{
  "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": 4.685604171080919,
      "learning_rate": 4.761904761904762e-06,
      "loss": 0.8717,
      "step": 10
    },
    {
      "epoch": 0.14253897550111358,
      "grad_norm": 1.2641988163659033,
      "learning_rate": 9.523809523809525e-06,
      "loss": 0.4892,
      "step": 20
    },
    {
      "epoch": 0.21380846325167038,
      "grad_norm": 1.0513027523822995,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.4157,
      "step": 30
    },
    {
      "epoch": 0.28507795100222716,
      "grad_norm": 0.9614551103195862,
      "learning_rate": 1.904761904761905e-05,
      "loss": 0.3784,
      "step": 40
    },
    {
      "epoch": 0.35634743875278396,
      "grad_norm": 1.3389289028347522,
      "learning_rate": 1.997790438338385e-05,
      "loss": 0.3547,
      "step": 50
    },
    {
      "epoch": 0.42761692650334077,
      "grad_norm": 0.9265654502813704,
      "learning_rate": 1.9888308262251286e-05,
      "loss": 0.3354,
      "step": 60
    },
    {
      "epoch": 0.49888641425389757,
      "grad_norm": 0.8836746097261403,
      "learning_rate": 1.973044870579824e-05,
      "loss": 0.3059,
      "step": 70
    },
    {
      "epoch": 0.5701559020044543,
      "grad_norm": 0.8586242191121829,
      "learning_rate": 1.9505415489478293e-05,
      "loss": 0.2888,
      "step": 80
    },
    {
      "epoch": 0.6414253897550112,
      "grad_norm": 0.963159348675228,
      "learning_rate": 1.921476211870408e-05,
      "loss": 0.2733,
      "step": 90
    },
    {
      "epoch": 0.7126948775055679,
      "grad_norm": 0.8670780499563064,
      "learning_rate": 1.8860495104301346e-05,
      "loss": 0.256,
      "step": 100
    },
    {
      "epoch": 0.7839643652561247,
      "grad_norm": 1.1644273575940398,
      "learning_rate": 1.844506011066308e-05,
      "loss": 0.244,
      "step": 110
    },
    {
      "epoch": 0.8552338530066815,
      "grad_norm": 0.7602497462679673,
      "learning_rate": 1.7971325072229227e-05,
      "loss": 0.2354,
      "step": 120
    },
    {
      "epoch": 0.9265033407572383,
      "grad_norm": 0.7109787470699661,
      "learning_rate": 1.7442560394846518e-05,
      "loss": 0.2227,
      "step": 130
    },
    {
      "epoch": 0.9977728285077951,
      "grad_norm": 0.7430484913809842,
      "learning_rate": 1.686241637868734e-05,
      "loss": 0.2105,
      "step": 140
    },
    {
      "epoch": 1.064142538975501,
      "grad_norm": 0.640558938311108,
      "learning_rate": 1.6234898018587336e-05,
      "loss": 0.1545,
      "step": 150
    },
    {
      "epoch": 1.135412026726058,
      "grad_norm": 0.6919473525807,
      "learning_rate": 1.5564337355766412e-05,
      "loss": 0.1449,
      "step": 160
    },
    {
      "epoch": 1.2066815144766148,
      "grad_norm": 0.6044841545181189,
      "learning_rate": 1.4855363571801523e-05,
      "loss": 0.1388,
      "step": 170
    },
    {
      "epoch": 1.2779510022271716,
      "grad_norm": 0.6162626150448226,
      "learning_rate": 1.4112871031306118e-05,
      "loss": 0.1389,
      "step": 180
    },
    {
      "epoch": 1.3492204899777283,
      "grad_norm": 0.5465386596527281,
      "learning_rate": 1.3341985493931877e-05,
      "loss": 0.1351,
      "step": 190
    },
    {
      "epoch": 1.4204899777282851,
      "grad_norm": 0.5720040016751858,
      "learning_rate": 1.2548028728946548e-05,
      "loss": 0.1344,
      "step": 200
    },
    {
      "epoch": 1.4917594654788418,
      "grad_norm": 0.7640959736921902,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.1343,
      "step": 210
    },
    {
      "epoch": 1.5630289532293986,
      "grad_norm": 0.53080562119513,
      "learning_rate": 1.0912947110386484e-05,
      "loss": 0.1338,
      "step": 220
    },
    {
      "epoch": 1.6342984409799555,
