{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.962406015037594,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3,
      "learning_rate": 6.25e-05,
      "loss": 10.8217,
      "step": 5
    },
    {
      "epoch": 0.6,
      "learning_rate": 9.995728791936504e-05,
      "loss": 10.8213,
      "step": 10
    },
    {
      "epoch": 0.9,
      "learning_rate": 9.947761466636014e-05,
      "loss": 10.8201,
      "step": 15
    },
    {
      "epoch": 0.96,
      "eval_loss": 10.819129943847656,
      "eval_runtime": 6.4186,
      "eval_samples_per_second": 69.174,
      "eval_steps_per_second": 17.294,
      "step": 16
    },
    {
      "epoch": 1.24,
      "learning_rate": 9.847001329696653e-05,
      "loss": 12.1716,
      "step": 20
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.694523495787149e-05,
      "loss": 10.8181,
      "step": 25
    },
    {
      "epoch": 1.84,
      "learning_rate": 9.491954909459895e-05,
      "loss": 10.8167,
      "step": 30
    },
    {
      "epoch": 1.96,
      "eval_loss": 10.81454086303711,
      "eval_runtime": 6.3633,
      "eval_samples_per_second": 69.775,
      "eval_steps_per_second": 17.444,
      "step": 32
    },
    {
      "epoch": 2.18,
      "learning_rate": 9.241456985587868e-05,
      "loss": 12.1668,
      "step": 35
    },
    {
      "epoch": 2.48,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.8133,
      "step": 40
    },
    {
      "epoch": 2.78,
      "learning_rate": 8.60784730526531e-05,
      "loss": 10.8117,
      "step": 45
    },
    {
      "epoch": 2.96,
      "eval_loss": 10.809527397155762,
      "eval_runtime": 6.247,
      "eval_samples_per_second": 71.074,
      "eval_steps_per_second": 17.769,
      "step": 48
    },
    {
      "epoch": 3.12,
      "learning_rate": 8.231496189304704e-05,
      "loss": 12.1615,
      "step": 50
    },
    {
      "epoch": 3.42,
      "learning_rate": 7.820664880476256e-05,
      "loss": 10.8084,
      "step": 55
    },
    {
      "epoch": 3.72,
      "learning_rate": 7.379736965185368e-05,
      "loss": 10.8058,
      "step": 60
    },
    {
      "epoch": 3.96,
      "eval_loss": 10.802533149719238,
      "eval_runtime": 5.8936,
      "eval_samples_per_second": 75.335,
      "eval_steps_per_second": 18.834,
      "step": 64
    },
    {
      "epoch": 4.06,
      "learning_rate": 6.91341716182545e-05,
      "loss": 12.1538,
      "step": 65
    },
    {
      "epoch": 4.36,
      "learning_rate": 6.426681121245527e-05,
      "loss": 10.802,
      "step": 70
    },
    {
      "epoch": 4.66,
      "learning_rate": 5.924722336357793e-05,
      "loss": 10.8007,
      "step": 75
    },
    {
      "epoch": 4.96,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 10.7997,
      "step": 80
    },
    {
      "epoch": 4.96,
      "eval_loss": 10.798870086669922,
      "eval_runtime": 6.2383,
      "eval_samples_per_second": 71.174,
      "eval_steps_per_second": 17.793,
      "step": 80
    },
    {
      "epoch": 5.3,
      "learning_rate": 4.8966654938622295e-05,
      "loss": 12.148,
      "step": 85
    },
    {
      "epoch": 5.6,
      "learning_rate": 4.381536843653262e-05,
      "loss": 10.7968,
      "step": 90
    },
    {
      "epoch": 5.9,
      "learning_rate": 3.87300721992097e-05,
      "loss": 10.7959,
      "step": 95
    },
    {
      "epoch": 5.96,
      "eval_loss": 10.794721603393555,
      "eval_runtime": 6.3176,
      "eval_samples_per_second": 70.28,
      "eval_steps_per_second": 17.57,
      "step": 96
    },
    {
      "epoch": 6.24,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 12.1442,
      "step": 100
    },
    {
      "epoch": 6.54,
      "learning_rate": 2.8973208692864624e-05,
      "loss": 10.7943,
      "step": 105
    },
    {
      "epoch": 6.84,
      "learning_rate": 2.4405747545519963e-05,
      "loss": 10.7934,
      "step": 110
    },
    {
      "epoch": 6.96,
      "eval_loss": 10.792530059814453,
      "eval_runtime": 6.3054,
      "eval_samples_per_second": 70.416,
      "eval_steps_per_second": 17.604,
      "step": 112
    },
    {
      "epoch": 7.18,
      "learning_rate": 2.0111378089837956e-05,
      "loss": 12.1419,
      "step": 115
    },
    {
      "epoch": 7.48,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 10.7926,
      "step": 120
    },
    {
      "epoch": 7.78,
      "learning_rate": 1.2521795812943704e-05,
      "loss": 10.7924,
      "step": 125
    },
    {
      "epoch": 7.96,
      "eval_loss": 10.791926383972168,
      "eval_runtime": 5.785,
      "eval_samples_per_second": 76.75,
      "eval_steps_per_second": 19.187,
      "step": 128
    },
    {
      "epoch": 8.12,
      "learning_rate": 9.307564136490254e-06,
      "loss": 12.1411,
      "step": 130
    },
    {
      "epoch": 8.42,
      "learning_rate": 6.527522369181655e-06,
      "loss": 10.7921,
      "step": 135
    },
    {
      "epoch": 8.72,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 10.7921,
      "step": 140
    },
    {
      "epoch": 8.96,
      "eval_loss": 10.79179859161377,
      "eval_runtime": 6.2936,
      "eval_samples_per_second": 70.548,
      "eval_steps_per_second": 17.637,
      "step": 144
    },
    {
      "epoch": 9.06,
      "learning_rate": 2.3837118562592797e-06,
      "loss": 12.1411,
      "step": 145
    },
    {
      "epoch": 9.36,
      "learning_rate": 1.064157733632276e-06,
      "loss": 10.792,
      "step": 150
    },
    {
      "epoch": 9.66,
      "learning_rate": 2.667509943378721e-07,
      "loss": 10.792,
      "step": 155
    },
    {
      "epoch": 9.96,
      "learning_rate": 0.0,
      "loss": 10.792,
      "step": 160
    },
    {
      "epoch": 9.96,
      "eval_loss": 10.791767120361328,
      "eval_runtime": 5.8131,
      "eval_samples_per_second": 76.379,
      "eval_steps_per_second": 19.095,
      "step": 160
    },
    {
      "epoch": 9.96,
      "step": 160,
      "total_flos": 39596851200.0,
      "train_loss": 11.18234748840332,
      "train_runtime": 256.0921,
      "train_samples_per_second": 332.537,
      "train_steps_per_second": 0.625
    }
  ],
  "max_steps": 160,
  "num_train_epochs": 10,
  "total_flos": 39596851200.0,
  "trial_name": null,
  "trial_params": null
}