{
  "best_metric": 1.6663275957107544,
  "best_model_checkpoint": "/data/user_data/gonilude/java_and_text_pythia_410m/checkpoint-150",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 243,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_accuracy": 0.25,
      "eval_loss": 2.6309967041015625,
      "eval_runtime": 0.5335,
      "eval_samples_per_second": 134.957,
      "eval_steps_per_second": 16.87,
      "num_input_tokens_seen": 0,
      "step": 0
    },
    {
      "epoch": 0.012345679012345678,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 3.7346,
      "num_input_tokens_seen": 8192,
      "step": 1
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 3.0853,
      "num_input_tokens_seen": 40960,
      "step": 5
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 140.6628875732422,
      "learning_rate": 1e-05,
      "loss": 2.951,
      "num_input_tokens_seen": 81920,
      "step": 10
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 121.90998840332031,
      "learning_rate": 1.9999106432103785e-05,
      "loss": 3.6623,
      "num_input_tokens_seen": 122880,
      "step": 15
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 119.89352416992188,
      "learning_rate": 1.9967848320275253e-05,
      "loss": 2.5551,
      "num_input_tokens_seen": 163840,
      "step": 20
    },
    {
      "epoch": 0.30864197530864196,
      "grad_norm": 69.07218170166016,
      "learning_rate": 1.9892071378116378e-05,
      "loss": 2.146,
      "num_input_tokens_seen": 204800,
      "step": 25
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 38.68893051147461,
      "learning_rate": 1.9772114043845968e-05,
      "loss": 2.4626,
      "num_input_tokens_seen": 245760,
      "step": 30
    },
    {
      "epoch": 0.43209876543209874,
      "grad_norm": 12.328490257263184,
      "learning_rate": 1.9608512076038964e-05,
      "loss": 1.976,
      "num_input_tokens_seen": 286720,
      "step": 35
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 28.689950942993164,
      "learning_rate": 1.9401996160798574e-05,
      "loss": 1.8516,
      "num_input_tokens_seen": 327680,
      "step": 40
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 20.923078536987305,
      "learning_rate": 1.915348864833476e-05,
      "loss": 1.669,
      "num_input_tokens_seen": 368640,
      "step": 45
    },
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 60.305381774902344,
      "learning_rate": 1.8864099433524302e-05,
      "loss": 1.9603,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6172839506172839,
      "eval_accuracy": 0.19444444444444445,
      "eval_loss": 1.8224691152572632,
      "eval_runtime": 0.3688,
      "eval_samples_per_second": 195.251,
      "eval_steps_per_second": 24.406,
      "num_input_tokens_seen": 409600,
      "step": 50
    },
    {
      "epoch": 0.6790123456790124,
      "grad_norm": 37.31528854370117,
      "learning_rate": 1.853512099885085e-05,
      "loss": 1.6856,
      "num_input_tokens_seen": 450560,
      "step": 55
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 34.03938674926758,
      "learning_rate": 1.816802264186438e-05,
      "loss": 1.989,
      "num_input_tokens_seen": 491520,
      "step": 60
    },
    {
      "epoch": 0.8024691358024691,
      "grad_norm": 27.516170501708984,
      "learning_rate": 1.7764443912941675e-05,
      "loss": 1.8994,
      "num_input_tokens_seen": 532480,
      "step": 65
    },
    {
      "epoch": 0.8641975308641975,
      "grad_norm": 23.523881912231445,
      "learning_rate": 1.7326187292656332e-05,
      "loss": 1.7613,
      "num_input_tokens_seen": 573440,
      "step": 70
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 25.84837532043457,
      "learning_rate": 1.6855210141462964e-05,
      "loss": 1.9531,
      "num_input_tokens_seen": 614400,
      "step": 75
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 34.3070068359375,
      "learning_rate": 1.635361595765024e-05,
      "loss": 1.9051,
