{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06398464368551547,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031992321842757736,
      "eval_loss": 1.8430436849594116,
      "eval_runtime": 153.2735,
      "eval_samples_per_second": 34.35,
      "eval_steps_per_second": 4.3,
      "step": 1
    },
    {
      "epoch": 0.0031992321842757737,
      "grad_norm": 2.4950242042541504,
      "learning_rate": 0.00019967573081342103,
      "loss": 6.7553,
      "step": 10
    },
    {
      "epoch": 0.006398464368551547,
      "grad_norm": 4.571041107177734,
      "learning_rate": 0.0001970941817426052,
      "loss": 5.4044,
      "step": 20
    },
    {
      "epoch": 0.009597696552827321,
      "grad_norm": 4.416581630706787,
      "learning_rate": 0.00019199794436588243,
      "loss": 4.8963,
      "step": 30
    },
    {
      "epoch": 0.012796928737103095,
      "grad_norm": 3.993983268737793,
      "learning_rate": 0.0001845190085543795,
      "loss": 5.1191,
      "step": 40
    },
    {
      "epoch": 0.015996160921378868,
      "grad_norm": 4.616549015045166,
      "learning_rate": 0.00017485107481711012,
      "loss": 4.7698,
      "step": 50
    },
    {
      "epoch": 0.015996160921378868,
      "eval_loss": 1.1898785829544067,
      "eval_runtime": 80.8462,
      "eval_samples_per_second": 65.124,
      "eval_steps_per_second": 8.151,
      "step": 50
    },
    {
      "epoch": 0.019195393105654643,
      "grad_norm": 3.3337819576263428,
      "learning_rate": 0.00016324453755953773,
      "loss": 4.6702,
      "step": 60
    },
    {
      "epoch": 0.022394625289930418,
      "grad_norm": 3.842341899871826,
      "learning_rate": 0.00015000000000000001,
      "loss": 4.7757,
      "step": 70
    },
    {
      "epoch": 0.02559385747420619,
      "grad_norm": 3.498433828353882,
      "learning_rate": 0.00013546048870425356,
      "loss": 4.7406,
      "step": 80
    },
    {
      "epoch": 0.028793089658481964,
      "grad_norm": 4.5708184242248535,
      "learning_rate": 0.00012000256937760445,
      "loss": 4.6306,
      "step": 90
    },
    {
      "epoch": 0.031992321842757736,
      "grad_norm": 4.5923027992248535,
      "learning_rate": 0.00010402659401094152,
      "loss": 4.5951,
      "step": 100
    },
    {
      "epoch": 0.031992321842757736,
      "eval_loss": 1.1325416564941406,
      "eval_runtime": 80.8493,
      "eval_samples_per_second": 65.121,
      "eval_steps_per_second": 8.151,
      "step": 100
    },
    {
      "epoch": 0.035191554027033514,
      "grad_norm": 4.968773365020752,
      "learning_rate": 8.79463319744677e-05,
      "loss": 4.365,
      "step": 110
    },
    {
      "epoch": 0.038390786211309286,
      "grad_norm": 4.013457775115967,
      "learning_rate": 7.217825360835473e-05,
      "loss": 4.5421,
      "step": 120
    },
    {
      "epoch": 0.04159001839558506,
      "grad_norm": 4.1948041915893555,
      "learning_rate": 5.713074385969457e-05,
      "loss": 4.5082,
      "step": 130
    },
    {
      "epoch": 0.044789250579860836,
      "grad_norm": 4.111287593841553,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 4.3099,
      "step": 140
    },
    {
      "epoch": 0.04798848276413661,
      "grad_norm": 5.362466335296631,
      "learning_rate": 3.072756464904006e-05,
      "loss": 4.2747,
      "step": 150
    },
    {
      "epoch": 0.04798848276413661,
      "eval_loss": 1.0948984622955322,
      "eval_runtime": 80.8489,
      "eval_samples_per_second": 65.121,
      "eval_steps_per_second": 8.151,
      "step": 150
    },
    {
      "epoch": 0.05118771494841238,
      "grad_norm": 4.674208164215088,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 4.4265,
      "step": 160
    },
    {
      "epoch": 0.05438694713268816,
      "grad_norm": 6.218277454376221,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 4.4142,
      "step": 170
    },
    {
      "epoch": 0.05758617931696393,
      "grad_norm": 5.0643768310546875,
      "learning_rate": 5.146355805285452e-06,
      "loss": 4.5209,
      "step": 180
    },
    {
      "epoch": 0.0607854115012397,
      "grad_norm": 4.299080848693848,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 4.4362,
      "step": 190
    },
    {
      "epoch": 0.06398464368551547,
      "grad_norm": 4.9810404777526855,
      "learning_rate": 0.0,
      "loss": 4.3688,
      "step": 200
    },
    {
      "epoch": 0.06398464368551547,
      "eval_loss": 1.0858551263809204,
      "eval_runtime": 80.9167,
      "eval_samples_per_second": 65.067,
      "eval_steps_per_second": 8.144,
      "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": 3.5985119241673114e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}