{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017515818974010902,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.757909487005452e-05,
      "eval_loss": 1.114413857460022,
      "eval_runtime": 765.8661,
      "eval_samples_per_second": 6.278,
      "eval_steps_per_second": 3.139,
      "step": 1
    },
    {
      "epoch": 0.0004378954743502726,
      "grad_norm": 1.446079969406128,
      "learning_rate": 5e-05,
      "loss": 4.1878,
      "step": 5
    },
    {
      "epoch": 0.0008757909487005452,
      "grad_norm": 2.547062873840332,
      "learning_rate": 0.0001,
      "loss": 4.0999,
      "step": 10
    },
    {
      "epoch": 0.0013136864230508178,
      "grad_norm": 2.3454508781433105,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.7314,
      "step": 15
    },
    {
      "epoch": 0.0017515818974010904,
      "grad_norm": 2.411564588546753,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.9206,
      "step": 20
    },
    {
      "epoch": 0.0021894773717513628,
      "grad_norm": 1.9333136081695557,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.6502,
      "step": 25
    },
    {
      "epoch": 0.0026273728461016356,
      "grad_norm": 2.324923515319824,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.6737,
      "step": 30
    },
    {
      "epoch": 0.003065268320451908,
      "grad_norm": 2.5995092391967773,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.6196,
      "step": 35
    },
    {
      "epoch": 0.0035031637948021808,
      "grad_norm": 2.193145990371704,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.5232,
      "step": 40
    },
    {
      "epoch": 0.003941059269152453,
      "grad_norm": 2.480156898498535,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.4605,
      "step": 45
    },
    {
      "epoch": 0.0043789547435027255,
      "grad_norm": 4.0897698402404785,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.8129,
      "step": 50
    },
    {
      "epoch": 0.0043789547435027255,
      "eval_loss": 0.8563802242279053,
      "eval_runtime": 766.9707,
      "eval_samples_per_second": 6.269,
      "eval_steps_per_second": 3.134,
      "step": 50
    },
    {
      "epoch": 0.004816850217852999,
      "grad_norm": 1.8455181121826172,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.1623,
      "step": 55
    },
    {
      "epoch": 0.005254745692203271,
      "grad_norm": 2.248112678527832,
      "learning_rate": 8.386407858128706e-05,
      "loss": 3.2379,
      "step": 60
    },
    {
      "epoch": 0.0056926411665535435,
      "grad_norm": 2.164348602294922,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.2753,
      "step": 65
    },
    {
      "epoch": 0.006130536640903816,
      "grad_norm": 2.1592774391174316,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.1848,
      "step": 70
    },
    {
      "epoch": 0.006568432115254089,
      "grad_norm": 2.558497190475464,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.3365,
      "step": 75
    },
    {
      "epoch": 0.0070063275896043616,
      "grad_norm": 2.571784734725952,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.3205,
      "step": 80
    },
    {
      "epoch": 0.007444223063954634,
      "grad_norm": 2.5822806358337402,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.4073,
      "step": 85
    },
    {
      "epoch": 0.007882118538304906,
      "grad_norm": 2.714940309524536,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.3058,
      "step": 90
    },
    {
      "epoch": 0.00832001401265518,
      "grad_norm": 3.211641311645508,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.6893,
      "step": 95
    },
    {
      "epoch": 0.008757909487005451,
      "grad_norm": 7.980849266052246,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.3992,
      "step": 100
    },
    {
      "epoch": 0.008757909487005451,
      "eval_loss": 0.8133825063705444,
      "eval_runtime": 767.3147,
      "eval_samples_per_second": 6.266,
      "eval_steps_per_second": 3.133,
      "step": 100
    },
    {
      "epoch": 0.009195804961355724,
      "grad_norm": 1.9374659061431885,
      "learning_rate": 5e-05,
      "loss": 2.98,
      "step": 105
    },
    {
      "epoch": 0.009633700435705998,
      "grad_norm": 2.3840270042419434,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 3.0368,
      "step": 110
    },
    {
      "epoch": 0.010071595910056269,
      "grad_norm": 2.3761801719665527,
      "learning_rate": 4.17702704859633e-05,
      "loss": 3.0822,
      "step": 115
    },
    {
      "epoch": 0.010509491384406542,
      "grad_norm": 2.6670830249786377,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.2291,
      "step": 120
    },
    {
      "epoch": 0.010947386858756816,
      "grad_norm": 2.69366455078125,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 3.1744,
      "step": 125
    },
    {
      "epoch": 0.011385282333107087,
      "grad_norm": 2.5782558917999268,
      "learning_rate": 2.991522876735154e-05,
      "loss": 3.2758,
      "step": 130
    },
    {
      "epoch": 0.01182317780745736,
      "grad_norm": 2.608020067214966,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.1772,
      "step": 135
    },
    {
      "epoch": 0.012261073281807632,
      "grad_norm": 2.934964656829834,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 3.2948,
      "step": 140
    },
    {
      "epoch": 0.012698968756157905,
      "grad_norm": 2.883345603942871,
      "learning_rate": 1.928936436551661e-05,
      "loss": 3.1347,
      "step": 145
    },
    {
      "epoch": 0.013136864230508178,
      "grad_norm": 6.287515163421631,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.1222,
      "step": 150
    },
    {
      "epoch": 0.013136864230508178,
      "eval_loss": 0.7958467602729797,
      "eval_runtime": 768.0113,
      "eval_samples_per_second": 6.26,
      "eval_steps_per_second": 3.13,
      "step": 150
    },
    {
      "epoch": 0.01357475970485845,
      "grad_norm": 2.337789297103882,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 3.2356,
      "step": 155
    },
    {
      "epoch": 0.014012655179208723,
      "grad_norm": 2.2584314346313477,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.9298,
      "step": 160
    },
    {
      "epoch": 0.014450550653558995,
      "grad_norm": 2.495149850845337,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.2654,
      "step": 165
    },
    {
      "epoch": 0.014888446127909268,
      "grad_norm": 3.1713342666625977,
      "learning_rate": 6.026312439675552e-06,
      "loss": 3.0731,
      "step": 170
    },
    {
      "epoch": 0.015326341602259541,
      "grad_norm": 2.6922738552093506,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 3.0576,
      "step": 175
    },
    {
      "epoch": 0.015764237076609813,
      "grad_norm": 2.837632656097412,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.1416,
      "step": 180
    },
    {
      "epoch": 0.016202132550960084,
      "grad_norm": 2.974255323410034,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 3.3309,
      "step": 185
    },
    {
      "epoch": 0.01664002802531036,
      "grad_norm": 2.985832691192627,
      "learning_rate": 6.819348298638839e-07,
      "loss": 3.3008,
      "step": 190
    },
    {
      "epoch": 0.01707792349966063,
      "grad_norm": 3.1796650886535645,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 3.2432,
      "step": 195
    },
    {
      "epoch": 0.017515818974010902,
      "grad_norm": 6.4413299560546875,
      "learning_rate": 0.0,
      "loss": 3.6426,
      "step": 200
    },
    {
      "epoch": 0.017515818974010902,
      "eval_loss": 0.7911927103996277,
      "eval_runtime": 767.2573,
      "eval_samples_per_second": 6.266,
      "eval_steps_per_second": 3.133,
      "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": 1.5586696026390528e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}