{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02294630564479119,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011473152822395595,
      "eval_loss": 0.8775278925895691,
      "eval_runtime": 130.7747,
      "eval_samples_per_second": 28.064,
      "eval_steps_per_second": 14.032,
      "step": 1
    },
    {
      "epoch": 0.0011473152822395595,
      "grad_norm": 0.649625301361084,
      "learning_rate": 0.00019967573081342103,
      "loss": 0.3523,
      "step": 10
    },
    {
      "epoch": 0.002294630564479119,
      "grad_norm": 1.058106541633606,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.0131,
      "step": 20
    },
    {
      "epoch": 0.0034419458467186783,
      "grad_norm": 0.3737371563911438,
      "learning_rate": 0.00019199794436588243,
      "loss": 0.0078,
      "step": 30
    },
    {
      "epoch": 0.004589261128958238,
      "grad_norm": 0.12368472665548325,
      "learning_rate": 0.0001845190085543795,
      "loss": 0.0104,
      "step": 40
    },
    {
      "epoch": 0.005736576411197797,
      "grad_norm": 0.0030845513101667166,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.0094,
      "step": 50
    },
    {
      "epoch": 0.005736576411197797,
      "eval_loss": 0.0031162549275904894,
      "eval_runtime": 130.7788,
      "eval_samples_per_second": 28.063,
      "eval_steps_per_second": 14.031,
      "step": 50
    },
    {
      "epoch": 0.006883891693437357,
      "grad_norm": 0.007391553372144699,
      "learning_rate": 0.00016324453755953773,
      "loss": 0.0107,
      "step": 60
    },
    {
      "epoch": 0.008031206975676917,
      "grad_norm": 0.2855464220046997,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0091,
      "step": 70
    },
    {
      "epoch": 0.009178522257916476,
      "grad_norm": 0.021395135670900345,
      "learning_rate": 0.00013546048870425356,
      "loss": 0.0049,
      "step": 80
    },
    {
      "epoch": 0.010325837540156035,
      "grad_norm": 0.02801685221493244,
      "learning_rate": 0.00012000256937760445,
      "loss": 0.0041,
      "step": 90
    },
    {
      "epoch": 0.011473152822395595,
      "grad_norm": 0.02345002442598343,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.0036,
      "step": 100
    },
    {
      "epoch": 0.011473152822395595,
      "eval_loss": 0.0019256711238995194,
      "eval_runtime": 130.8012,
      "eval_samples_per_second": 28.058,
      "eval_steps_per_second": 14.029,
      "step": 100
    },
    {
      "epoch": 0.012620468104635154,
      "grad_norm": 0.011921586468815804,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.0043,
      "step": 110
    },
    {
      "epoch": 0.013767783386874713,
      "grad_norm": 0.012118199840188026,
      "learning_rate": 7.217825360835473e-05,
      "loss": 0.0006,
      "step": 120
    },
    {
      "epoch": 0.014915098669114273,
      "grad_norm": 0.030214006081223488,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.0014,
      "step": 130
    },
    {
      "epoch": 0.016062413951353834,
      "grad_norm": 0.12021081894636154,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 0.0014,
      "step": 140
    },
    {
      "epoch": 0.01720972923359339,
      "grad_norm": 0.011173585429787636,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.0007,
      "step": 150
    },
    {
      "epoch": 0.01720972923359339,
      "eval_loss": 0.0014718682505190372,
      "eval_runtime": 130.949,
      "eval_samples_per_second": 28.026,
      "eval_steps_per_second": 14.013,
      "step": 150
    },
    {
      "epoch": 0.018357044515832952,
      "grad_norm": 0.0016395815182477236,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 0.0011,
      "step": 160
    },
    {
      "epoch": 0.01950435979807251,
      "grad_norm": 0.0021897745318710804,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 0.0019,
      "step": 170
    },
    {
      "epoch": 0.02065167508031207,
      "grad_norm": 0.0021913335658609867,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.0002,
      "step": 180
    },
    {
      "epoch": 0.02179899036255163,
      "grad_norm": 0.002481397008523345,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 0.0011,
      "step": 190
    },
    {
      "epoch": 0.02294630564479119,
      "grad_norm": 0.009852674789726734,
      "learning_rate": 0.0,
      "loss": 0.0026,
      "step": 200
    },
    {
      "epoch": 0.02294630564479119,
      "eval_loss": 0.0012154106516391039,
      "eval_runtime": 130.9478,
      "eval_samples_per_second": 28.026,
      "eval_steps_per_second": 14.013,
      "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": 3.84607147524096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}