006590464421789723,
      "grad_norm": NaN,
      "learning_rate": 4.72751631047092e-05,
      "loss": 0.55,
      "step": 16
    },
    {
      "epoch": 0.007002368448151581,
      "grad_norm": NaN,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0074142724745134385,
      "grad_norm": NaN,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.007826176500875297,
      "grad_norm": NaN,
      "learning_rate": 4.401014914000078e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.008238080527237153,
      "grad_norm": NaN,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.008649984553599012,
      "grad_norm": NaN,
      "learning_rate": 4.123620120825459e-05,
      "loss": 0.5579,
      "step": 21
    },
    {
      "epoch": 0.00906188857996087,
      "grad_norm": NaN,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.009473792606322726,
      "grad_norm": NaN,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.009885696632684585,
      "grad_norm": NaN,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.010297600659046443,
      "grad_norm": NaN,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0107095046854083,
      "grad_norm": NaN,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.0107095046854083,
      "eval_loss": NaN,
      "eval_runtime": 83.3154,
      "eval_samples_per_second": 12.279,
      "eval_steps_per_second": 6.145,
      "step": 26
    },
    {
      "epoch": 0.011121408711770158,
      "grad_norm": NaN,
      "learning_rate": 3.083613409639764e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.011533312738132016,
      "grad_norm": NaN,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.011945216764493873,
      "grad_norm": NaN,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 0.4629,
      "step": 29
    },
    {
      "epoch": 0.01235712079085573,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.012769024817217589,
      "grad_norm": NaN,
      "learning_rate": 2.303852260680388e-05,
      "loss": 0.5824,
      "step": 31
    },
    {
      "epoch": 0.013180928843579446,
      "grad_norm": NaN,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 2.1818,
      "step": 32
    },
    {
      "epoch": 0.013592832869941304,
      "grad_norm": NaN,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.014004736896303162,
      "grad_norm": NaN,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.3391,
      "step": 34
    },
    {
      "epoch": 0.014416640922665019,
      "grad_norm": NaN,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.014828544949026877,
      "grad_norm": NaN,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.015240448975388735,
      "grad_norm": NaN,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.015652353001750594,
      "grad_norm": NaN,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": NaN,
      "learning_rate": 8.763798791745411e-06,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.01606425702811245,
      "eval_loss": NaN,
      "eval_runtime": 83.2604,
      "eval_samples_per_second": 12.287,
      "eval_steps_per_second": 6.149,
      "step": 39
    },
    {
      "epoch": 0.016476161054474307,
      "grad_norm": NaN,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.016888065080836165,
      "grad_norm": NaN,
      "learning_rate": 5.989850859999227e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.017299969107198023,
      "grad_norm": NaN,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 1.0405,
      "step": 42
    },
    {
      "epoch": 0.01771187313355988,
      "grad_norm": NaN,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 0.8838,
      "step": 43
    },
    {
      "epoch": 0.01812377715992174,
      "grad_norm": NaN,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.018535681186283594,
      "grad_norm": NaN,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.018947585212645453,
      "grad_norm": NaN,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.4555,
      "step": 46
    },
    {
      "epoch": 0.01935948923900731,
      "grad_norm": NaN,
      "learning_rate": 6.907519900580861e-07,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.01977139326536917,
      "grad_norm": NaN,
      "learning_rate": 3.077914851215585e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.020183297291731028,
      "grad_norm": NaN,
      "learning_rate": 7.706665667180091e-08,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.020595201318092886,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0721,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7489812216807424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}