      "num_input_tokens_seen": 655360,
      "step": 80
    },
    {
      "epoch": 1.0493827160493827,
      "grad_norm": 31.36409568786621,
      "learning_rate": 1.5823644982606905e-05,
      "loss": 1.8392,
      "num_input_tokens_seen": 696320,
      "step": 85
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 27.246265411376953,
      "learning_rate": 1.5267664195359917e-05,
      "loss": 1.6923,
      "num_input_tokens_seen": 737280,
      "step": 90
    },
    {
      "epoch": 1.1728395061728394,
      "grad_norm": 41.13190841674805,
      "learning_rate": 1.4688156741071513e-05,
      "loss": 1.8443,
      "num_input_tokens_seen": 778240,
      "step": 95
    },
    {
      "epoch": 1.2345679012345678,
      "grad_norm": 38.65595626831055,
      "learning_rate": 1.408771084071012e-05,
      "loss": 1.7774,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.2345679012345678,
      "eval_accuracy": 0.18055555555555555,
      "eval_loss": 1.7543673515319824,
      "eval_runtime": 0.371,
      "eval_samples_per_second": 194.075,
      "eval_steps_per_second": 24.259,
      "num_input_tokens_seen": 819200,
      "step": 100
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 14.981557846069336,
      "learning_rate": 1.3469008231427207e-05,
      "loss": 1.8287,
      "num_input_tokens_seen": 860160,
      "step": 105
    },
    {
      "epoch": 1.3580246913580247,
      "grad_norm": 21.5086727142334,
      "learning_rate": 1.283481218926818e-05,
      "loss": 1.5601,
      "num_input_tokens_seen": 901120,
      "step": 110
    },
    {
      "epoch": 1.4197530864197532,
      "grad_norm": 24.150880813598633,
      "learning_rate": 1.2187955187710752e-05,
      "loss": 1.8594,
      "num_input_tokens_seen": 942080,
      "step": 115
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 11.27273941040039,
      "learning_rate": 1.1531326247150802e-05,
      "loss": 1.6694,
      "num_input_tokens_seen": 983040,
      "step": 120
    },
    {
      "epoch": 1.5432098765432098,
      "grad_norm": 24.10595703125,
      "learning_rate": 1.0867858031835975e-05,
      "loss": 1.6684,
      "num_input_tokens_seen": 1024000,
      "step": 125
    },
    {
      "epoch": 1.6049382716049383,
      "grad_norm": 15.398138046264648,
      "learning_rate": 1.0200513751875227e-05,
      "loss": 1.6126,
      "num_input_tokens_seen": 1064960,
      "step": 130
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 25.667972564697266,
      "learning_rate": 9.532273928823151e-06,
      "loss": 1.5059,
      "num_input_tokens_seen": 1105920,
      "step": 135
    },
    {
      "epoch": 1.7283950617283952,
      "grad_norm": 21.25739288330078,
      "learning_rate": 8.866123083947182e-06,
      "loss": 1.6684,
      "num_input_tokens_seen": 1146880,
      "step": 140
    },
    {
      "epoch": 1.7901234567901234,
      "grad_norm": 17.899890899658203,
      "learning_rate": 8.20503640863111e-06,
      "loss": 1.5919,
      "num_input_tokens_seen": 1187840,
      "step": 145
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 25.205127716064453,
      "learning_rate": 7.55196647644814e-06,
      "loss": 1.6193,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.8518518518518519,
      "eval_accuracy": 0.18055555555555555,
      "eval_loss": 1.6663275957107544,
      "eval_runtime": 0.3724,
      "eval_samples_per_second": 193.328,
      "eval_steps_per_second": 24.166,
      "num_input_tokens_seen": 1228800,
      "step": 150
    },
    {
      "epoch": 1.9135802469135803,
      "grad_norm": 32.01460647583008,
      "learning_rate": 6.909830056250527e-06,
      "loss": 1.649,
      "num_input_tokens_seen": 1269760,
      "step": 155
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 23.55994415283203,
      "learning_rate": 6.2814950851718695e-06,
      "loss": 1.7344,
      "num_input_tokens_seen": 1310720,
      "step": 160
    },
    {
      "epoch": 2.037037037037037,
      "grad_norm": 40.77457046508789,
      "learning_rate": 5.669767859723636e-06,
