{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1771,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028232636928289104,
      "grad_norm": 1.75,
      "learning_rate": 4.537037037037038e-06,
      "loss": 0.7356,
      "step": 50
    },
    {
      "epoch": 0.05646527385657821,
      "grad_norm": 2.21875,
      "learning_rate": 4.991530674368419e-06,
      "loss": 0.6929,
      "step": 100
    },
    {
      "epoch": 0.08469791078486731,
      "grad_norm": 1.6953125,
      "learning_rate": 4.962327657422145e-06,
      "loss": 0.6668,
      "step": 150
    },
    {
      "epoch": 0.11293054771315642,
      "grad_norm": 1.3515625,
      "learning_rate": 4.91253057525732e-06,
      "loss": 0.6428,
      "step": 200
    },
    {
      "epoch": 0.1411631846414455,
      "grad_norm": 1.546875,
      "learning_rate": 4.8425559136144585e-06,
      "loss": 0.662,
      "step": 250
    },
    {
      "epoch": 0.16939582156973462,
      "grad_norm": 1.8046875,
      "learning_rate": 4.752988916598333e-06,
      "loss": 0.644,
      "step": 300
    },
    {
      "epoch": 0.1976284584980237,
      "grad_norm": 1.6953125,
      "learning_rate": 4.644578691896712e-06,
      "loss": 0.6516,
      "step": 350
    },
    {
      "epoch": 0.22586109542631283,
      "grad_norm": 2.109375,
      "learning_rate": 4.518231945500217e-06,
      "loss": 0.6616,
      "step": 400
    },
    {
      "epoch": 0.2540937323546019,
      "grad_norm": 1.7421875,
      "learning_rate": 4.375005398323957e-06,
      "loss": 0.6432,
      "step": 450
    },
    {
      "epoch": 0.282326369282891,
      "grad_norm": 1.65625,
      "learning_rate": 4.216096948155693e-06,
      "loss": 0.652,
      "step": 500
    },
    {
      "epoch": 0.3105590062111801,
      "grad_norm": 2.125,
      "learning_rate": 4.042835650849013e-06,
      "loss": 0.6376,
      "step": 550
    },
    {
      "epoch": 0.33879164313946925,
      "grad_norm": 2.0625,
      "learning_rate": 3.856670604555346e-06,
      "loss": 0.6358,
      "step": 600
    },
    {
      "epoch": 0.36702428006775834,
      "grad_norm": 1.7421875,
      "learning_rate": 3.6591588299633184e-06,
      "loss": 0.6363,
      "step": 650
    },
    {
      "epoch": 0.3952569169960474,
      "grad_norm": 1.578125,
      "learning_rate": 3.4519522479109736e-06,
      "loss": 0.6386,
      "step": 700
    },
    {
      "epoch": 0.4234895539243365,
      "grad_norm": 3.453125,
      "learning_rate": 3.236783863285632e-06,
      "loss": 0.6448,
      "step": 750
    },
    {
      "epoch": 0.45172219085262566,
      "grad_norm": 2.1875,
      "learning_rate": 3.015453270764544e-06,
      "loss": 0.63,
      "step": 800
    },
    {
      "epoch": 0.47995482778091475,
      "grad_norm": 2.5625,
      "learning_rate": 2.7898116036213417e-06,
      "loss": 0.6377,
      "step": 850
    },
    {
      "epoch": 0.5081874647092038,
      "grad_norm": 2.640625,
      "learning_rate": 2.5617460514813238e-06,
      "loss": 0.638,
      "step": 900
    },
    {
      "epoch": 0.536420101637493,
      "grad_norm": 2.0625,
      "learning_rate": 2.333164076513759e-06,
      "loss": 0.6339,
      "step": 950
    },
    {
      "epoch": 0.564652738565782,
      "grad_norm": 2.125,
      "learning_rate": 2.105977460071578e-06,
      "loss": 0.6215,
      "step": 1000
    },
    {
      "epoch": 0.5928853754940712,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8820863132068939e-06,
      "loss": 0.6411,
      "step": 1050
    },
    {
      "epoch": 0.6211180124223602,
      "grad_norm": 1.140625,
      "learning_rate": 1.663363184792921e-06,
      "loss": 0.6317,
      "step": 1100
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 1.7890625,
      "learning_rate": 1.4516374001665143e-06,
      "loss": 0.6287,
      "step": 1150
    },
    {
      "epoch": 0.6775832862789385,
      "grad_norm": 1.203125,
      "learning_rate": 1.2486797612775693e-06,
      "loss": 0.6498,
      "step": 1200
    },
    {
      "epoch": 0.7058159232072275,
      "grad_norm": 1.59375,
      "learning_rate": 1.0561877363079853e-06,
      "loss": 0.6423,
      "step": 1250
    },
    {
      "epoch": 0.7340485601355167,
      "grad_norm": 2.078125,
      "learning_rate": 8.75771262629145e-07,
      "loss": 0.6316,
      "step": 1300
    },
    {
      "epoch": 0.7622811970638057,
      "grad_norm": 1.1171875,
      "learning_rate": 7.089392818371207e-07,
      "loss": 0.6361,
      "step": 1350
    },
    {
      "epoch": 0.7905138339920948,
      "grad_norm": 1.859375,
      "learning_rate": 5.570871194819521e-07,
      "loss": 0.6243,
      "step": 1400
    },
    {
      "epoch": 0.818746470920384,
      "grad_norm": 3.125,
      "learning_rate": 4.2148481504262316e-07,
      "loss": 0.6408,
      "step": 1450
    },
    {
      "epoch": 0.846979107848673,
      "grad_norm": 2.921875,
      "learning_rate": 3.0326649975182866e-07,
      "loss": 0.6262,
      "step": 1500
    },
    {
      "epoch": 0.8752117447769622,
      "grad_norm": 1.875,
      "learning_rate": 2.034209111107635e-07,
      "loss": 0.6414,
      "step": 1550
    },
    {
      "epoch": 0.9034443817052513,
      "grad_norm": 1.375,
      "learning_rate": 1.2278312342729415e-07,
      "loss": 0.6341,
      "step": 1600
    },
    {
      "epoch": 0.9316770186335404,
      "grad_norm": 2.359375,
      "learning_rate": 6.202756354044327e-08,
      "loss": 0.6351,
      "step": 1650
    },
    {
      "epoch": 0.9599096555618295,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1662370145288935e-08,
      "loss": 0.6261,
      "step": 1700
    },
    {
      "epoch": 0.9881422924901185,
      "grad_norm": 1.3359375,
      "learning_rate": 2.025143894951176e-09,
      "loss": 0.6328,
      "step": 1750
    }
  ],
  "logging_steps": 50,
  "max_steps": 1771,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 6.698468202388193e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}