{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.42598509052183176,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002129925452609159,
      "eval_loss": 2.7690510749816895,
      "eval_runtime": 10.8689,
      "eval_samples_per_second": 18.217,
      "eval_steps_per_second": 9.109,
      "step": 1
    },
    {
      "epoch": 0.021299254526091587,
      "grad_norm": 0.9117720127105713,
      "learning_rate": 0.00019967573081342103,
      "loss": 2.5495,
      "step": 10
    },
    {
      "epoch": 0.042598509052183174,
      "grad_norm": 0.8717552423477173,
      "learning_rate": 0.0001970941817426052,
      "loss": 2.0983,
      "step": 20
    },
    {
      "epoch": 0.06389776357827476,
      "grad_norm": 1.2311043739318848,
      "learning_rate": 0.00019199794436588243,
      "loss": 1.8648,
      "step": 30
    },
    {
      "epoch": 0.08519701810436635,
      "grad_norm": 1.172974944114685,
      "learning_rate": 0.0001845190085543795,
      "loss": 1.5353,
      "step": 40
    },
    {
      "epoch": 0.10649627263045794,
      "grad_norm": 0.9758444428443909,
      "learning_rate": 0.00017485107481711012,
      "loss": 1.5798,
      "step": 50
    },
    {
      "epoch": 0.10649627263045794,
      "eval_loss": 1.4063894748687744,
      "eval_runtime": 9.8815,
      "eval_samples_per_second": 20.037,
      "eval_steps_per_second": 10.019,
      "step": 50
    },
    {
      "epoch": 0.12779552715654952,
      "grad_norm": 1.1444264650344849,
      "learning_rate": 0.00016324453755953773,
      "loss": 1.4037,
      "step": 60
    },
    {
      "epoch": 0.14909478168264112,
      "grad_norm": 1.1249662637710571,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3047,
      "step": 70
    },
    {
      "epoch": 0.1703940362087327,
      "grad_norm": 1.2312196493148804,
      "learning_rate": 0.00013546048870425356,
      "loss": 1.3984,
      "step": 80
    },
    {
      "epoch": 0.19169329073482427,
      "grad_norm": 1.0474377870559692,
      "learning_rate": 0.00012000256937760445,
      "loss": 1.2502,
      "step": 90
    },
    {
      "epoch": 0.21299254526091588,
      "grad_norm": 1.5092288255691528,
      "learning_rate": 0.00010402659401094152,
      "loss": 1.1157,
      "step": 100
    },
    {
      "epoch": 0.21299254526091588,
      "eval_loss": 1.1967875957489014,
      "eval_runtime": 9.8822,
      "eval_samples_per_second": 20.036,
      "eval_steps_per_second": 10.018,
      "step": 100
    },
    {
      "epoch": 0.23429179978700745,
      "grad_norm": 1.3918311595916748,
      "learning_rate": 8.79463319744677e-05,
      "loss": 1.2214,
      "step": 110
    },
    {
      "epoch": 0.25559105431309903,
      "grad_norm": 1.0303548574447632,
      "learning_rate": 7.217825360835473e-05,
      "loss": 1.0175,
      "step": 120
    },
    {
      "epoch": 0.27689030883919064,
      "grad_norm": 1.4731521606445312,
      "learning_rate": 5.713074385969457e-05,
      "loss": 1.1181,
      "step": 130
    },
    {
      "epoch": 0.29818956336528224,
      "grad_norm": 1.2414261102676392,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 1.1889,
      "step": 140
    },
    {
      "epoch": 0.3194888178913738,
      "grad_norm": 1.6876599788665771,
      "learning_rate": 3.072756464904006e-05,
      "loss": 1.2897,
      "step": 150
    },
    {
      "epoch": 0.3194888178913738,
      "eval_loss": 1.076661229133606,
      "eval_runtime": 9.8889,
      "eval_samples_per_second": 20.023,
      "eval_steps_per_second": 10.011,
      "step": 150
    },
    {
      "epoch": 0.3407880724174654,
      "grad_norm": 1.265449047088623,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 1.1214,
      "step": 160
    },
    {
      "epoch": 0.362087326943557,
      "grad_norm": 1.5992355346679688,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 1.2369,
      "step": 170
    },
    {
      "epoch": 0.38338658146964855,
      "grad_norm": 1.3271338939666748,
      "learning_rate": 5.146355805285452e-06,
      "loss": 1.0608,
      "step": 180
    },
    {
      "epoch": 0.40468583599574015,
      "grad_norm": 1.452867865562439,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 1.0436,
      "step": 190
    },
    {
      "epoch": 0.42598509052183176,
      "grad_norm": 1.2788019180297852,
      "learning_rate": 0.0,
      "loss": 1.0797,
      "step": 200
    },
    {
      "epoch": 0.42598509052183176,
      "eval_loss": 1.058427333831787,
      "eval_runtime": 9.8879,
      "eval_samples_per_second": 20.024,
      "eval_steps_per_second": 10.012,
      "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": 6.435312538484736e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}