      "loss": 1.5739,
      "num_input_tokens_seen": 1351680,
      "step": 165
    },
    {
      "epoch": 2.0987654320987654,
      "grad_norm": 23.66048240661621,
      "learning_rate": 5.077380502193725e-06,
      "loss": 1.4769,
      "num_input_tokens_seen": 1392640,
      "step": 170
    },
    {
      "epoch": 2.1604938271604937,
      "grad_norm": 20.150760650634766,
      "learning_rate": 4.5069787583250815e-06,
      "loss": 1.5486,
      "num_input_tokens_seen": 1433600,
      "step": 175
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 11.237411499023438,
      "learning_rate": 3.961110180772955e-06,
      "loss": 1.5313,
      "num_input_tokens_seen": 1474560,
      "step": 180
    },
    {
      "epoch": 2.2839506172839505,
      "grad_norm": 30.582534790039062,
      "learning_rate": 3.442212751116305e-06,
      "loss": 1.6429,
      "num_input_tokens_seen": 1515520,
      "step": 185
    },
    {
      "epoch": 2.3456790123456788,
      "grad_norm": 24.695331573486328,
      "learning_rate": 2.9526039912402504e-06,
      "loss": 1.4812,
      "num_input_tokens_seen": 1556480,
      "step": 190
    },
    {
      "epoch": 2.4074074074074074,
      "grad_norm": 6.564646244049072,
      "learning_rate": 2.4944706127207252e-06,
      "loss": 1.5954,
      "num_input_tokens_seen": 1597440,
      "step": 195
    },
    {
      "epoch": 2.4691358024691357,
      "grad_norm": 31.85268783569336,
      "learning_rate": 2.0698587504397684e-06,
      "loss": 1.7311,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.4691358024691357,
      "eval_accuracy": 0.19444444444444445,
      "eval_loss": 1.7398681640625,
      "eval_runtime": 0.4238,
      "eval_samples_per_second": 169.875,
      "eval_steps_per_second": 21.234,
      "num_input_tokens_seen": 1638400,
      "step": 200
    },
    {
      "epoch": 2.5308641975308643,
      "grad_norm": 29.221206665039062,
      "learning_rate": 1.680664824050432e-06,
      "loss": 1.4484,
      "num_input_tokens_seen": 1679360,
      "step": 205
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 35.87575149536133,
      "learning_rate": 1.3286270681062275e-06,
      "loss": 1.5614,
      "num_input_tokens_seen": 1720320,
      "step": 210
    },
    {
      "epoch": 2.6543209876543212,
      "grad_norm": 29.08688735961914,
      "learning_rate": 1.015317768683669e-06,
      "loss": 1.5382,
      "num_input_tokens_seen": 1761280,
      "step": 215
    },
    {
      "epoch": 2.7160493827160495,
      "grad_norm": 23.70969581604004,
      "learning_rate": 7.421362411709676e-07,
      "loss": 1.5272,
      "num_input_tokens_seen": 1802240,
      "step": 220
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 35.782222747802734,
      "learning_rate": 5.103025805858197e-07,
      "loss": 1.5842,
      "num_input_tokens_seen": 1843200,
      "step": 225
    },
    {
      "epoch": 2.8395061728395063,
      "grad_norm": 31.512516021728516,
      "learning_rate": 3.2085221233487564e-07,
      "loss": 1.5197,
      "num_input_tokens_seen": 1884160,
      "step": 230
    },
    {
      "epoch": 2.9012345679012346,
      "grad_norm": 24.439847946166992,
      "learning_rate": 1.7463126775252192e-07,
      "loss": 1.5678,
      "num_input_tokens_seen": 1925120,
      "step": 235
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 28.297935485839844,
      "learning_rate": 7.229280507293657e-08,
      "loss": 1.6146,
      "num_input_tokens_seen": 1966080,
      "step": 240
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 1990656,
      "step": 243,
      "total_flos": 3610849453277184.0,
      "train_loss": 1.8222727520475663,
      "train_runtime": 109.7362,
      "train_samples_per_second": 17.633,
      "train_steps_per_second": 2.214
    }
  ],
  "logging_steps": 5,
  "max_steps": 243,
  "num_input_tokens_seen": 1990656,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3610849453277184.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}