{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0030034314203978047,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5017157101989023e-05,
      "eval_loss": 3.4940359592437744,
      "eval_runtime": 2298.8386,
      "eval_samples_per_second": 12.197,
      "eval_steps_per_second": 6.099,
      "step": 1
    },
    {
      "epoch": 7.508578550994511e-05,
      "grad_norm": 0.3800654113292694,
      "learning_rate": 5e-05,
      "loss": 1.406,
      "step": 5
    },
    {
      "epoch": 0.00015017157101989022,
      "grad_norm": 0.7993976473808289,
      "learning_rate": 0.0001,
      "loss": 1.6444,
      "step": 10
    },
    {
      "epoch": 0.00022525735652983533,
      "grad_norm": 0.8274301290512085,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.6831,
      "step": 15
    },
    {
      "epoch": 0.00030034314203978044,
      "grad_norm": 1.1854416131973267,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.8049,
      "step": 20
    },
    {
      "epoch": 0.0003754289275497256,
      "grad_norm": 1.5541913509368896,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.7347,
      "step": 25
    },
    {
      "epoch": 0.00045051471305967067,
      "grad_norm": 1.7877317667007446,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.8298,
      "step": 30
    },
    {
      "epoch": 0.0005256004985696158,
      "grad_norm": 2.2849998474121094,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.3391,
      "step": 35
    },
    {
      "epoch": 0.0006006862840795609,
      "grad_norm": 4.458853244781494,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.3874,
      "step": 40
    },
    {
      "epoch": 0.000675772069589506,
      "grad_norm": 5.58752965927124,
      "learning_rate": 9.185832391312644e-05,
      "loss": 4.1727,
      "step": 45
    },
    {
      "epoch": 0.0007508578550994512,
      "grad_norm": 17.630456924438477,
      "learning_rate": 8.945702546981969e-05,
      "loss": 4.9483,
      "step": 50
    },
    {
      "epoch": 0.0007508578550994512,
      "eval_loss": 2.8145010471343994,
      "eval_runtime": 2308.5092,
      "eval_samples_per_second": 12.146,
      "eval_steps_per_second": 6.073,
      "step": 50
    },
    {
      "epoch": 0.0008259436406093962,
      "grad_norm": 1.356021761894226,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.5806,
      "step": 55
    },
    {
      "epoch": 0.0009010294261193413,
      "grad_norm": 0.8718690872192383,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.4852,
      "step": 60
    },
    {
      "epoch": 0.0009761152116292864,
      "grad_norm": 1.0226633548736572,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6258,
      "step": 65
    },
    {
      "epoch": 0.0010512009971392316,
      "grad_norm": 0.9398789405822754,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.7249,
      "step": 70
    },
    {
      "epoch": 0.0011262867826491766,
      "grad_norm": 1.301905632019043,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.8587,
      "step": 75
    },
    {
      "epoch": 0.0012013725681591218,
      "grad_norm": 1.5729906558990479,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.8419,
      "step": 80
    },
    {
      "epoch": 0.001276458353669067,
      "grad_norm": 1.849243402481079,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.12,
      "step": 85
    },
    {
      "epoch": 0.001351544139179012,
      "grad_norm": 3.608657121658325,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.2251,
      "step": 90
    },
    {
      "epoch": 0.0014266299246889571,
      "grad_norm": 5.073084831237793,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 4.0405,
      "step": 95
    },
    {
      "epoch": 0.0015017157101989023,
      "grad_norm": 9.735648155212402,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 4.5536,
      "step": 100
    },
    {
      "epoch": 0.0015017157101989023,
      "eval_loss": 2.4490885734558105,
      "eval_runtime": 2312.1302,
      "eval_samples_per_second": 12.127,
      "eval_steps_per_second": 6.064,
      "step": 100
    },
    {
      "epoch": 0.0015768014957088473,
      "grad_norm": 0.8634369969367981,
      "learning_rate": 5e-05,
      "loss": 1.3816,
      "step": 105
    },
    {
      "epoch": 0.0016518872812187925,
      "grad_norm": 0.7216693758964539,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.5009,
      "step": 110
    },
    {
      "epoch": 0.0017269730667287377,
      "grad_norm": 0.9396697282791138,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.6304,
      "step": 115
    },
    {
      "epoch": 0.0018020588522386827,
      "grad_norm": 1.026105284690857,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.674,
      "step": 120
    },
    {
      "epoch": 0.0018771446377486279,
      "grad_norm": 1.0835193395614624,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.531,
      "step": 125
    },
    {
      "epoch": 0.0019522304232585728,
      "grad_norm": 1.1509310007095337,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.7271,
      "step": 130
    },
    {
      "epoch": 0.002027316208768518,
      "grad_norm": 2.0080721378326416,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.1363,
      "step": 135
    },
    {
      "epoch": 0.0021024019942784632,
      "grad_norm": 2.767570734024048,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.8779,
      "step": 140
    },
    {
      "epoch": 0.0021774877797884084,
      "grad_norm": 4.044328212738037,
      "learning_rate": 1.928936436551661e-05,
      "loss": 3.7799,
      "step": 145
    },
    {
      "epoch": 0.002252573565298353,
      "grad_norm": 12.717976570129395,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 4.5699,
      "step": 150
    },
    {
      "epoch": 0.002252573565298353,
      "eval_loss": 2.327751636505127,
      "eval_runtime": 2313.9453,
      "eval_samples_per_second": 12.117,
      "eval_steps_per_second": 6.059,
      "step": 150
    },
    {
      "epoch": 0.0023276593508082984,
      "grad_norm": 0.4896831214427948,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.3756,
      "step": 155
    },
    {
      "epoch": 0.0024027451363182436,
      "grad_norm": 0.7484576106071472,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.4297,
      "step": 160
    },
    {
      "epoch": 0.0024778309218281887,
      "grad_norm": 0.7907517552375793,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.531,
      "step": 165
    },
    {
      "epoch": 0.002552916707338134,
      "grad_norm": 0.9451369643211365,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.5736,
      "step": 170
    },
    {
      "epoch": 0.002628002492848079,
      "grad_norm": 1.0756996870040894,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.6789,
      "step": 175
    },
    {
      "epoch": 0.002703088278358024,
      "grad_norm": 1.4432721138000488,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.8192,
      "step": 180
    },
    {
      "epoch": 0.002778174063867969,
      "grad_norm": 1.6177784204483032,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.0462,
      "step": 185
    },
    {
      "epoch": 0.0028532598493779143,
      "grad_norm": 3.0353176593780518,
      "learning_rate": 6.819348298638839e-07,
      "loss": 2.6835,
      "step": 190
    },
    {
      "epoch": 0.0029283456348878595,
      "grad_norm": 3.7709476947784424,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 3.513,
      "step": 195
    },
    {
      "epoch": 0.0030034314203978047,
      "grad_norm": 10.600866317749023,
      "learning_rate": 0.0,
      "loss": 4.5757,
      "step": 200
    },
    {
      "epoch": 0.0030034314203978047,
      "eval_loss": 2.316987991333008,
      "eval_runtime": 2314.3781,
      "eval_samples_per_second": 12.115,
      "eval_steps_per_second": 6.058,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.444496098787328e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}