{
  "best_metric": 1.5968663692474365,
  "best_model_checkpoint": "/content/drive/MyDrive/GPT2_medium_trained_model/checkpoint-15000",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 15010,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1665556295802798,
      "grad_norm": 0.349942684173584,
      "learning_rate": 0.0001,
      "loss": 2.3138,
      "step": 500
    },
    {
      "epoch": 0.1665556295802798,
      "eval_loss": 1.781299114227295,
      "eval_runtime": 45.0711,
      "eval_samples_per_second": 33.303,
      "eval_steps_per_second": 8.342,
      "step": 500
    },
    {
      "epoch": 0.3331112591605596,
      "grad_norm": 0.34403911232948303,
      "learning_rate": 9.655410062026189e-05,
      "loss": 1.8307,
      "step": 1000
    },
    {
      "epoch": 0.3331112591605596,
      "eval_loss": 1.7246960401535034,
      "eval_runtime": 45.0478,
      "eval_samples_per_second": 33.32,
      "eval_steps_per_second": 8.347,
      "step": 1000
    },
    {
      "epoch": 0.4996668887408394,
      "grad_norm": 0.39671897888183594,
      "learning_rate": 9.310820124052379e-05,
      "loss": 1.785,
      "step": 1500
    },
    {
      "epoch": 0.4996668887408394,
      "eval_loss": 1.7043348550796509,
      "eval_runtime": 45.0791,
      "eval_samples_per_second": 33.297,
      "eval_steps_per_second": 8.341,
      "step": 1500
    },
    {
      "epoch": 0.6662225183211192,
      "grad_norm": 0.40807807445526123,
      "learning_rate": 8.966230186078567e-05,
      "loss": 1.7692,
      "step": 2000
    },
    {
      "epoch": 0.6662225183211192,
      "eval_loss": 1.6906121969223022,
      "eval_runtime": 45.0622,
      "eval_samples_per_second": 33.31,
      "eval_steps_per_second": 8.344,
      "step": 2000
    },
    {
      "epoch": 0.832778147901399,
      "grad_norm": 0.4667167663574219,
      "learning_rate": 8.621640248104756e-05,
      "loss": 1.7505,
      "step": 2500
    },
    {
      "epoch": 0.832778147901399,
      "eval_loss": 1.677463412284851,
      "eval_runtime": 45.0632,
      "eval_samples_per_second": 33.309,
      "eval_steps_per_second": 8.344,
      "step": 2500
    },
    {
      "epoch": 0.9993337774816788,
      "grad_norm": 0.4343186020851135,
      "learning_rate": 8.277050310130945e-05,
      "loss": 1.7475,
      "step": 3000
    },
    {
      "epoch": 0.9993337774816788,
      "eval_loss": 1.6700527667999268,
      "eval_runtime": 45.0648,
      "eval_samples_per_second": 33.308,
      "eval_steps_per_second": 8.344,
      "step": 3000
    },
    {
      "epoch": 1.1658894070619588,
      "grad_norm": 0.45604434609413147,
      "learning_rate": 7.932460372157134e-05,
      "loss": 1.7341,
      "step": 3500
    },
    {
      "epoch": 1.1658894070619588,
      "eval_loss": 1.659743309020996,
      "eval_runtime": 45.0486,
      "eval_samples_per_second": 33.32,
      "eval_steps_per_second": 8.347,
      "step": 3500
    },
    {
      "epoch": 1.3324450366422385,
      "grad_norm": 0.4247240126132965,
      "learning_rate": 7.587870434183322e-05,
      "loss": 1.734,
      "step": 4000
    },
    {
      "epoch": 1.3324450366422385,
      "eval_loss": 1.6542617082595825,
      "eval_runtime": 45.0632,
      "eval_samples_per_second": 33.309,
      "eval_steps_per_second": 8.344,
      "step": 4000
    },
    {
      "epoch": 1.4990006662225184,
      "grad_norm": 0.42194628715515137,
      "learning_rate": 7.243280496209511e-05,
      "loss": 1.7152,
      "step": 4500
    },
    {
      "epoch": 1.4990006662225184,
      "eval_loss": 1.6479216814041138,
      "eval_runtime": 45.0448,
      "eval_samples_per_second": 33.322,
      "eval_steps_per_second": 8.347,
      "step": 4500
    },
    {
      "epoch": 1.6655562958027983,
      "grad_norm": 0.48870036005973816,
      "learning_rate": 6.8986905582357e-05,
      "loss": 1.7146,
      "step": 5000
    },
    {
      "epoch": 1.6655562958027983,
      "eval_loss": 1.6431379318237305,
      "eval_runtime": 45.0495,
      "eval_samples_per_second": 33.319,
