{
  "best_metric": 0.5249539017677307,
  "best_model_checkpoint": "post-auto-v3/checkpoint-180",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 49.678558349609375,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 2.749,
      "step": 4
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 38.787879943847656,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 3.1578,
      "step": 8
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 42.88180160522461,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 2.6539,
      "step": 12
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 35.309532165527344,
      "learning_rate": 2.962962962962963e-05,
      "loss": 1.7708,
      "step": 16
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 23.5089168548584,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.1406,
      "step": 20
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 7.427271842956543,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.8041,
      "step": 24
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 11.275213241577148,
      "learning_rate": 4.9794238683127575e-05,
      "loss": 0.8478,
      "step": 28
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 21.598812103271484,
      "learning_rate": 4.8971193415637865e-05,
      "loss": 0.885,
      "step": 32
    },
    {
      "epoch": 0.4,
      "grad_norm": 15.150390625,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.7711,
      "step": 36
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 8.3656587600708,
      "learning_rate": 4.732510288065844e-05,
      "loss": 0.6932,
      "step": 40
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 6.864919662475586,
      "learning_rate": 4.650205761316873e-05,
      "loss": 0.6934,
      "step": 44
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 20.607200622558594,
      "learning_rate": 4.567901234567901e-05,
      "loss": 0.6592,
      "step": 48
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 5.4164276123046875,
      "learning_rate": 4.48559670781893e-05,
      "loss": 0.6815,
      "step": 52
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 21.185943603515625,
      "learning_rate": 4.403292181069959e-05,
      "loss": 0.7281,
      "step": 56
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 5.345090866088867,
      "learning_rate": 4.3209876543209875e-05,
      "loss": 0.7072,
      "step": 60
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 28.171621322631836,
      "learning_rate": 4.2386831275720165e-05,
      "loss": 0.5982,
      "step": 64
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 18.241920471191406,
      "learning_rate": 4.1563786008230455e-05,
      "loss": 0.6613,
      "step": 68
    },
    {
      "epoch": 0.8,
      "grad_norm": 26.421844482421875,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.8852,
      "step": 72
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 18.892175674438477,
      "learning_rate": 3.9917695473251035e-05,
      "loss": 0.7267,
      "step": 76
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 15.053618431091309,
      "learning_rate": 3.909465020576132e-05,
      "loss": 0.3929,
      "step": 80
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 45.083675384521484,
      "learning_rate": 3.82716049382716e-05,
      "loss": 0.5913,
      "step": 84
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 16.20758628845215,
      "learning_rate": 3.74485596707819e-05,
      "loss": 0.6828,
      "step": 88
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7166666666666667,
      "eval_f1_macro": 0.7356755710414246,
      "eval_f1_micro": 0.7166666666666667,
      "eval_f1_weighted": 0.714955155503936,
      "eval_loss": 0.5613141655921936,
      "eval_precision_macro": 0.7246444246444246,
      "eval_precision_micro": 0.7166666666666667,
      "eval_precision_weighted": 0.7248502348502348,
      "eval_recall_macro": 0.7572316572316572,
      "eval_recall_micro": 0.7166666666666667,
      "eval_recall_weighted": 0.7166666666666667,
      "eval_runtime": 45.0143,
      "eval_samples_per_second": 3.999,
      "eval_steps_per_second": 0.267,
      "step": 90
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 23.50992774963379,
      "learning_rate": 3.662551440329218e-05,
      "loss": 0.661,
      "step": 92
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 16.499202728271484,
      "learning_rate": 3.580246913580247e-05,
      "loss": 0.54,
      "step": 96
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 12.408361434936523,
      "learning_rate": 3.497942386831276e-05,
      "loss": 0.4252,
      "step": 100
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 30.811758041381836,
      "learning_rate": 3.4156378600823045e-05,
      "loss": 0.3497,
      "step": 104
    },
    {
      "epoch": 1.2,
      "grad_norm": 33.299259185791016,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.3372,
      "step": 108
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 9.907443046569824,
      "learning_rate": 3.2510288065843625e-05,
      "loss": 0.4249,
      "step": 112
    },
    {
      "epoch": 1.2888888888888888,
      "grad_norm": 26.002504348754883,
      "learning_rate": 3.168724279835391e-05,
      "loss": 0.4189,
      "step": 116
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 28.73817253112793,
      "learning_rate": 3.08641975308642e-05,
      "loss": 0.7664,
      "step": 120
    },
    {
      "epoch": 1.3777777777777778,
      "grad_norm": 26.192493438720703,
      "learning_rate": 3.0041152263374488e-05,
      "loss": 0.5389,
      "step": 124
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 38.437782287597656,
      "learning_rate": 2.9218106995884775e-05,
      "loss": 0.5959,
      "step": 128
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 17.456642150878906,
      "learning_rate": 2.839506172839506e-05,
      "loss": 0.474,
      "step": 132
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 14.425949096679688,
      "learning_rate": 2.757201646090535e-05,
      "loss": 0.5086,
      "step": 136
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 20.57114028930664,
      "learning_rate": 2.6748971193415638e-05,
      "loss": 0.6384,
      "step": 140
    },
    {
      "epoch": 1.6,
      "grad_norm": 18.78620719909668,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.5804,
      "step": 144
    },
    {
      "epoch": 1.6444444444444444,
      "grad_norm": 33.17873764038086,
      "learning_rate": 2.510288065843622e-05,
      "loss": 0.5028,
      "step": 148
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 26.253496170043945,
      "learning_rate": 2.4279835390946505e-05,
      "loss": 0.446,
      "step": 152
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 22.726823806762695,
      "learning_rate": 2.345679012345679e-05,
      "loss": 0.5482,
      "step": 156
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 13.564722061157227,
      "learning_rate": 2.2633744855967078e-05,
      "loss": 0.4052,
      "step": 160
    },
    {
      "epoch": 1.8222222222222222,
      "grad_norm": 13.872465133666992,
      "learning_rate": 2.1810699588477368e-05,
      "loss": 0.3939,
      "step": 164
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 8.408356666564941,
      "learning_rate": 2.0987654320987655e-05,
      "loss": 0.3675,
      "step": 168
    },
    {
      "epoch": 1.911111111111111,
      "grad_norm": 6.3673624992370605,
      "learning_rate": 2.016460905349794e-05,
      "loss": 0.3066,
      "step": 172
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 11.568488121032715,
      "learning_rate": 1.934156378600823e-05,
      "loss": 0.2487,
      "step": 176
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.9987974166870117,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.3745,
      "step": 180
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7722222222222223,
      "eval_f1_macro": 0.8129276695270152,
      "eval_f1_micro": 0.7722222222222223,
      "eval_f1_weighted": 0.7733237593303729,
      "eval_loss": 0.5249539017677307,
      "eval_precision_macro": 0.8374953236064346,
      "eval_precision_micro": 0.7722222222222223,
      "eval_precision_weighted": 0.775858897618157,
      "eval_recall_macro": 0.7930180930180931,
      "eval_recall_micro": 0.7722222222222223,
      "eval_recall_weighted": 0.7722222222222223,
      "eval_runtime": 47.7709,
      "eval_samples_per_second": 3.768,
      "eval_steps_per_second": 0.251,
      "step": 180
    }
  ],
  "logging_steps": 4,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 94720830382080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}