{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0396000396000396,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000198000198000198,
      "eval_loss": 1.105994701385498,
      "eval_runtime": 179.0951,
      "eval_samples_per_second": 11.876,
      "eval_steps_per_second": 5.941,
      "step": 1
    },
    {
      "epoch": 0.00198000198000198,
      "grad_norm": 1.0463930368423462,
      "learning_rate": 0.00019967573081342103,
      "loss": 4.1634,
      "step": 10
    },
    {
      "epoch": 0.00396000396000396,
      "grad_norm": 1.356583595275879,
      "learning_rate": 0.0001970941817426052,
      "loss": 3.8079,
      "step": 20
    },
    {
      "epoch": 0.00594000594000594,
      "grad_norm": 1.0096588134765625,
      "learning_rate": 0.00019199794436588243,
      "loss": 3.8102,
      "step": 30
    },
    {
      "epoch": 0.00792000792000792,
      "grad_norm": 1.113966464996338,
      "learning_rate": 0.0001845190085543795,
      "loss": 3.648,
      "step": 40
    },
    {
      "epoch": 0.0099000099000099,
      "grad_norm": 1.8908063173294067,
      "learning_rate": 0.00017485107481711012,
      "loss": 3.9368,
      "step": 50
    },
    {
      "epoch": 0.0099000099000099,
      "eval_loss": 0.8949177861213684,
      "eval_runtime": 179.1181,
      "eval_samples_per_second": 11.875,
      "eval_steps_per_second": 5.94,
      "step": 50
    },
    {
      "epoch": 0.01188001188001188,
      "grad_norm": 1.6522492170333862,
      "learning_rate": 0.00016324453755953773,
      "loss": 3.7852,
      "step": 60
    },
    {
      "epoch": 0.01386001386001386,
      "grad_norm": 1.0012105703353882,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.986,
      "step": 70
    },
    {
      "epoch": 0.01584001584001584,
      "grad_norm": 1.3137774467468262,
      "learning_rate": 0.00013546048870425356,
      "loss": 3.5971,
      "step": 80
    },
    {
      "epoch": 0.01782001782001782,
      "grad_norm": 1.7296185493469238,
      "learning_rate": 0.00012000256937760445,
      "loss": 3.526,
      "step": 90
    },
    {
      "epoch": 0.0198000198000198,
      "grad_norm": 0.9635865688323975,
      "learning_rate": 0.00010402659401094152,
      "loss": 3.4423,
      "step": 100
    },
    {
      "epoch": 0.0198000198000198,
      "eval_loss": 0.8596881031990051,
      "eval_runtime": 178.8666,
      "eval_samples_per_second": 11.892,
      "eval_steps_per_second": 5.949,
      "step": 100
    },
    {
      "epoch": 0.02178002178002178,
      "grad_norm": 1.0146996974945068,
      "learning_rate": 8.79463319744677e-05,
      "loss": 3.1704,
      "step": 110
    },
    {
      "epoch": 0.02376002376002376,
      "grad_norm": 1.135063886642456,
      "learning_rate": 7.217825360835473e-05,
      "loss": 3.1235,
      "step": 120
    },
    {
      "epoch": 0.02574002574002574,
      "grad_norm": 2.2007548809051514,
      "learning_rate": 5.713074385969457e-05,
      "loss": 3.7979,
      "step": 130
    },
    {
      "epoch": 0.02772002772002772,
      "grad_norm": 1.6966371536254883,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 3.3632,
      "step": 140
    },
    {
      "epoch": 0.0297000297000297,
      "grad_norm": 1.37982976436615,
      "learning_rate": 3.072756464904006e-05,
      "loss": 3.2835,
      "step": 150
    },
    {
      "epoch": 0.0297000297000297,
      "eval_loss": 0.8436567783355713,
      "eval_runtime": 178.8718,
      "eval_samples_per_second": 11.891,
      "eval_steps_per_second": 5.948,
      "step": 150
    },
    {
      "epoch": 0.03168003168003168,
      "grad_norm": 1.863335371017456,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 3.3173,
      "step": 160
    },
    {
      "epoch": 0.03366003366003366,
      "grad_norm": 1.6313773393630981,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 3.3616,
      "step": 170
    },
    {
      "epoch": 0.03564003564003564,
      "grad_norm": 1.686877965927124,
      "learning_rate": 5.146355805285452e-06,
      "loss": 3.8833,
      "step": 180
    },
    {
      "epoch": 0.03762003762003762,
      "grad_norm": 1.3582342863082886,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 3.5635,
      "step": 190
    },
    {
      "epoch": 0.0396000396000396,
      "grad_norm": 1.307408332824707,
      "learning_rate": 0.0,
      "loss": 3.1055,
      "step": 200
    },
    {
      "epoch": 0.0396000396000396,
      "eval_loss": 0.8413098454475403,
      "eval_runtime": 178.7099,
      "eval_samples_per_second": 11.902,
      "eval_steps_per_second": 5.954,
      "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": 9.680730813628416e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}