{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9835189309576835,
  "eval_steps": 500,
  "global_step": 420,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07126948775055679,
      "grad_norm": 5.386155724865442,
      "learning_rate": 4.761904761904762e-06,
      "loss": 0.7203,
      "step": 10
    },
    {
      "epoch": 0.14253897550111358,
      "grad_norm": 1.2149269336601682,
      "learning_rate": 9.523809523809525e-06,
      "loss": 0.3218,
      "step": 20
    },
    {
      "epoch": 0.21380846325167038,
      "grad_norm": 1.0072270588517231,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.2636,
      "step": 30
    },
    {
      "epoch": 0.28507795100222716,
      "grad_norm": 0.9813159151052762,
      "learning_rate": 1.904761904761905e-05,
      "loss": 0.2119,
      "step": 40
    },
    {
      "epoch": 0.35634743875278396,
      "grad_norm": 1.035099883660933,
      "learning_rate": 1.997790438338385e-05,
      "loss": 0.1677,
      "step": 50
    },
    {
      "epoch": 0.42761692650334077,
      "grad_norm": 0.9282522157774155,
      "learning_rate": 1.9888308262251286e-05,
      "loss": 0.1309,
      "step": 60
    },
    {
      "epoch": 0.49888641425389757,
      "grad_norm": 0.8460447757616745,
      "learning_rate": 1.973044870579824e-05,
      "loss": 0.1007,
      "step": 70
    },
    {
      "epoch": 0.5701559020044543,
      "grad_norm": 0.773597113207918,
      "learning_rate": 1.9505415489478293e-05,
      "loss": 0.0746,
      "step": 80
    },
    {
      "epoch": 0.6414253897550112,
      "grad_norm": 0.6729520417158498,
      "learning_rate": 1.921476211870408e-05,
      "loss": 0.0566,
      "step": 90
    },
    {
      "epoch": 0.7126948775055679,
      "grad_norm": 0.6645593102219655,
      "learning_rate": 1.8860495104301346e-05,
      "loss": 0.0461,
      "step": 100
    },
    {
      "epoch": 0.7839643652561247,
      "grad_norm": 0.540570020337723,
      "learning_rate": 1.844506011066308e-05,
      "loss": 0.0349,
      "step": 110
    },
    {
      "epoch": 0.8552338530066815,
      "grad_norm": 0.4956176907731711,
      "learning_rate": 1.7971325072229227e-05,
      "loss": 0.0299,
      "step": 120
    },
    {
      "epoch": 0.9265033407572383,
      "grad_norm": 0.44790338559252657,
      "learning_rate": 1.7442560394846518e-05,
      "loss": 0.0248,
      "step": 130
    },
    {
      "epoch": 0.9977728285077951,
      "grad_norm": 0.39981088306375556,
      "learning_rate": 1.686241637868734e-05,
      "loss": 0.0208,
      "step": 140
    },
    {
      "epoch": 1.064142538975501,
      "grad_norm": 0.35406624135481934,
      "learning_rate": 1.6234898018587336e-05,
      "loss": 0.0119,
      "step": 150
    },
    {
      "epoch": 1.135412026726058,
      "grad_norm": 0.32098694162314906,
      "learning_rate": 1.5564337355766412e-05,
      "loss": 0.0113,
      "step": 160
    },
    {
      "epoch": 1.2066815144766148,
      "grad_norm": 0.3423106380492279,
      "learning_rate": 1.4855363571801523e-05,
      "loss": 0.0094,
      "step": 170
    },
    {
      "epoch": 1.2779510022271716,
      "grad_norm": 0.2891429255279275,
      "learning_rate": 1.4112871031306118e-05,
      "loss": 0.0084,
      "step": 180
    },
    {
      "epoch": 1.3492204899777283,
      "grad_norm": 0.29170524600010345,
      "learning_rate": 1.3341985493931877e-05,
      "loss": 0.008,
      "step": 190
    },
    {
      "epoch": 1.4204899777282851,
      "grad_norm": 0.2675628632665854,
      "learning_rate": 1.2548028728946548e-05,
      "loss": 0.0071,
      "step": 200
    },
    {
      "epoch": 1.4917594654788418,
      "grad_norm": 0.25509463751220524,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.0068,
      "step": 210
    },
    {
      "epoch": 1.5630289532293986,
      "grad_norm": 0.2735783379244568,
      "learning_rate": 1.0912947110386484e-05,
