{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018096817976172522,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006032272658724174,
      "eval_loss": 10.375473976135254,
      "eval_runtime": 3.6489,
      "eval_samples_per_second": 191.563,
      "eval_steps_per_second": 95.918,
      "step": 1
    },
    {
      "epoch": 0.0018096817976172522,
      "grad_norm": 0.03265144303441048,
      "learning_rate": 3e-05,
      "loss": 10.375,
      "step": 3
    },
    {
      "epoch": 0.003016136329362087,
      "eval_loss": 10.375377655029297,
      "eval_runtime": 3.6411,
      "eval_samples_per_second": 191.977,
      "eval_steps_per_second": 96.126,
      "step": 5
    },
    {
      "epoch": 0.0036193635952345045,
      "grad_norm": 0.02685490809381008,
      "learning_rate": 6e-05,
      "loss": 10.3773,
      "step": 6
    },
    {
      "epoch": 0.005429045392851757,
      "grad_norm": 0.027488619089126587,
      "learning_rate": 9e-05,
      "loss": 10.3759,
      "step": 9
    },
    {
      "epoch": 0.006032272658724174,
      "eval_loss": 10.375048637390137,
      "eval_runtime": 3.6542,
      "eval_samples_per_second": 191.287,
      "eval_steps_per_second": 95.78,
      "step": 10
    },
    {
      "epoch": 0.007238727190469009,
      "grad_norm": 0.03698119521141052,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3748,
      "step": 12
    },
    {
      "epoch": 0.009048408988086261,
      "grad_norm": 0.023825794458389282,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3752,
      "step": 15
    },
    {
      "epoch": 0.009048408988086261,
      "eval_loss": 10.37456226348877,
      "eval_runtime": 3.689,
      "eval_samples_per_second": 189.484,
      "eval_steps_per_second": 94.878,
      "step": 15
    },
    {
      "epoch": 0.010858090785703513,
      "grad_norm": 0.029680514708161354,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3744,
      "step": 18
    },
    {
      "epoch": 0.012064545317448348,
      "eval_loss": 10.374188423156738,
      "eval_runtime": 3.6606,
      "eval_samples_per_second": 190.954,
      "eval_steps_per_second": 95.614,
      "step": 20
    },
    {
      "epoch": 0.012667772583320766,
      "grad_norm": 0.027766700834035873,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 10.3737,
      "step": 21
    },
    {
      "epoch": 0.014477454380938018,
      "grad_norm": 0.037035077810287476,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3747,
      "step": 24
    },
    {
      "epoch": 0.015080681646810435,
      "eval_loss": 10.37399673461914,
      "eval_runtime": 3.6845,
      "eval_samples_per_second": 189.714,
      "eval_steps_per_second": 94.993,
      "step": 25
    },
    {
      "epoch": 0.016287136178555272,
      "grad_norm": 0.027561597526073456,
      "learning_rate": 5.449673790581611e-06,
      "loss": 10.3736,
      "step": 27
    },
    {
      "epoch": 0.018096817976172522,
      "grad_norm": 0.035397447645664215,
      "learning_rate": 0.0,
      "loss": 10.3744,
      "step": 30
    },
    {
      "epoch": 0.018096817976172522,
      "eval_loss": 10.3739595413208,
      "eval_runtime": 3.7296,
      "eval_samples_per_second": 187.419,
      "eval_steps_per_second": 93.843,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1569073397760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}