{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13183915622940012,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013183915622940012,
      "eval_loss": 2.959343671798706,
      "eval_runtime": 4.375,
      "eval_samples_per_second": 36.572,
      "eval_steps_per_second": 18.286,
      "step": 1
    },
    {
      "epoch": 0.013183915622940013,
      "grad_norm": 2.8018999099731445,
      "learning_rate": 0.00019967573081342103,
      "loss": 2.226,
      "step": 10
    },
    {
      "epoch": 0.026367831245880026,
      "grad_norm": 2.211209535598755,
      "learning_rate": 0.0001970941817426052,
      "loss": 1.5754,
      "step": 20
    },
    {
      "epoch": 0.03955174686882004,
      "grad_norm": 1.9760048389434814,
      "learning_rate": 0.00019199794436588243,
      "loss": 1.3827,
      "step": 30
    },
    {
      "epoch": 0.05273566249176005,
      "grad_norm": 2.5705409049987793,
      "learning_rate": 0.0001845190085543795,
      "loss": 1.3755,
      "step": 40
    },
    {
      "epoch": 0.06591957811470006,
      "grad_norm": 2.566218852996826,
      "learning_rate": 0.00017485107481711012,
      "loss": 1.4399,
      "step": 50
    },
    {
      "epoch": 0.06591957811470006,
      "eval_loss": 1.2694450616836548,
      "eval_runtime": 4.3616,
      "eval_samples_per_second": 36.684,
      "eval_steps_per_second": 18.342,
      "step": 50
    },
    {
      "epoch": 0.07910349373764008,
      "grad_norm": 2.1022636890411377,
      "learning_rate": 0.00016324453755953773,
      "loss": 1.2797,
      "step": 60
    },
    {
      "epoch": 0.0922874093605801,
      "grad_norm": 2.0848679542541504,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3117,
      "step": 70
    },
    {
      "epoch": 0.1054713249835201,
      "grad_norm": 2.1038565635681152,
      "learning_rate": 0.00013546048870425356,
      "loss": 1.2998,
      "step": 80
    },
    {
      "epoch": 0.11865524060646011,
      "grad_norm": 2.0592269897460938,
      "learning_rate": 0.00012000256937760445,
      "loss": 1.3859,
      "step": 90
    },
    {
      "epoch": 0.13183915622940012,
      "grad_norm": 1.9211629629135132,
      "learning_rate": 0.00010402659401094152,
      "loss": 1.2282,
      "step": 100
    },
    {
      "epoch": 0.13183915622940012,
      "eval_loss": 1.1935606002807617,
      "eval_runtime": 4.3651,
      "eval_samples_per_second": 36.654,
      "eval_steps_per_second": 18.327,
      "step": 100
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4967074313011200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}