{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 3498,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05717552887364208,
      "grad_norm": 19.87455940246582,
      "learning_rate": 1.942824471126358e-05,
      "loss": 0.9362,
      "step": 100
    },
    {
      "epoch": 0.11435105774728416,
      "grad_norm": 10.90371322631836,
      "learning_rate": 1.885648942252716e-05,
      "loss": 0.7137,
      "step": 200
    },
    {
      "epoch": 0.17152658662092624,
      "grad_norm": 26.497846603393555,
      "learning_rate": 1.828473413379074e-05,
      "loss": 0.6532,
      "step": 300
    },
    {
      "epoch": 0.22870211549456831,
      "grad_norm": 21.90129852294922,
      "learning_rate": 1.7712978845054317e-05,
      "loss": 0.6318,
      "step": 400
    },
    {
      "epoch": 0.2858776443682104,
      "grad_norm": 20.014867782592773,
      "learning_rate": 1.7141223556317898e-05,
      "loss": 0.555,
      "step": 500
    },
    {
      "epoch": 0.34305317324185247,
      "grad_norm": 27.840036392211914,
      "learning_rate": 1.6569468267581476e-05,
      "loss": 0.5262,
      "step": 600
    },
    {
      "epoch": 0.40022870211549455,
      "grad_norm": 14.611533164978027,
      "learning_rate": 1.5997712978845054e-05,
      "loss": 0.4997,
      "step": 700
    },
    {
      "epoch": 0.45740423098913663,
      "grad_norm": 10.490826606750488,
      "learning_rate": 1.5425957690108635e-05,
      "loss": 0.5154,
      "step": 800
    },
    {
      "epoch": 0.5145797598627787,
      "grad_norm": 17.69927406311035,
      "learning_rate": 1.4854202401372213e-05,
      "loss": 0.4825,
      "step": 900
    },
    {
      "epoch": 0.5717552887364208,
      "grad_norm": 22.311716079711914,
      "learning_rate": 1.4282447112635793e-05,
      "loss": 0.4482,
      "step": 1000
    },
    {
      "epoch": 0.6289308176100629,
      "grad_norm": 28.744029998779297,
      "learning_rate": 1.371069182389937e-05,
      "loss": 0.4562,
      "step": 1100
    },
    {
      "epoch": 0.6861063464837049,
      "grad_norm": 15.368144989013672,
      "learning_rate": 1.3138936535162952e-05,
      "loss": 0.4399,
      "step": 1200
    },
    {
      "epoch": 0.743281875357347,
      "grad_norm": 22.21993064880371,
      "learning_rate": 1.256718124642653e-05,
      "loss": 0.4399,
      "step": 1300
    },
    {
      "epoch": 0.8004574042309891,
      "grad_norm": 18.359333038330078,
      "learning_rate": 1.199542595769011e-05,
      "loss": 0.4338,
      "step": 1400
    },
    {
      "epoch": 0.8576329331046312,
      "grad_norm": 30.874675750732422,
      "learning_rate": 1.1423670668953687e-05,
      "loss": 0.4127,
      "step": 1500
    },
    {
      "epoch": 0.9148084619782733,
      "grad_norm": 12.474808692932129,
      "learning_rate": 1.0851915380217269e-05,
      "loss": 0.373,
      "step": 1600
    },
    {
      "epoch": 0.9719839908519153,
      "grad_norm": 29.6883602142334,
      "learning_rate": 1.0280160091480847e-05,
      "loss": 0.4119,
      "step": 1700
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8380503058433533,
      "eval_loss": 0.4416338801383972,
      "eval_macro_f1": 0.8374092069972946,
      "eval_mae": 0.21598056032018295,
      "eval_runtime": 69.9108,
      "eval_samples_per_second": 100.07,
      "eval_steps_per_second": 6.265,
      "step": 1749
    },
    {
      "epoch": 1.0291595197255574,
      "grad_norm": 22.368494033813477,
      "learning_rate": 9.708404802744426e-06,
      "loss": 0.3394,
      "step": 1800
    },
    {
      "epoch": 1.0863350485991996,
      "grad_norm": 30.913814544677734,
      "learning_rate": 9.136649514008006e-06,
      "loss": 0.3285,
      "step": 1900
    },
    {
      "epoch": 1.1435105774728416,
      "grad_norm": 16.7418155670166,
      "learning_rate": 8.564894225271586e-06,
      "loss": 0.326,
      "step": 2000
    },
    {
      "epoch": 1.2006861063464838,
      "grad_norm": 13.248634338378906,
      "learning_rate": 7.993138936535163e-06,
      "loss": 0.344,
      "step": 2100
    },
    {
      "epoch": 1.2578616352201257,
      "grad_norm": 15.368040084838867,
      "learning_rate": 7.421383647798742e-06,
      "loss": 0.3512,
      "step": 2200
    },
    {
      "epoch": 1.315037164093768,
      "grad_norm": 22.94597053527832,
      "learning_rate": 6.849628359062321e-06,
      "loss": 0.3379,
      "step": 2300
    },
    {
      "epoch": 1.3722126929674099,
      "grad_norm": 11.906438827514648,
      "learning_rate": 6.277873070325901e-06,
      "loss": 0.3283,
      "step": 2400
    },
    {
      "epoch": 1.429388221841052,
      "grad_norm": 59.21862030029297,
      "learning_rate": 5.706117781589479e-06,
      "loss": 0.3028,
      "step": 2500
    },
    {
      "epoch": 1.486563750714694,
      "grad_norm": 15.572158813476562,
      "learning_rate": 5.134362492853059e-06,
      "loss": 0.3089,
      "step": 2600
    },
    {
      "epoch": 1.5437392795883362,
      "grad_norm": 20.811290740966797,
      "learning_rate": 4.562607204116639e-06,
      "loss": 0.3098,
      "step": 2700
    },
    {
      "epoch": 1.6009148084619782,
      "grad_norm": 50.088809967041016,
      "learning_rate": 3.990851915380217e-06,
      "loss": 0.297,
      "step": 2800
    },
    {
      "epoch": 1.6580903373356204,
      "grad_norm": 19.114036560058594,
      "learning_rate": 3.419096626643797e-06,
      "loss": 0.278,
      "step": 2900
    },
    {
      "epoch": 1.7152658662092626,
      "grad_norm": 22.178640365600586,
      "learning_rate": 2.847341337907376e-06,
      "loss": 0.2603,
      "step": 3000
    },
    {
      "epoch": 1.7724413950829045,
      "grad_norm": 7.50466251373291,
      "learning_rate": 2.275586049170955e-06,
      "loss": 0.3038,
      "step": 3100
    },
    {
      "epoch": 1.8296169239565465,
      "grad_norm": 25.798389434814453,
      "learning_rate": 1.7038307604345341e-06,
      "loss": 0.2875,
      "step": 3200
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 14.6487455368042,
      "learning_rate": 1.1320754716981133e-06,
      "loss": 0.2458,
      "step": 3300
    },
    {
      "epoch": 1.943967981703831,
      "grad_norm": 42.344337463378906,
      "learning_rate": 5.603201829616924e-07,
      "loss": 0.2803,
      "step": 3400
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8775014281272888,
      "eval_loss": 0.3536728620529175,
      "eval_macro_f1": 0.8769359614090297,
      "eval_mae": 0.1700971983990852,
      "eval_runtime": 69.5884,
      "eval_samples_per_second": 100.534,
      "eval_steps_per_second": 6.294,
      "step": 3498
    }
  ],
  "logging_steps": 100,
  "max_steps": 3498,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4722774402387968e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}