{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.599552035331726,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.6745,
      "step": 10
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7566113471984863,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.1165,
      "step": 20
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.7895037531852722,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 1.0005,
      "step": 30
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.9041371941566467,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.9161,
      "step": 40
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.5681982040405273,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.8706,
      "step": 50
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.3350074291229248,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 0.6968,
      "step": 60
    },
    {
      "epoch": 2.8,
      "grad_norm": 3.031379222869873,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.6251,
      "step": 70
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.9845056533813477,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 0.5596,
      "step": 80
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.8699216842651367,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 0.4151,
      "step": 90
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.090395450592041,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.4593,
      "step": 100
    },
    {
      "epoch": 4.4,
      "grad_norm": 4.337036609649658,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 0.3523,
      "step": 110
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.6753166913986206,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 0.2795,
      "step": 120
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.229514241218567,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 0.2316,
      "step": 130
    },
    {
      "epoch": 5.6,
      "grad_norm": 3.4132261276245117,
      "learning_rate": 9.651005032974994e-06,
      "loss": 0.1902,
      "step": 140
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.828024387359619,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.2474,
      "step": 150
    },
    {
      "epoch": 6.4,
      "grad_norm": 2.4975504875183105,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.1158,
      "step": 160
    },
    {
      "epoch": 6.8,
      "grad_norm": 0.9191762208938599,
      "learning_rate": 5.616288532109225e-06,
      "loss": 0.0792,
      "step": 170
    },
    {
      "epoch": 7.2,
      "grad_norm": 0.6133431792259216,
      "learning_rate": 4.408070965292534e-06,
      "loss": 0.0685,
      "step": 180
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.393449068069458,
      "learning_rate": 3.308693936411421e-06,
      "loss": 0.0354,
      "step": 190
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.0987842082977295,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.0431,
      "step": 200
    },
    {
      "epoch": 8.4,
      "grad_norm": 0.27947095036506653,
      "learning_rate": 1.5195190384357405e-06,
      "loss": 0.0141,
      "step": 210
    },
    {
      "epoch": 8.8,
      "grad_norm": 0.2128460854291916,
      "learning_rate": 8.645454235739903e-07,
      "loss": 0.0148,
      "step": 220
    },
    {
      "epoch": 9.2,
      "grad_norm": 0.27845025062561035,
      "learning_rate": 3.8738304061681107e-07,
      "loss": 0.0074,
      "step": 230
    },
    {
      "epoch": 9.6,
      "grad_norm": 0.5408875942230225,
      "learning_rate": 9.731931258429638e-08,
      "loss": 0.0085,
      "step": 240
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.4381401240825653,
      "learning_rate": 0.0,
      "loss": 0.0063,
      "step": 250
    },
    {
      "epoch": 10.0,
      "step": 250,
      "total_flos": 1.2690688742965248e+16,
      "train_loss": 0.4011231598258018,
      "train_runtime": 16356.6727,
      "train_samples_per_second": 0.061,
      "train_steps_per_second": 0.015
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2690688742965248e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}