      "loss": 0.0061,
      "step": 220
    },
    {
      "epoch": 1.6342984409799555,
      "grad_norm": 0.3003300875836066,
      "learning_rate": 1.0083109959960974e-05,
      "loss": 0.0063,
      "step": 230
    },
    {
      "epoch": 1.7055679287305123,
      "grad_norm": 0.19323431116905368,
      "learning_rate": 9.252699064135759e-06,
      "loss": 0.0064,
      "step": 240
    },
    {
      "epoch": 1.7768374164810692,
      "grad_norm": 0.22373763241676137,
      "learning_rate": 8.427447122476148e-06,
      "loss": 0.0059,
      "step": 250
    },
    {
      "epoch": 1.8481069042316258,
      "grad_norm": 0.15915308096304018,
      "learning_rate": 7.613051219968624e-06,
      "loss": 0.0057,
      "step": 260
    },
    {
      "epoch": 1.9193763919821827,
      "grad_norm": 0.33268347981540936,
      "learning_rate": 6.815133497483157e-06,
      "loss": 0.0052,
      "step": 270
    },
    {
      "epoch": 1.9906458797327393,
      "grad_norm": 0.20058068644639454,
      "learning_rate": 6.039202339608432e-06,
      "loss": 0.0043,
      "step": 280
    },
    {
      "epoch": 2.057015590200445,
      "grad_norm": 0.08868612045438849,
      "learning_rate": 5.290614347797802e-06,
      "loss": 0.0028,
      "step": 290
    },
    {
      "epoch": 2.128285077951002,
      "grad_norm": 0.0965700135627628,
      "learning_rate": 4.5745373613424075e-06,
      "loss": 0.0018,
      "step": 300
    },
    {
      "epoch": 2.199554565701559,
      "grad_norm": 0.13147304998556522,
      "learning_rate": 3.89591478145437e-06,
      "loss": 0.0018,
      "step": 310
    },
    {
      "epoch": 2.270824053452116,
      "grad_norm": 0.0865160523809111,
      "learning_rate": 3.2594314447468457e-06,
      "loss": 0.0021,
      "step": 320
    },
    {
      "epoch": 2.3420935412026727,
      "grad_norm": 0.08623261922970193,
      "learning_rate": 2.669481281701739e-06,
      "loss": 0.0017,
      "step": 330
    },
    {
      "epoch": 2.4133630289532295,
      "grad_norm": 0.09890169247970056,
      "learning_rate": 2.130136983393112e-06,
      "loss": 0.0015,
      "step": 340
    },
    {
      "epoch": 2.4846325167037864,
      "grad_norm": 0.060124530329447,
      "learning_rate": 1.6451218858706374e-06,
      "loss": 0.0015,
      "step": 350
    },
    {
      "epoch": 2.5559020044543432,
      "grad_norm": 0.10348698785220752,
      "learning_rate": 1.2177842662977136e-06,
      "loss": 0.0017,
      "step": 360
    },
    {
      "epoch": 2.6271714922048996,
      "grad_norm": 0.05761979057124168,
      "learning_rate": 8.510742282896545e-07,
      "loss": 0.0013,
      "step": 370
    },
    {
      "epoch": 2.6984409799554565,
      "grad_norm": 0.10255509224491521,
      "learning_rate": 5.475233360227516e-07,
      "loss": 0.0015,
      "step": 380
    },
    {
      "epoch": 2.7697104677060134,
      "grad_norm": 0.07270662190562449,
      "learning_rate": 3.0922713770922155e-07,
      "loss": 0.0015,
      "step": 390
    },
    {
      "epoch": 2.8409799554565702,
      "grad_norm": 0.06332685354019421,
      "learning_rate": 1.3783069908621772e-07,
      "loss": 0.0014,
      "step": 400
    },
    {
      "epoch": 2.912249443207127,
      "grad_norm": 0.07631487155394302,
      "learning_rate": 3.451724678784518e-08,
      "loss": 0.0016,
      "step": 410
    },
    {
      "epoch": 2.9835189309576835,
      "grad_norm": 0.08995532446896395,
      "learning_rate": 0.0,
      "loss": 0.0014,
      "step": 420
    },
    {
      "epoch": 2.9835189309576835,
      "step": 420,
      "total_flos": 151515727134720.0,
      "train_loss": 0.05550877188021938,
      "train_runtime": 12091.2718,
      "train_samples_per_second": 17.824,
      "train_steps_per_second": 0.035
    }
  ],
  "logging_steps": 10,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 151515727134720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}