{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.998642226748133,
  "eval_steps": 500,
  "global_step": 368,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05431093007467753,
      "grad_norm": 1.0013175010681152,
      "learning_rate": 2e-05,
      "loss": 1.8305,
      "step": 10
    },
    {
      "epoch": 0.10862186014935506,
      "grad_norm": 0.6650476455688477,
      "learning_rate": 4e-05,
      "loss": 1.6895,
      "step": 20
    },
    {
      "epoch": 0.1629327902240326,
      "grad_norm": 0.2262110561132431,
      "learning_rate": 6e-05,
      "loss": 1.4921,
      "step": 30
    },
    {
      "epoch": 0.2172437202987101,
      "grad_norm": 0.22021710872650146,
      "learning_rate": 8e-05,
      "loss": 1.4074,
      "step": 40
    },
    {
      "epoch": 0.27155465037338766,
      "grad_norm": 0.18622460961341858,
      "learning_rate": 0.0001,
      "loss": 1.2593,
      "step": 50
    },
    {
      "epoch": 0.3258655804480652,
      "grad_norm": 0.18928822875022888,
      "learning_rate": 0.00012,
      "loss": 1.1828,
      "step": 60
    },
    {
      "epoch": 0.3801765105227427,
      "grad_norm": 4.061775207519531,
      "learning_rate": 0.00014,
      "loss": 1.0697,
      "step": 70
    },
    {
      "epoch": 0.4344874405974202,
      "grad_norm": 0.20349960029125214,
      "learning_rate": 0.00016,
      "loss": 1.0102,
      "step": 80
    },
    {
      "epoch": 0.48879837067209775,
      "grad_norm": 0.23872722685337067,
      "learning_rate": 0.00018,
      "loss": 0.9941,
      "step": 90
    },
    {
      "epoch": 0.5431093007467753,
      "grad_norm": 0.20515283942222595,
      "learning_rate": 0.0002,
      "loss": 0.9608,
      "step": 100
    },
    {
      "epoch": 0.5974202308214528,
      "grad_norm": 0.22473494708538055,
      "learning_rate": 0.00019931371771625544,
      "loss": 0.9308,
      "step": 110
    },
    {
      "epoch": 0.6517311608961304,
      "grad_norm": 0.24142144620418549,
      "learning_rate": 0.0001972642905324813,
      "loss": 0.9381,
      "step": 120
    },
    {
      "epoch": 0.7060420909708078,
      "grad_norm": 0.260145902633667,
      "learning_rate": 0.00019387984816003867,
      "loss": 0.8955,
      "step": 130
    },
    {
      "epoch": 0.7603530210454854,
      "grad_norm": 0.22235779464244843,
      "learning_rate": 0.00018920684425573865,
      "loss": 0.8667,
      "step": 140
    },
    {
      "epoch": 0.814663951120163,
      "grad_norm": 0.23329713940620422,
      "learning_rate": 0.00018330941881540915,
      "loss": 0.873,
      "step": 150
    },
    {
      "epoch": 0.8689748811948405,
      "grad_norm": 0.2553715109825134,
      "learning_rate": 0.0001762685178110382,
      "loss": 0.8651,
      "step": 160
    },
    {
      "epoch": 0.923285811269518,
      "grad_norm": 0.22536128759384155,
      "learning_rate": 0.0001681807821550438,
      "loss": 0.8504,
      "step": 170
    },
    {
      "epoch": 0.9775967413441955,
      "grad_norm": 0.22558774054050446,
      "learning_rate": 0.00015915722124135227,
      "loss": 0.8414,
      "step": 180
    },
    {
      "epoch": 1.031907671418873,
      "grad_norm": 0.2400912493467331,
      "learning_rate": 0.00014932168926979074,
      "loss": 0.8389,
      "step": 190
    },
    {
      "epoch": 1.0862186014935507,
      "grad_norm": 0.23116886615753174,
      "learning_rate": 0.00013880918526722497,
      "loss": 0.8289,
      "step": 200
    },
    {
      "epoch": 1.140529531568228,
      "grad_norm": 0.2643767297267914,
      "learning_rate": 0.00012776400013875006,
      "loss": 0.8037,
      "step": 210
    },
    {
      "epoch": 1.1948404616429056,
      "grad_norm": 0.23654422163963318,
      "learning_rate": 0.00011633773618185302,
      "loss": 0.8209,
      "step": 220
    },
    {
      "epoch": 1.2491513917175832,
      "grad_norm": 0.25414180755615234,
      "learning_rate": 0.00010468722624699401,
      "loss": 0.8327,
      "step": 230
    },
    {
      "epoch": 1.3034623217922607,
      "grad_norm": 0.24420738220214844,
      "learning_rate": 9.297238110547074e-05,
      "loss": 0.8056,
      "step": 240
    },
    {
      "epoch": 1.3577732518669383,
      "grad_norm": 0.23167012631893158,
      "learning_rate": 8.13539945708319e-05,
      "loss": 0.8294,
      "step": 250
    },
    {
      "epoch": 1.4120841819416157,
      "grad_norm": 0.2467813491821289,
      "learning_rate": 6.999153649996595e-05,
      "loss": 0.7809,
      "step": 260
    },
    {
      "epoch": 1.4663951120162932,
      "grad_norm": 0.2599235475063324,
      "learning_rate": 5.904096396634935e-05,
      "loss": 0.7995,
      "step": 270
    },
    {
      "epoch": 1.5207060420909708,
      "grad_norm": 0.2679561674594879,
      "learning_rate": 4.865258064851579e-05,
      "loss": 0.7845,
      "step": 280
    },
    {
      "epoch": 1.5750169721656482,
      "grad_norm": 0.2540304958820343,
      "learning_rate": 3.8968973815020806e-05,
      "loss": 0.7868,
      "step": 290
    },
    {
      "epoch": 1.629327902240326,
      "grad_norm": 0.26017382740974426,
      "learning_rate": 3.0123057222115836e-05,
      "loss": 0.7665,
      "step": 300
    },
    {
      "epoch": 1.6836388323150033,
      "grad_norm": 0.2591923177242279,
      "learning_rate": 2.2236246786624792e-05,
      "loss": 0.7936,
      "step": 310
    },
    {
      "epoch": 1.737949762389681,
      "grad_norm": 0.2649495601654053,
      "learning_rate": 1.5416794074090258e-05,
      "loss": 0.7597,
      "step": 320
    },
    {
      "epoch": 1.7922606924643585,
      "grad_norm": 0.25946423411369324,
      "learning_rate": 9.75830047614117e-06,
      "loss": 0.7954,
      "step": 330
    },
    {
      "epoch": 1.8465716225390358,
      "grad_norm": 0.24905863404273987,
      "learning_rate": 5.338432470956589e-06,
      "loss": 0.7648,
      "step": 340
    },
    {
      "epoch": 1.9008825526137136,
      "grad_norm": 0.2536468803882599,
      "learning_rate": 2.2178556007054872e-06,
      "loss": 0.8026,
      "step": 350
    },
    {
      "epoch": 1.955193482688391,
      "grad_norm": 0.27082565426826477,
      "learning_rate": 4.3940179781019055e-07,
      "loss": 0.7768,
      "step": 360
    }
  ],
  "logging_steps": 10,
  "max_steps": 368,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.122148310240461e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}