      "eval_steps_per_second": 8.346,
      "step": 5000
    },
    {
      "epoch": 1.832111925383078,
      "grad_norm": 0.4430600106716156,
      "learning_rate": 6.554100620261888e-05,
      "loss": 1.7073,
      "step": 5500
    },
    {
      "epoch": 1.832111925383078,
      "eval_loss": 1.6352075338363647,
      "eval_runtime": 45.0591,
      "eval_samples_per_second": 33.312,
      "eval_steps_per_second": 8.345,
      "step": 5500
    },
    {
      "epoch": 1.9986675549633577,
      "grad_norm": 0.4781087338924408,
      "learning_rate": 6.209510682288078e-05,
      "loss": 1.7011,
      "step": 6000
    },
    {
      "epoch": 1.9986675549633577,
      "eval_loss": 1.6312915086746216,
      "eval_runtime": 45.0576,
      "eval_samples_per_second": 33.313,
      "eval_steps_per_second": 8.345,
      "step": 6000
    },
    {
      "epoch": 2.1652231845436374,
      "grad_norm": 0.4676028788089752,
      "learning_rate": 5.864920744314266e-05,
      "loss": 1.699,
      "step": 6500
    },
    {
      "epoch": 2.1652231845436374,
      "eval_loss": 1.6273860931396484,
      "eval_runtime": 45.0547,
      "eval_samples_per_second": 33.315,
      "eval_steps_per_second": 8.345,
      "step": 6500
    },
    {
      "epoch": 2.3317788141239175,
      "grad_norm": 0.5153520703315735,
      "learning_rate": 5.5203308063404545e-05,
      "loss": 1.6886,
      "step": 7000
    },
    {
      "epoch": 2.3317788141239175,
      "eval_loss": 1.622995138168335,
      "eval_runtime": 45.0582,
      "eval_samples_per_second": 33.312,
      "eval_steps_per_second": 8.345,
      "step": 7000
    },
    {
      "epoch": 2.498334443704197,
      "grad_norm": 0.44470497965812683,
      "learning_rate": 5.1757408683666443e-05,
      "loss": 1.6857,
      "step": 7500
    },
    {
      "epoch": 2.498334443704197,
      "eval_loss": 1.6191588640213013,
      "eval_runtime": 45.051,
      "eval_samples_per_second": 33.318,
      "eval_steps_per_second": 8.346,
      "step": 7500
    },
    {
      "epoch": 2.664890073284477,
      "grad_norm": 0.517364501953125,
      "learning_rate": 4.831150930392833e-05,
      "loss": 1.6828,
      "step": 8000
    },
    {
      "epoch": 2.664890073284477,
      "eval_loss": 1.6161798238754272,
      "eval_runtime": 45.0439,
      "eval_samples_per_second": 33.323,
      "eval_steps_per_second": 8.347,
      "step": 8000
    },
    {
      "epoch": 2.831445702864757,
      "grad_norm": 0.5027415752410889,
      "learning_rate": 4.486560992419022e-05,
      "loss": 1.6808,
      "step": 8500
    },
    {
      "epoch": 2.831445702864757,
      "eval_loss": 1.6137065887451172,
      "eval_runtime": 45.0572,
      "eval_samples_per_second": 33.313,
      "eval_steps_per_second": 8.345,
      "step": 8500
    },
    {
      "epoch": 2.9980013324450367,
      "grad_norm": 0.47020256519317627,
      "learning_rate": 4.1419710544452104e-05,
      "loss": 1.6889,
      "step": 9000
    },
    {
      "epoch": 2.9980013324450367,
      "eval_loss": 1.6114857196807861,
      "eval_runtime": 45.0897,
      "eval_samples_per_second": 33.289,
      "eval_steps_per_second": 8.339,
      "step": 9000
    },
    {
      "epoch": 3.1645569620253164,
      "grad_norm": 0.5054105520248413,
      "learning_rate": 3.797381116471399e-05,
      "loss": 1.6835,
      "step": 9500
    },
    {
      "epoch": 3.1645569620253164,
      "eval_loss": 1.6083775758743286,
      "eval_runtime": 45.0444,
      "eval_samples_per_second": 33.323,
      "eval_steps_per_second": 8.347,
      "step": 9500
    },
    {
      "epoch": 3.331112591605596,
      "grad_norm": 0.4983905553817749,
      "learning_rate": 3.452791178497588e-05,
      "loss": 1.6733,
      "step": 10000
    },
    {
      "epoch": 3.331112591605596,
      "eval_loss": 1.606980800628662,
      "eval_runtime": 45.0583,
      "eval_samples_per_second": 33.312,
      "eval_steps_per_second": 8.345,
      "step": 10000
    },
    {
      "epoch": 3.497668221185876,
