{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 464,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04310344827586207,
      "grad_norm": 0.22970597445964813,
      "learning_rate": 3.2142857142857144e-05,
      "loss": 0.5477,
      "step": 10
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 0.24922381341457367,
      "learning_rate": 4.99847706754774e-05,
      "loss": 0.4192,
      "step": 20
    },
    {
      "epoch": 0.12931034482758622,
      "grad_norm": 0.1861911565065384,
      "learning_rate": 4.9863047384206835e-05,
      "loss": 0.2814,
      "step": 30
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.16707484424114227,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.2082,
      "step": 40
    },
    {
      "epoch": 0.21551724137931033,
      "grad_norm": 0.17490606009960175,
      "learning_rate": 4.925739315689991e-05,
      "loss": 0.1599,
      "step": 50
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 0.16346780955791473,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.144,
      "step": 60
    },
    {
      "epoch": 0.3017241379310345,
      "grad_norm": 0.16197219491004944,
      "learning_rate": 4.817959636416969e-05,
      "loss": 0.123,
      "step": 70
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.1676415354013443,
      "learning_rate": 4.7469851157479177e-05,
      "loss": 0.1168,
      "step": 80
    },
    {
      "epoch": 0.3879310344827586,
      "grad_norm": 0.14542680978775024,
      "learning_rate": 4.665063509461097e-05,
      "loss": 0.1112,
      "step": 90
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 0.1882169097661972,
      "learning_rate": 4.572593931387604e-05,
      "loss": 0.1005,
      "step": 100
    },
    {
      "epoch": 0.47413793103448276,
      "grad_norm": 0.14488768577575684,
      "learning_rate": 4.4700268840168045e-05,
      "loss": 0.102,
      "step": 110
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.15230809152126312,
      "learning_rate": 4.357862063693486e-05,
      "loss": 0.103,
      "step": 120
    },
    {
      "epoch": 0.5603448275862069,
      "grad_norm": 0.13396801054477692,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 0.1035,
      "step": 130
    },
    {
      "epoch": 0.603448275862069,
      "grad_norm": 0.1350702941417694,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 0.0995,
      "step": 140
    },
    {
      "epoch": 0.646551724137931,
      "grad_norm": 0.1560034453868866,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.0979,
      "step": 150
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.13901282846927643,
      "learning_rate": 3.824798160583012e-05,
      "loss": 0.0947,
      "step": 160
    },
    {
      "epoch": 0.7327586206896551,
      "grad_norm": 0.18362534046173096,
      "learning_rate": 3.673678906964727e-05,
      "loss": 0.0969,
      "step": 170
    },
    {
      "epoch": 0.7758620689655172,
      "grad_norm": 0.17652247846126556,
      "learning_rate": 3.516841607689501e-05,
      "loss": 0.0905,
      "step": 180
    },
    {
      "epoch": 0.8189655172413793,
      "grad_norm": 0.1358911544084549,
      "learning_rate": 3.355050358314172e-05,
      "loss": 0.0925,
      "step": 190
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.1052212044596672,
      "learning_rate": 3.1890933895424976e-05,
      "loss": 0.0953,
      "step": 200
    },
    {
      "epoch": 0.9051724137931034,
      "grad_norm": 0.13334128260612488,
      "learning_rate": 3.0197792270443982e-05,
      "loss": 0.0886,
      "step": 210
    },
    {
      "epoch": 0.9482758620689655,
      "grad_norm": 0.12180697172880173,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 0.0914,
      "step": 220
    },
    {
      "epoch": 0.9913793103448276,
      "grad_norm": 0.1343410611152649,
      "learning_rate": 2.674391184360313e-05,
      "loss": 0.0887,
      "step": 230
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 0.13129718601703644,
      "learning_rate": 2.5e-05,
      "loss": 0.0993,
      "step": 240
    },
    {
      "epoch": 1.0775862068965518,
