{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.832,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.064,
      "grad_norm": 2.67690372467041,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8906,
      "step": 1
    },
    {
      "epoch": 0.128,
      "grad_norm": 2.5836398601531982,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8844,
      "step": 2
    },
    {
      "epoch": 0.192,
      "grad_norm": 2.692220687866211,
      "learning_rate": 6e-06,
      "loss": 0.7934,
      "step": 3
    },
    {
      "epoch": 0.256,
      "grad_norm": 2.424602508544922,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8946,
      "step": 4
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.7447768449783325,
      "learning_rate": 1e-05,
      "loss": 0.7398,
      "step": 5
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.985548734664917,
      "learning_rate": 9.984586668665641e-06,
      "loss": 0.7794,
      "step": 6
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.9407026171684265,
      "learning_rate": 9.938441702975689e-06,
      "loss": 0.7591,
      "step": 7
    },
    {
      "epoch": 0.512,
      "grad_norm": 1.5231335163116455,
      "learning_rate": 9.861849601988384e-06,
      "loss": 0.7895,
      "step": 8
    },
    {
      "epoch": 0.576,
      "grad_norm": 1.7350199222564697,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.8721,
      "step": 9
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.5788978338241577,
      "learning_rate": 9.619397662556434e-06,
      "loss": 0.8114,
      "step": 10
    },
    {
      "epoch": 0.704,
      "grad_norm": 1.2389469146728516,
      "learning_rate": 9.45503262094184e-06,
      "loss": 0.7008,
      "step": 11
    },
    {
      "epoch": 0.768,
      "grad_norm": 1.423549771308899,
      "learning_rate": 9.263200821770462e-06,
      "loss": 0.7585,
      "step": 12
    },
    {
      "epoch": 0.832,
      "grad_norm": 1.1815698146820068,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.6632,
      "step": 13
    },
    {
      "epoch": 0.896,
      "grad_norm": 1.1034165620803833,
      "learning_rate": 8.802029828000157e-06,
      "loss": 0.7416,
      "step": 14
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.8475093245506287,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.7517,
      "step": 15
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8475093245506287,
      "learning_rate": 8.247240241650918e-06,
      "loss": 0.7802,
      "step": 16
    },
    {
      "epoch": 1.064,
      "grad_norm": 1.1045087575912476,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.6967,
      "step": 17
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.6255977153778076,
      "learning_rate": 7.612492823579744e-06,
      "loss": 0.6597,
      "step": 18
    },
    {
      "epoch": 1.192,
      "grad_norm": 0.7395212054252625,
      "learning_rate": 7.269952498697734e-06,
      "loss": 0.6748,
      "step": 19
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.6993595957756042,
      "learning_rate": 6.913417161825449e-06,
      "loss": 0.7681,
      "step": 20
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.7346011996269226,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.7262,
      "step": 21
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.6753884553909302,
      "learning_rate": 6.1672268192795285e-06,
      "loss": 0.6249,
      "step": 22
    },
    {
      "epoch": 1.448,
      "grad_norm": 0.7035785913467407,
      "learning_rate": 5.782172325201155e-06,
      "loss": 0.6907,
      "step": 23
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.6587271094322205,
      "learning_rate": 5.392295478639226e-06,
      "loss": 0.6754,
      "step": 24
    },
    {
      "epoch": 1.576,
      "grad_norm": 0.5424773097038269,
      "learning_rate": 5e-06,
      "loss": 0.6626,
      "step": 25
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.5312824845314026,
      "learning_rate": 4.6077045213607765e-06,
      "loss": 0.7369,
      "step": 26
    },
    {
      "epoch": 1.704,
      "grad_norm": 0.5092198848724365,
      "learning_rate": 4.217827674798845e-06,
      "loss": 0.766,
      "step": 27
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.49842214584350586,
      "learning_rate": 3.832773180720475e-06,
      "loss": 0.7003,
      "step": 28
    },
    {
      "epoch": 1.8319999999999999,
      "grad_norm": 0.5175044536590576,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.7393,
      "step": 29
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.48302003741264343,
      "learning_rate": 3.0865828381745515e-06,
      "loss": 0.7018,
      "step": 30
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.4566391110420227,
      "learning_rate": 2.7300475013022666e-06,
      "loss": 0.6598,
      "step": 31
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6593987941741943,
      "learning_rate": 2.387507176420256e-06,
      "loss": 0.651,
      "step": 32
    },
    {
      "epoch": 2.064,
      "grad_norm": 0.6568493843078613,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.7002,
      "step": 33
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.4518449306488037,
      "learning_rate": 1.7527597583490825e-06,
      "loss": 0.7008,
      "step": 34
    },
    {
      "epoch": 2.192,
      "grad_norm": 0.4067769944667816,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.6299,
      "step": 35
    },
    {
      "epoch": 2.2560000000000002,
      "grad_norm": 0.41410645842552185,
      "learning_rate": 1.1979701719998454e-06,
      "loss": 0.6832,
      "step": 36
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.33175525069236755,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.5874,
      "step": 37
    },
    {
      "epoch": 2.384,
      "grad_norm": 0.4822118580341339,
      "learning_rate": 7.367991782295392e-07,
      "loss": 0.6533,
      "step": 38
    },
    {
      "epoch": 2.448,
      "grad_norm": 0.4443027079105377,
      "learning_rate": 5.449673790581611e-07,
      "loss": 0.7716,
      "step": 39
    },
    {
      "epoch": 2.512,
      "grad_norm": 0.38352447748184204,
      "learning_rate": 3.8060233744356634e-07,
      "loss": 0.7014,
      "step": 40
    },
    {
      "epoch": 2.576,
      "grad_norm": 0.39618387818336487,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.5842,
      "step": 41
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.3571045398712158,
      "learning_rate": 1.3815039801161723e-07,
      "loss": 0.6552,
      "step": 42
    },
    {
      "epoch": 2.7039999999999997,
      "grad_norm": 0.44936269521713257,
      "learning_rate": 6.15582970243117e-08,
      "loss": 0.6133,
      "step": 43
    },
    {
      "epoch": 2.768,
      "grad_norm": 0.40641671419143677,
      "learning_rate": 1.541333133436018e-08,
      "loss": 0.6315,
      "step": 44
    },
    {
      "epoch": 2.832,
      "grad_norm": 0.4280812740325928,
      "learning_rate": 0.0,
      "loss": 0.6455,
      "step": 45
    },
    {
      "epoch": 2.832,
      "step": 45,
      "total_flos": 75420674818048.0,
      "train_loss": 0.7178263836436801,
      "train_runtime": 10468.2018,
      "train_samples_per_second": 0.287,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 1,
  "max_steps": 45,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 75420674818048.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}