      "grad_norm": 0.5068171077311262,
      "learning_rate": 1.0083109959960974e-05,
      "loss": 0.1293,
      "step": 230
    },
    {
      "epoch": 1.7055679287305123,
      "grad_norm": 0.49963066619909136,
      "learning_rate": 9.252699064135759e-06,
      "loss": 0.1287,
      "step": 240
    },
    {
      "epoch": 1.7768374164810692,
      "grad_norm": 0.521344314047473,
      "learning_rate": 8.427447122476148e-06,
      "loss": 0.1247,
      "step": 250
    },
    {
      "epoch": 1.8481069042316258,
      "grad_norm": 4.7924235896878695,
      "learning_rate": 7.613051219968624e-06,
      "loss": 0.1239,
      "step": 260
    },
    {
      "epoch": 1.9193763919821827,
      "grad_norm": 0.4969928754549942,
      "learning_rate": 6.815133497483157e-06,
      "loss": 0.1222,
      "step": 270
    },
    {
      "epoch": 1.9906458797327393,
      "grad_norm": 0.500956385648517,
      "learning_rate": 6.039202339608432e-06,
      "loss": 0.1212,
      "step": 280
    },
    {
      "epoch": 2.057015590200445,
      "grad_norm": 0.5845299543980047,
      "learning_rate": 5.290614347797802e-06,
      "loss": 0.0776,
      "step": 290
    },
    {
      "epoch": 2.128285077951002,
      "grad_norm": 0.44519642303803225,
      "learning_rate": 4.5745373613424075e-06,
      "loss": 0.0638,
      "step": 300
    },
    {
      "epoch": 2.199554565701559,
      "grad_norm": 0.4795882837748153,
      "learning_rate": 3.89591478145437e-06,
      "loss": 0.0625,
      "step": 310
    },
    {
      "epoch": 2.270824053452116,
      "grad_norm": 0.4576670345879725,
      "learning_rate": 3.2594314447468457e-06,
      "loss": 0.0612,
      "step": 320
    },
    {
      "epoch": 2.3420935412026727,
      "grad_norm": 0.4236209462699708,
      "learning_rate": 2.669481281701739e-06,
      "loss": 0.0608,
      "step": 330
    },
    {
      "epoch": 2.4133630289532295,
      "grad_norm": 0.45036728156429356,
      "learning_rate": 2.130136983393112e-06,
      "loss": 0.0579,
      "step": 340
    },
    {
      "epoch": 2.4846325167037864,
      "grad_norm": 0.45059110908552646,
      "learning_rate": 1.6451218858706374e-06,
      "loss": 0.0603,
      "step": 350
    },
    {
      "epoch": 2.5559020044543432,
      "grad_norm": 0.4381629824180297,
      "learning_rate": 1.2177842662977136e-06,
      "loss": 0.0584,
      "step": 360
    },
    {
      "epoch": 2.6271714922048996,
      "grad_norm": 0.41364318576656084,
      "learning_rate": 8.510742282896545e-07,
      "loss": 0.0584,
      "step": 370
    },
    {
      "epoch": 2.6984409799554565,
      "grad_norm": 0.4444155477890125,
      "learning_rate": 5.475233360227516e-07,
      "loss": 0.0585,
      "step": 380
    },
    {
      "epoch": 2.7697104677060134,
      "grad_norm": 0.42695421857815985,
      "learning_rate": 3.0922713770922155e-07,
      "loss": 0.0586,
      "step": 390
    },
    {
      "epoch": 2.8409799554565702,
      "grad_norm": 0.4412239439982416,
      "learning_rate": 1.3783069908621772e-07,
      "loss": 0.059,
      "step": 400
    },
    {
      "epoch": 2.912249443207127,
      "grad_norm": 0.42736358920502854,
      "learning_rate": 3.451724678784518e-08,
      "loss": 0.0584,
      "step": 410
    },
    {
      "epoch": 2.9835189309576835,
      "grad_norm": 0.4447112762348948,
      "learning_rate": 0.0,
      "loss": 0.0579,
      "step": 420
    },
    {
      "epoch": 2.9835189309576835,
      "step": 420,
      "total_flos": 138158572830720.0,
      "train_loss": 0.1809410313765208,
      "train_runtime": 10427.4481,
      "train_samples_per_second": 20.669,
      "train_steps_per_second": 0.04
    }
  ],
  "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": 138158572830720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}