      "grad_norm": 0.12985403835773468,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 0.0925,
      "step": 250
    },
    {
      "epoch": 1.1206896551724137,
      "grad_norm": 0.10140767693519592,
      "learning_rate": 2.1520672475998373e-05,
      "loss": 0.086,
      "step": 260
    },
    {
      "epoch": 1.1637931034482758,
      "grad_norm": 0.10552043467760086,
      "learning_rate": 1.980220772955602e-05,
      "loss": 0.0885,
      "step": 270
    },
    {
      "epoch": 1.206896551724138,
      "grad_norm": 0.17615962028503418,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 0.0935,
      "step": 280
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.16146473586559296,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 0.089,
      "step": 290
    },
    {
      "epoch": 1.293103448275862,
      "grad_norm": 0.11695656925439835,
      "learning_rate": 1.4831583923104999e-05,
      "loss": 0.0934,
      "step": 300
    },
    {
      "epoch": 1.3362068965517242,
      "grad_norm": 0.13488854467868805,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 0.0902,
      "step": 310
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 0.14104993641376495,
      "learning_rate": 1.175201839416988e-05,
      "loss": 0.0915,
      "step": 320
    },
    {
      "epoch": 1.4224137931034484,
      "grad_norm": 0.11073966324329376,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.0904,
      "step": 330
    },
    {
      "epoch": 1.4655172413793103,
      "grad_norm": 0.12246192991733551,
      "learning_rate": 8.930309757836517e-06,
      "loss": 0.086,
      "step": 340
    },
    {
      "epoch": 1.5086206896551724,
      "grad_norm": 0.11951974779367447,
      "learning_rate": 7.633540738525066e-06,
      "loss": 0.0883,
      "step": 350
    },
    {
      "epoch": 1.5517241379310345,
      "grad_norm": 0.11673244833946228,
      "learning_rate": 6.421379363065142e-06,
      "loss": 0.0868,
      "step": 360
    },
    {
      "epoch": 1.5948275862068966,
      "grad_norm": 0.11525051295757294,
      "learning_rate": 5.299731159831953e-06,
      "loss": 0.0889,
      "step": 370
    },
    {
      "epoch": 1.6379310344827587,
      "grad_norm": 0.16884970664978027,
      "learning_rate": 4.274060686123959e-06,
      "loss": 0.0905,
      "step": 380
    },
    {
      "epoch": 1.6810344827586206,
      "grad_norm": 0.12776394188404083,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.0905,
      "step": 390
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 0.13251963257789612,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 0.0862,
      "step": 400
    },
    {
      "epoch": 1.7672413793103448,
      "grad_norm": 0.14248506724834442,
      "learning_rate": 1.8204036358303173e-06,
      "loss": 0.09,
      "step": 410
    },
    {
      "epoch": 1.8103448275862069,
      "grad_norm": 0.10634557157754898,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.0839,
      "step": 420
    },
    {
      "epoch": 1.853448275862069,
      "grad_norm": 0.12421922385692596,
      "learning_rate": 7.426068431000882e-07,
      "loss": 0.088,
      "step": 430
    },
    {
      "epoch": 1.896551724137931,
      "grad_norm": 0.12003956735134125,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 0.0932,
      "step": 440
    },
    {
      "epoch": 1.9396551724137931,
      "grad_norm": 0.10775435715913773,
      "learning_rate": 1.3695261579316777e-07,
      "loss": 0.0842,
      "step": 450
    },
    {
      "epoch": 1.9827586206896552,
      "grad_norm": 0.13052473962306976,
      "learning_rate": 1.522932452260595e-08,
      "loss": 0.0894,
      "step": 460
    },
    {
      "epoch": 2.0,
      "step": 464,
      "total_flos": 2.4087255599087616e+17,
      "train_loss": 0.11968068110531774,
      "train_runtime": 7304.8453,
      "train_samples_per_second": 1.016,
      "train_steps_per_second": 0.064
    }
  ],
  "logging_steps": 10,
  "max_steps": 464,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4087255599087616e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}