{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 8.472058296203613,
      "learning_rate": 9.5e-05,
      "loss": 0.2548,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.20547232031822205,
      "eval_mse": 0.20547235012054443,
      "eval_runtime": 1.3582,
      "eval_samples_per_second": 14.725,
      "eval_steps_per_second": 2.209,
      "step": 10
    },
    {
      "epoch": 2.0,
      "grad_norm": 16.11898422241211,
      "learning_rate": 9e-05,
      "loss": 0.4596,
      "step": 20
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.10995284467935562,
      "eval_mse": 0.10995285212993622,
      "eval_runtime": 0.9281,
      "eval_samples_per_second": 21.551,
      "eval_steps_per_second": 3.233,
      "step": 20
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.556423187255859,
      "learning_rate": 8.5e-05,
      "loss": 0.0866,
      "step": 30
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.12321324646472931,
      "eval_mse": 0.12321324646472931,
      "eval_runtime": 0.8771,
      "eval_samples_per_second": 22.803,
      "eval_steps_per_second": 3.42,
      "step": 30
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.101408958435059,
      "learning_rate": 8e-05,
      "loss": 0.0741,
      "step": 40
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.055902622640132904,
      "eval_mse": 0.05590261146426201,
      "eval_runtime": 0.8907,
      "eval_samples_per_second": 22.455,
      "eval_steps_per_second": 3.368,
      "step": 40
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.8052617311477661,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0471,
      "step": 50
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.033162668347358704,
      "eval_mse": 0.033162668347358704,
      "eval_runtime": 0.8798,
      "eval_samples_per_second": 22.732,
      "eval_steps_per_second": 3.41,
      "step": 50
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.320048809051514,
      "learning_rate": 7e-05,
      "loss": 0.0206,
      "step": 60
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.0486394502222538,
      "eval_mse": 0.0486394464969635,
      "eval_runtime": 0.9146,
      "eval_samples_per_second": 21.867,
      "eval_steps_per_second": 3.28,
      "step": 60
    },
    {
      "epoch": 7.0,
      "grad_norm": 4.353482246398926,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.0136,
      "step": 70
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.03369127959012985,
      "eval_mse": 0.03369127959012985,
      "eval_runtime": 0.9267,
      "eval_samples_per_second": 21.582,
      "eval_steps_per_second": 3.237,
      "step": 70
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.3020066022872925,
      "learning_rate": 6e-05,
      "loss": 0.0065,
      "step": 80
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.03295436501502991,
      "eval_mse": 0.032954368740320206,
      "eval_runtime": 0.8738,
      "eval_samples_per_second": 22.889,
      "eval_steps_per_second": 3.433,
      "step": 80
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.6798593997955322,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0054,
      "step": 90
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.03235679119825363,
      "eval_mse": 0.03235679119825363,
      "eval_runtime": 0.911,
      "eval_samples_per_second": 21.953,
      "eval_steps_per_second": 3.293,
      "step": 90
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.5722326040267944,
      "learning_rate": 5e-05,
      "loss": 0.0023,
      "step": 100
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.03351482003927231,
      "eval_mse": 0.03351482003927231,
      "eval_runtime": 0.9079,
      "eval_samples_per_second": 22.029,
      "eval_steps_per_second": 3.304,
      "step": 100
    },
    {
      "epoch": 11.0,
      "grad_norm": 1.5198137760162354,
      "learning_rate": 4.5e-05,
      "loss": 0.0035,
      "step": 110
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.03029645048081875,
      "eval_mse": 0.030296454206109047,
      "eval_runtime": 0.8889,
      "eval_samples_per_second": 22.5,
      "eval_steps_per_second": 3.375,
      "step": 110
    },
    {
      "epoch": 12.0,
      "grad_norm": 2.942338705062866,
      "learning_rate": 4e-05,
      "loss": 0.0029,
      "step": 120
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.03209378570318222,
      "eval_mse": 0.03209378197789192,
      "eval_runtime": 0.9137,
      "eval_samples_per_second": 21.889,
      "eval_steps_per_second": 3.283,
      "step": 120
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.5375175476074219,
      "learning_rate": 3.5e-05,
      "loss": 0.0035,
      "step": 130
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.03165650740265846,
      "eval_mse": 0.03165651112794876,
      "eval_runtime": 0.9157,
      "eval_samples_per_second": 21.84,
      "eval_steps_per_second": 3.276,
      "step": 130
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.43184858560562134,
      "learning_rate": 3e-05,
      "loss": 0.0011,
      "step": 140
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.03108842670917511,
      "eval_mse": 0.03108843043446541,
      "eval_runtime": 0.889,
      "eval_samples_per_second": 22.498,
      "eval_steps_per_second": 3.375,
      "step": 140
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.3797425925731659,
      "learning_rate": 2.5e-05,
      "loss": 0.0007,
      "step": 150
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.029892250895500183,
      "eval_mse": 0.029892250895500183,
      "eval_runtime": 0.9199,
      "eval_samples_per_second": 21.742,
      "eval_steps_per_second": 3.261,
      "step": 150
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.3728632926940918,
      "learning_rate": 2e-05,
      "loss": 0.0004,
      "step": 160
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.029963841661810875,
      "eval_mse": 0.029963845387101173,
      "eval_runtime": 0.9532,
      "eval_samples_per_second": 20.981,
      "eval_steps_per_second": 3.147,
      "step": 160
    },
    {
      "epoch": 17.0,
      "grad_norm": 0.7130188941955566,
      "learning_rate": 1.5e-05,
      "loss": 0.0003,
      "step": 170
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.03030126914381981,
      "eval_mse": 0.03030126728117466,
      "eval_runtime": 0.8824,
      "eval_samples_per_second": 22.665,
      "eval_steps_per_second": 3.4,
      "step": 170
    },
    {
      "epoch": 18.0,
      "grad_norm": 0.05147755146026611,
      "learning_rate": 1e-05,
      "loss": 0.0001,
      "step": 180
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.03000779077410698,
      "eval_mse": 0.03000778891146183,
      "eval_runtime": 0.9309,
      "eval_samples_per_second": 21.484,
      "eval_steps_per_second": 3.223,
      "step": 180
    },
    {
      "epoch": 19.0,
      "grad_norm": 0.17308902740478516,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 19.0,
      "eval_loss": 0.030044889077544212,
      "eval_mse": 0.03004489280283451,
      "eval_runtime": 0.8961,
      "eval_samples_per_second": 22.32,
      "eval_steps_per_second": 3.348,
      "step": 190
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.0706406906247139,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}