{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000605226127611929,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.026130638059645e-05,
      "grad_norm": 6.897684097290039,
      "learning_rate": 2e-05,
      "loss": 14.1293,
      "step": 1
    },
    {
      "epoch": 3.026130638059645e-05,
      "eval_loss": 3.439159631729126,
      "eval_runtime": 842.2168,
      "eval_samples_per_second": 16.521,
      "eval_steps_per_second": 8.26,
      "step": 1
    },
    {
      "epoch": 6.05226127611929e-05,
      "grad_norm": 7.347817897796631,
      "learning_rate": 4e-05,
      "loss": 13.2212,
      "step": 2
    },
    {
      "epoch": 9.078391914178935e-05,
      "grad_norm": 6.220455646514893,
      "learning_rate": 6e-05,
      "loss": 13.1675,
      "step": 3
    },
    {
      "epoch": 0.0001210452255223858,
      "grad_norm": 6.953392505645752,
      "learning_rate": 8e-05,
      "loss": 14.161,
      "step": 4
    },
    {
      "epoch": 0.00015130653190298225,
      "grad_norm": 5.382694721221924,
      "learning_rate": 0.0001,
      "loss": 12.7597,
      "step": 5
    },
    {
      "epoch": 0.00015130653190298225,
      "eval_loss": 3.2645046710968018,
      "eval_runtime": 841.9675,
      "eval_samples_per_second": 16.526,
      "eval_steps_per_second": 8.263,
      "step": 5
    },
    {
      "epoch": 0.0001815678382835787,
      "grad_norm": 4.9391889572143555,
      "learning_rate": 0.00012,
      "loss": 12.6619,
      "step": 6
    },
    {
      "epoch": 0.00021182914466417516,
      "grad_norm": 4.317287921905518,
      "learning_rate": 0.00014,
      "loss": 11.4259,
      "step": 7
    },
    {
      "epoch": 0.0002420904510447716,
      "grad_norm": 5.104113578796387,
      "learning_rate": 0.00016,
      "loss": 12.6299,
      "step": 8
    },
    {
      "epoch": 0.0002723517574253681,
      "grad_norm": 5.477384567260742,
      "learning_rate": 0.00018,
      "loss": 12.2808,
      "step": 9
    },
    {
      "epoch": 0.0003026130638059645,
      "grad_norm": 5.456517696380615,
      "learning_rate": 0.0002,
      "loss": 12.0744,
      "step": 10
    },
    {
      "epoch": 0.0003026130638059645,
      "eval_loss": 2.7829158306121826,
      "eval_runtime": 843.9912,
      "eval_samples_per_second": 16.486,
      "eval_steps_per_second": 8.243,
      "step": 10
    },
    {
      "epoch": 0.00033287437018656097,
      "grad_norm": 5.335687160491943,
      "learning_rate": 0.00019510565162951537,
      "loss": 12.4119,
      "step": 11
    },
    {
      "epoch": 0.0003631356765671574,
      "grad_norm": 5.601584434509277,
      "learning_rate": 0.00018090169943749476,
      "loss": 11.0707,
      "step": 12
    },
    {
      "epoch": 0.00039339698294775386,
      "grad_norm": 5.754549503326416,
      "learning_rate": 0.00015877852522924732,
      "loss": 9.4772,
      "step": 13
    },
    {
      "epoch": 0.00042365828932835033,
      "grad_norm": 8.268277168273926,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.7824,
      "step": 14
    },
    {
      "epoch": 0.00045391959570894675,
      "grad_norm": 7.563680648803711,
      "learning_rate": 0.0001,
      "loss": 11.0886,
      "step": 15
    },
    {
      "epoch": 0.00045391959570894675,
      "eval_loss": 2.6860508918762207,
      "eval_runtime": 847.5438,
      "eval_samples_per_second": 16.417,
      "eval_steps_per_second": 8.208,
      "step": 15
    },
    {
      "epoch": 0.0004841809020895432,
      "grad_norm": 7.714522838592529,
      "learning_rate": 6.909830056250527e-05,
      "loss": 9.9248,
      "step": 16
    },
    {
      "epoch": 0.0005144422084701396,
      "grad_norm": 7.84112024307251,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.7425,
      "step": 17
    },
    {
      "epoch": 0.0005447035148507362,
      "grad_norm": 6.446829319000244,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 10.3292,
      "step": 18
    },
    {
      "epoch": 0.0005749648212313326,
      "grad_norm": 7.735879421234131,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 10.3231,
      "step": 19
    },
    {
      "epoch": 0.000605226127611929,
      "grad_norm": 6.886676788330078,
      "learning_rate": 0.0,
      "loss": 9.9093,
      "step": 20
    },
    {
      "epoch": 0.000605226127611929,
      "eval_loss": 2.6602911949157715,
      "eval_runtime": 843.1817,
      "eval_samples_per_second": 16.502,
      "eval_steps_per_second": 8.251,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6534646443540480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}