{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 24435,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.061387354205033766,
      "grad_norm": 4.773414134979248,
      "learning_rate": 2.9386126457949665e-05,
      "loss": 0.7901,
      "step": 500
    },
    {
      "epoch": 0.12277470841006753,
      "grad_norm": 5.613208293914795,
      "learning_rate": 2.8772252915899326e-05,
      "loss": 0.686,
      "step": 1000
    },
    {
      "epoch": 0.1841620626151013,
      "grad_norm": 6.7994384765625,
      "learning_rate": 2.815837937384899e-05,
      "loss": 0.6822,
      "step": 1500
    },
    {
      "epoch": 0.24554941682013506,
      "grad_norm": 4.575761318206787,
      "learning_rate": 2.7544505831798647e-05,
      "loss": 0.6375,
      "step": 2000
    },
    {
      "epoch": 0.3069367710251688,
      "grad_norm": 5.669924736022949,
      "learning_rate": 2.693063228974831e-05,
      "loss": 0.6488,
      "step": 2500
    },
    {
      "epoch": 0.3683241252302026,
      "grad_norm": 5.164685249328613,
      "learning_rate": 2.6316758747697975e-05,
      "loss": 0.6232,
      "step": 3000
    },
    {
      "epoch": 0.42971147943523635,
      "grad_norm": 3.6371734142303467,
      "learning_rate": 2.5702885205647636e-05,
      "loss": 0.6478,
      "step": 3500
    },
    {
      "epoch": 0.4910988336402701,
      "grad_norm": 13.574466705322266,
      "learning_rate": 2.50890116635973e-05,
      "loss": 0.6271,
      "step": 4000
    },
    {
      "epoch": 0.5524861878453039,
      "grad_norm": 3.65866756439209,
      "learning_rate": 2.4475138121546964e-05,
      "loss": 0.6212,
      "step": 4500
    },
    {
      "epoch": 0.6138735420503376,
      "grad_norm": 7.22385835647583,
      "learning_rate": 2.3861264579496625e-05,
      "loss": 0.6126,
      "step": 5000
    },
    {
      "epoch": 0.6752608962553714,
      "grad_norm": 4.810811996459961,
      "learning_rate": 2.3247391037446286e-05,
      "loss": 0.6095,
      "step": 5500
    },
    {
      "epoch": 0.7366482504604052,
      "grad_norm": 4.843252182006836,
      "learning_rate": 2.2633517495395946e-05,
      "loss": 0.5984,
      "step": 6000
    },
    {
      "epoch": 0.7980356046654389,
      "grad_norm": 3.590651750564575,
      "learning_rate": 2.201964395334561e-05,
      "loss": 0.6056,
      "step": 6500
    },
    {
      "epoch": 0.8594229588704727,
      "grad_norm": 6.5436177253723145,
      "learning_rate": 2.1405770411295274e-05,
      "loss": 0.6149,
      "step": 7000
    },
    {
      "epoch": 0.9208103130755064,
      "grad_norm": 3.6206412315368652,
      "learning_rate": 2.0791896869244935e-05,
      "loss": 0.6191,
      "step": 7500
    },
    {
      "epoch": 0.9821976672805403,
      "grad_norm": 3.8409266471862793,
      "learning_rate": 2.01780233271946e-05,
      "loss": 0.5964,
      "step": 8000
    },
    {
      "epoch": 1.043585021485574,
      "grad_norm": 3.4344983100891113,
      "learning_rate": 1.9564149785144263e-05,
      "loss": 0.5774,
      "step": 8500
    },
    {
      "epoch": 1.1049723756906078,
      "grad_norm": 6.731381893157959,
      "learning_rate": 1.8950276243093924e-05,
      "loss": 0.5958,
      "step": 9000
    },
    {
      "epoch": 1.1663597298956414,
      "grad_norm": 3.6475465297698975,
      "learning_rate": 1.8336402701043585e-05,
      "loss": 0.5723,
      "step": 9500
    },
    {
      "epoch": 1.2277470841006752,
      "grad_norm": 5.497737884521484,
      "learning_rate": 1.7722529158993245e-05,
      "loss": 0.5592,
      "step": 10000
    },
    {
      "epoch": 1.289134438305709,
      "grad_norm": 3.4102916717529297,
      "learning_rate": 1.710865561694291e-05,
      "loss": 0.563,
      "step": 10500
    },
    {
      "epoch": 1.350521792510743,
      "grad_norm": 2.2644035816192627,
      "learning_rate": 1.6494782074892574e-05,
      "loss": 0.5677,
      "step": 11000
    },
    {
      "epoch": 1.4119091467157765,
      "grad_norm": 4.101683139801025,
      "learning_rate": 1.5880908532842234e-05,
      "loss": 0.5714,
      "step": 11500
    },
    {
      "epoch": 1.4732965009208103,
      "grad_norm": 3.3737809658050537,
      "learning_rate": 1.52670349907919e-05,
      "loss": 0.5716,
      "step": 12000
    },
    {
      "epoch": 1.5346838551258442,
      "grad_norm": 4.371752738952637,
      "learning_rate": 1.465316144874156e-05,
      "loss": 0.5706,
      "step": 12500
