{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0723860589812333,
  "eval_steps": 200,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17873100983020554,
      "grad_norm": 0.8090553879737854,
      "learning_rate": 9.999142157322298e-05,
      "loss": 0.5369,
      "step": 200
    },
    {
      "epoch": 0.17873100983020554,
      "eval_loss": 0.18719753623008728,
      "eval_runtime": 42.7752,
      "eval_samples_per_second": 4.231,
      "eval_steps_per_second": 2.127,
      "step": 200
    },
    {
      "epoch": 0.3574620196604111,
      "grad_norm": 0.41231265664100647,
      "learning_rate": 9.95497608932715e-05,
      "loss": 0.1347,
      "step": 400
    },
    {
      "epoch": 0.3574620196604111,
      "eval_loss": 0.1247013583779335,
      "eval_runtime": 42.7006,
      "eval_samples_per_second": 4.239,
      "eval_steps_per_second": 2.131,
      "step": 400
    },
    {
      "epoch": 0.5361930294906166,
      "grad_norm": 0.23166905343532562,
      "learning_rate": 9.844466810070319e-05,
      "loss": 0.1059,
      "step": 600
    },
    {
      "epoch": 0.5361930294906166,
      "eval_loss": 0.1143762394785881,
      "eval_runtime": 42.7658,
      "eval_samples_per_second": 4.232,
      "eval_steps_per_second": 2.128,
      "step": 600
    },
    {
      "epoch": 0.7149240393208222,
      "grad_norm": 0.2017158418893814,
      "learning_rate": 9.669093951406317e-05,
      "loss": 0.0996,
      "step": 800
    },
    {
      "epoch": 0.7149240393208222,
      "eval_loss": 0.1081576719880104,
      "eval_runtime": 42.705,
      "eval_samples_per_second": 4.238,
      "eval_steps_per_second": 2.131,
      "step": 800
    },
    {
      "epoch": 0.8936550491510277,
      "grad_norm": 0.1813146024942398,
      "learning_rate": 9.431205617221452e-05,
      "loss": 0.0946,
      "step": 1000
    },
    {
      "epoch": 0.8936550491510277,
      "eval_loss": 0.10373637080192566,
      "eval_runtime": 43.753,
      "eval_samples_per_second": 4.137,
      "eval_steps_per_second": 2.08,
      "step": 1000
    },
    {
      "epoch": 1.0723860589812333,
      "grad_norm": 0.2062540054321289,
      "learning_rate": 9.133986944179754e-05,
      "loss": 0.0893,
      "step": 1200
    },
    {
      "epoch": 1.0723860589812333,
      "eval_loss": 0.10310747474431992,
      "eval_runtime": 43.7372,
      "eval_samples_per_second": 4.138,
      "eval_steps_per_second": 2.081,
      "step": 1200
    }
  ],
  "logging_steps": 200,
  "max_steps": 5595,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0081270048991232e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}