{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 137,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0072992700729927005,
      "grad_norm": 0.43487387895584106,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.7554,
      "step": 1
    },
    {
      "epoch": 0.0364963503649635,
      "grad_norm": 0.4084155857563019,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.7248,
      "step": 5
    },
    {
      "epoch": 0.072992700729927,
      "grad_norm": 0.4045219123363495,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.6877,
      "step": 10
    },
    {
      "epoch": 0.10948905109489052,
      "grad_norm": 0.5852366089820862,
      "learning_rate": 0.00019996738360808565,
      "loss": 1.5983,
      "step": 15
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 0.5415384769439697,
      "learning_rate": 0.00019882804237803488,
      "loss": 1.4422,
      "step": 20
    },
    {
      "epoch": 0.18248175182481752,
      "grad_norm": 0.49430617690086365,
      "learning_rate": 0.00019607909582962477,
      "loss": 1.3509,
      "step": 25
    },
    {
      "epoch": 0.21897810218978103,
      "grad_norm": 0.3028700649738312,
      "learning_rate": 0.0001917653158603628,
      "loss": 1.2905,
      "step": 30
    },
    {
      "epoch": 0.25547445255474455,
      "grad_norm": 0.21788553893566132,
      "learning_rate": 0.00018595696069872013,
      "loss": 1.2481,
      "step": 35
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 0.21770533919334412,
      "learning_rate": 0.00017874863061334657,
      "loss": 1.2255,
      "step": 40
    },
    {
      "epoch": 0.3284671532846715,
      "grad_norm": 0.19103731215000153,
      "learning_rate": 0.00017025772716520323,
      "loss": 1.2213,
      "step": 45
    },
    {
      "epoch": 0.36496350364963503,
      "grad_norm": 0.18975041806697845,
      "learning_rate": 0.0001606225410966638,
      "loss": 1.2069,
      "step": 50
    },
    {
      "epoch": 0.40145985401459855,
      "grad_norm": 0.21415986120700836,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1938,
      "step": 55
    },
    {
      "epoch": 0.43795620437956206,
      "grad_norm": 0.20551565289497375,
      "learning_rate": 0.0001385631124488136,
      "loss": 1.1837,
      "step": 60
    },
    {
      "epoch": 0.4744525547445255,
      "grad_norm": 0.20549848675727844,
      "learning_rate": 0.0001264981502196662,
      "loss": 1.1724,
      "step": 65
    },
    {
      "epoch": 0.5109489051094891,
      "grad_norm": 0.19810882210731506,
      "learning_rate": 0.00011400161449686293,
      "loss": 1.1713,
      "step": 70
    },
    {
      "epoch": 0.5474452554744526,
      "grad_norm": 0.18478353321552277,
      "learning_rate": 0.00010127703547159739,
      "loss": 1.1571,
      "step": 75
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 0.19806450605392456,
      "learning_rate": 8.853165746015997e-05,
      "loss": 1.1539,
      "step": 80
    },
    {
      "epoch": 0.6204379562043796,
      "grad_norm": 0.20397868752479553,
      "learning_rate": 7.597306353045393e-05,
      "loss": 1.1457,
      "step": 85
    },
    {
      "epoch": 0.656934306569343,
      "grad_norm": 0.18514488637447357,
      "learning_rate": 6.380579461128819e-05,
      "loss": 1.1613,
      "step": 90
    },
    {
      "epoch": 0.6934306569343066,
      "grad_norm": 0.18412043154239655,
      "learning_rate": 5.222801814877369e-05,
      "loss": 1.1449,
      "step": 95
    },
    {
      "epoch": 0.7299270072992701,
      "grad_norm": 0.19028052687644958,
      "learning_rate": 4.142830056718052e-05,
      "loss": 1.1511,
      "step": 100
    },
    {
      "epoch": 0.7664233576642335,
      "grad_norm": 0.1979902684688568,
      "learning_rate": 3.158253610095697e-05,
      "loss": 1.1457,
      "step": 105
    },
    {
      "epoch": 0.8029197080291971,
      "grad_norm": 0.19014957547187805,
      "learning_rate": 2.2851082017805703e-05,
      "loss": 1.1423,
      "step": 110
    },
    {
      "epoch": 0.8394160583941606,
      "grad_norm": 0.186836376786232,
      "learning_rate": 1.5376146891235598e-05,
      "loss": 1.1477,
      "step": 115
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 0.20176666975021362,
      "learning_rate": 9.279474459608805e-06,
      "loss": 1.153,
      "step": 120
    },
    {
      "epoch": 0.9124087591240876,
      "grad_norm": 0.19549883902072906,
      "learning_rate": 4.660360794506946e-06,
      "loss": 1.1444,
      "step": 125
    },
    {
      "epoch": 0.948905109489051,
      "grad_norm": 0.17397421598434448,
      "learning_rate": 1.5940370726542863e-06,
      "loss": 1.1508,
      "step": 130
    },
    {
      "epoch": 0.9854014598540146,
      "grad_norm": 0.1897565871477127,
      "learning_rate": 1.3044429107700318e-07,
      "loss": 1.1497,
      "step": 135
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6479942798614502,
      "eval_runtime": 1.1173,
      "eval_samples_per_second": 8.055,
      "eval_steps_per_second": 0.895,
      "step": 137
    },
    {
      "epoch": 1.0,
      "step": 137,
      "total_flos": 8.08957492854784e+17,
      "train_loss": 1.2461711733880705,
      "train_runtime": 2338.1563,
      "train_samples_per_second": 14.952,
      "train_steps_per_second": 0.059
    }
  ],
  "logging_steps": 5,
  "max_steps": 137,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 8.08957492854784e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}