    },
    {
      "epoch": 1.5960712093308778,
      "grad_norm": 2.752619504928589,
      "learning_rate": 1.4039287906691222e-05,
      "loss": 0.576,
      "step": 13000
    },
    {
      "epoch": 1.6574585635359116,
      "grad_norm": 5.145851135253906,
      "learning_rate": 1.3425414364640886e-05,
      "loss": 0.5532,
      "step": 13500
    },
    {
      "epoch": 1.7188459177409454,
      "grad_norm": 3.320183515548706,
      "learning_rate": 1.2811540822590546e-05,
      "loss": 0.5496,
      "step": 14000
    },
    {
      "epoch": 1.780233271945979,
      "grad_norm": 8.330361366271973,
      "learning_rate": 1.2197667280540209e-05,
      "loss": 0.5785,
      "step": 14500
    },
    {
      "epoch": 1.8416206261510129,
      "grad_norm": 5.743785381317139,
      "learning_rate": 1.1583793738489871e-05,
      "loss": 0.5484,
      "step": 15000
    },
    {
      "epoch": 1.9030079803560467,
      "grad_norm": 3.6862549781799316,
      "learning_rate": 1.0969920196439534e-05,
      "loss": 0.5614,
      "step": 15500
    },
    {
      "epoch": 1.9643953345610803,
      "grad_norm": 3.0343778133392334,
      "learning_rate": 1.0356046654389196e-05,
      "loss": 0.5636,
      "step": 16000
    },
    {
      "epoch": 2.0257826887661143,
      "grad_norm": 3.191669225692749,
      "learning_rate": 9.742173112338858e-06,
      "loss": 0.5583,
      "step": 16500
    },
    {
      "epoch": 2.087170042971148,
      "grad_norm": 2.4944469928741455,
      "learning_rate": 9.128299570288521e-06,
      "loss": 0.5592,
      "step": 17000
    },
    {
      "epoch": 2.1485573971761815,
      "grad_norm": 5.961979389190674,
      "learning_rate": 8.514426028238183e-06,
      "loss": 0.543,
      "step": 17500
    },
    {
      "epoch": 2.2099447513812156,
      "grad_norm": 3.5605664253234863,
      "learning_rate": 7.900552486187846e-06,
      "loss": 0.5553,
      "step": 18000
    },
    {
      "epoch": 2.271332105586249,
      "grad_norm": 4.210664749145508,
      "learning_rate": 7.286678944137508e-06,
      "loss": 0.5449,
      "step": 18500
    },
    {
      "epoch": 2.332719459791283,
      "grad_norm": 3.2335548400878906,
      "learning_rate": 6.6728054020871705e-06,
      "loss": 0.5365,
      "step": 19000
    },
    {
      "epoch": 2.394106813996317,
      "grad_norm": 2.6599347591400146,
      "learning_rate": 6.058931860036833e-06,
      "loss": 0.5399,
      "step": 19500
    },
    {
      "epoch": 2.4554941682013505,
      "grad_norm": 4.371065616607666,
      "learning_rate": 5.445058317986495e-06,
      "loss": 0.5443,
      "step": 20000
    },
    {
      "epoch": 2.5168815224063845,
      "grad_norm": 4.86035680770874,
      "learning_rate": 4.831184775936157e-06,
      "loss": 0.5334,
      "step": 20500
    },
    {
      "epoch": 2.578268876611418,
      "grad_norm": 7.235117435455322,
      "learning_rate": 4.21731123388582e-06,
      "loss": 0.5513,
      "step": 21000
    },
    {
      "epoch": 2.6396562308164517,
      "grad_norm": 7.687514305114746,
      "learning_rate": 3.603437691835482e-06,
      "loss": 0.5367,
      "step": 21500
    },
    {
      "epoch": 2.701043585021486,
      "grad_norm": 3.5359065532684326,
      "learning_rate": 2.9895641497851445e-06,
      "loss": 0.5545,
      "step": 22000
    },
    {
      "epoch": 2.7624309392265194,
      "grad_norm": 3.8917315006256104,
      "learning_rate": 2.375690607734807e-06,
      "loss": 0.5401,
      "step": 22500
    },
    {
      "epoch": 2.823818293431553,
      "grad_norm": 3.8702080249786377,
      "learning_rate": 1.761817065684469e-06,
      "loss": 0.5424,
      "step": 23000
    },
    {
      "epoch": 2.885205647636587,
      "grad_norm": 5.246346473693848,
      "learning_rate": 1.1479435236341315e-06,
      "loss": 0.5495,
      "step": 23500
    },
    {
      "epoch": 2.9465930018416207,
      "grad_norm": 4.763291358947754,
      "learning_rate": 5.340699815837937e-07,
      "loss": 0.538,
      "step": 24000
    },
    {
      "epoch": 3.0,
      "step": 24435,
      "total_flos": 2.645641233904435e+16,
      "train_loss": 0.5831284902567558,
      "train_runtime": 2740.1657,
      "train_samples_per_second": 142.676,
      "train_steps_per_second": 8.917
    }
  ],
  "logging_steps": 500,
  "max_steps": 24435,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.645641233904435e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}