      "grad_norm": 0.4818781316280365,
      "learning_rate": 3.108201240523777e-05,
      "loss": 1.6659,
      "step": 10500
    },
    {
      "epoch": 3.497668221185876,
      "eval_loss": 1.6059489250183105,
      "eval_runtime": 45.0647,
      "eval_samples_per_second": 33.308,
      "eval_steps_per_second": 8.344,
      "step": 10500
    },
    {
      "epoch": 3.664223850766156,
      "grad_norm": 0.5904703140258789,
      "learning_rate": 2.7636113025499656e-05,
      "loss": 1.6701,
      "step": 11000
    },
    {
      "epoch": 3.664223850766156,
      "eval_loss": 1.6036906242370605,
      "eval_runtime": 45.0719,
      "eval_samples_per_second": 33.302,
      "eval_steps_per_second": 8.342,
      "step": 11000
    },
    {
      "epoch": 3.8307794803464357,
      "grad_norm": 0.5586133003234863,
      "learning_rate": 2.4190213645761544e-05,
      "loss": 1.6688,
      "step": 11500
    },
    {
      "epoch": 3.8307794803464357,
      "eval_loss": 1.6019277572631836,
      "eval_runtime": 45.0455,
      "eval_samples_per_second": 33.322,
      "eval_steps_per_second": 8.347,
      "step": 11500
    },
    {
      "epoch": 3.9973351099267154,
      "grad_norm": 0.525917649269104,
      "learning_rate": 2.0744314266023432e-05,
      "loss": 1.6627,
      "step": 12000
    },
    {
      "epoch": 3.9973351099267154,
      "eval_loss": 1.60073983669281,
      "eval_runtime": 45.0484,
      "eval_samples_per_second": 33.32,
      "eval_steps_per_second": 8.347,
      "step": 12000
    },
    {
      "epoch": 4.1638907395069955,
      "grad_norm": 0.5083144307136536,
      "learning_rate": 1.7298414886285323e-05,
      "loss": 1.6688,
      "step": 12500
    },
    {
      "epoch": 4.1638907395069955,
      "eval_loss": 1.59957754611969,
      "eval_runtime": 45.065,
      "eval_samples_per_second": 33.307,
      "eval_steps_per_second": 8.344,
      "step": 12500
    },
    {
      "epoch": 4.330446369087275,
      "grad_norm": 0.5289840698242188,
      "learning_rate": 1.385251550654721e-05,
      "loss": 1.66,
      "step": 13000
    },
    {
      "epoch": 4.330446369087275,
      "eval_loss": 1.5992504358291626,
      "eval_runtime": 45.0504,
      "eval_samples_per_second": 33.318,
      "eval_steps_per_second": 8.346,
      "step": 13000
    },
    {
      "epoch": 4.497001998667555,
      "grad_norm": 0.549419105052948,
      "learning_rate": 1.0406616126809098e-05,
      "loss": 1.6672,
      "step": 13500
    },
    {
      "epoch": 4.497001998667555,
      "eval_loss": 1.5988696813583374,
      "eval_runtime": 45.053,
      "eval_samples_per_second": 33.316,
      "eval_steps_per_second": 8.346,
      "step": 13500
    },
    {
      "epoch": 4.663557628247835,
      "grad_norm": 0.485193133354187,
      "learning_rate": 6.9607167470709864e-06,
      "loss": 1.6596,
      "step": 14000
    },
    {
      "epoch": 4.663557628247835,
      "eval_loss": 1.5973259210586548,
      "eval_runtime": 45.0682,
      "eval_samples_per_second": 33.305,
      "eval_steps_per_second": 8.343,
      "step": 14000
    },
    {
      "epoch": 4.830113257828114,
      "grad_norm": 0.5129671692848206,
      "learning_rate": 3.514817367332874e-06,
      "loss": 1.6509,
      "step": 14500
    },
    {
      "epoch": 4.830113257828114,
      "eval_loss": 1.596968173980713,
      "eval_runtime": 45.0647,
      "eval_samples_per_second": 33.308,
      "eval_steps_per_second": 8.344,
      "step": 14500
    },
    {
      "epoch": 4.996668887408394,
      "grad_norm": 0.5455211997032166,
      "learning_rate": 6.891798759476224e-08,
      "loss": 1.6642,
      "step": 15000
    },
    {
      "epoch": 4.996668887408394,
      "eval_loss": 1.5968663692474365,
      "eval_runtime": 45.0733,
      "eval_samples_per_second": 33.301,
      "eval_steps_per_second": 8.342,
      "step": 15000
    }
  ],
  "logging_steps": 500,
  "max_steps": 15010,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.615808210272256e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}