{
  "best_global_step": 10000,
  "best_metric": 0.0,
  "best_model_checkpoint": "./results_code_to_text_codemodernbert_gpt2_all_languages/checkpoint-10000",
  "epoch": 1.151688790348124,
  "eval_steps": 10000,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011517751734861355,
      "grad_norm": 2.149099826812744,
      "learning_rate": 9.999664806726203e-05,
      "loss": 7.9953,
      "step": 100
    },
    {
      "epoch": 0.02303550346972271,
      "grad_norm": 2.219588041305542,
      "learning_rate": 9.998602828889252e-05,
      "loss": 4.0086,
      "step": 200
    },
    {
      "epoch": 0.03455325520458406,
      "grad_norm": 2.8714349269866943,
      "learning_rate": 9.996813639049668e-05,
      "loss": 3.5128,
      "step": 300
    },
    {
      "epoch": 0.04607100693944542,
      "grad_norm": 2.233255386352539,
      "learning_rate": 9.994297497504253e-05,
      "loss": 2.5397,
      "step": 400
    },
    {
      "epoch": 0.057588758674306774,
      "grad_norm": 3.247396469116211,
      "learning_rate": 9.991054770308961e-05,
      "loss": 1.9996,
      "step": 500
    },
    {
      "epoch": 0.06910651040916813,
      "grad_norm": 3.2835168838500977,
      "learning_rate": 9.987085929225645e-05,
      "loss": 1.7329,
      "step": 600
    },
    {
      "epoch": 0.08062426214402948,
      "grad_norm": 2.6005859375,
      "learning_rate": 9.98239155165343e-05,
      "loss": 1.6232,
      "step": 700
    },
    {
      "epoch": 0.09214201387889084,
      "grad_norm": 1.9255400896072388,
      "learning_rate": 9.976972320544693e-05,
      "loss": 1.5533,
      "step": 800
    },
    {
      "epoch": 0.10365976561375219,
      "grad_norm": 2.3379406929016113,
      "learning_rate": 9.970829024305725e-05,
      "loss": 1.5081,
      "step": 900
    },
    {
      "epoch": 0.11517751734861355,
      "grad_norm": 1.4015233516693115,
      "learning_rate": 9.963962556682021e-05,
      "loss": 1.4448,
      "step": 1000
    },
    {
      "epoch": 0.1266952690834749,
      "grad_norm": 2.204472541809082,
      "learning_rate": 9.956373916628259e-05,
      "loss": 1.3501,
      "step": 1100
    },
    {
      "epoch": 0.13821302081833625,
      "grad_norm": 2.014930248260498,
      "learning_rate": 9.948064208162966e-05,
      "loss": 1.3379,
      "step": 1200
    },
    {
      "epoch": 0.1497307725531976,
      "grad_norm": 1.2242907285690308,
      "learning_rate": 9.939034640207901e-05,
      "loss": 1.3679,
      "step": 1300
    },
    {
      "epoch": 0.16124852428805897,
      "grad_norm": 1.4741770029067993,
      "learning_rate": 9.929286526412182e-05,
      "loss": 1.2859,
      "step": 1400
    },
    {
      "epoch": 0.17276627602292033,
      "grad_norm": 1.6436251401901245,
      "learning_rate": 9.91882128496117e-05,
      "loss": 1.2964,
      "step": 1500
    },
    {
      "epoch": 0.1842840277577817,
      "grad_norm": 1.5630017518997192,
      "learning_rate": 9.907640438370148e-05,
      "loss": 1.3205,
      "step": 1600
    },
    {
      "epoch": 0.19580177949264305,
      "grad_norm": 1.3735089302062988,
      "learning_rate": 9.895745613262816e-05,
      "loss": 1.2516,
      "step": 1700
    },
    {
      "epoch": 0.20731953122750438,
      "grad_norm": 1.54973566532135,
      "learning_rate": 9.883138540134653e-05,
      "loss": 1.2208,
      "step": 1800
    },
    {
      "epoch": 0.21883728296236574,
      "grad_norm": 1.3270553350448608,
      "learning_rate": 9.869821053101151e-05,
      "loss": 1.3005,
      "step": 1900
    },
    {
      "epoch": 0.2303550346972271,
      "grad_norm": 1.321956753730774,
      "learning_rate": 9.85579508963099e-05,
      "loss": 1.2757,
      "step": 2000
    },
    {
      "epoch": 0.24187278643208845,
      "grad_norm": 1.3433573246002197,
      "learning_rate": 9.841062690264163e-05,
      "loss": 1.2155,
      "step": 2100
    },
    {
      "epoch": 0.2533905381669498,
      "grad_norm": 1.2773957252502441,
      "learning_rate": 9.825625998315115e-05,
      "loss": 1.2106,
      "step": 2200
    },
    {
      "epoch": 0.26490828990181114,
      "grad_norm": 1.2487130165100098,
      "learning_rate": 9.809487259560925e-05,
      "loss": 1.1769,
      "step": 2300
    },
    {
      "epoch": 0.2764260416366725,
      "grad_norm": 1.2487260103225708,
      "learning_rate": 9.792648821914587e-05,
      "loss": 1.2285,
      "step": 2400
    },
    {
      "epoch": 0.28794379337153386,
      "grad_norm": 2.003361940383911,
      "learning_rate": 9.775113135083427e-05,
      "loss": 1.1602,
      "step": 2500
    },
    {
      "epoch": 0.2994615451063952,
      "grad_norm": 1.1892813444137573,
      "learning_rate": 9.756882750212708e-05,
      "loss": 1.1457,
      "step": 2600
    },
    {
      "epoch": 0.3109792968412566,
      "grad_norm": 0.9468798637390137,
      "learning_rate": 9.737960319514486e-05,
      "loss": 1.1555,
      "step": 2700
    },
    {
      "epoch": 0.32249704857611794,
      "grad_norm": 1.7301925420761108,
      "learning_rate": 9.718348595881761e-05,
      "loss": 1.1718,
      "step": 2800
    },
    {
      "epoch": 0.3340148003109793,
      "grad_norm": 1.5235856771469116,
      "learning_rate": 9.698050432487968e-05,
      "loss": 1.1165,
      "step": 2900
    },
    {
      "epoch": 0.34553255204584066,
      "grad_norm": 1.4494585990905762,
      "learning_rate": 9.6770687823719e-05,
      "loss": 1.1172,
      "step": 3000
    },
    {
      "epoch": 0.357050303780702,
      "grad_norm": 1.3340733051300049,
      "learning_rate": 9.655406698008081e-05,
      "loss": 1.1798,
      "step": 3100
    },
    {
      "epoch": 0.3685680555155634,
      "grad_norm": 1.0183467864990234,
      "learning_rate": 9.633067330862688e-05,
      "loss": 1.1363,
      "step": 3200
    },
    {
      "epoch": 0.38008580725042473,
      "grad_norm": 0.9531416893005371,
      "learning_rate": 9.61005393093507e-05,
      "loss": 1.2012,
      "step": 3300
    },
    {
      "epoch": 0.3916035589852861,
      "grad_norm": 0.9986298680305481,
      "learning_rate": 9.586369846284912e-05,
      "loss": 1.1742,
      "step": 3400
    },
    {
      "epoch": 0.40312131072014745,
      "grad_norm": 1.2070988416671753,
      "learning_rate": 9.562018522545175e-05,
      "loss": 1.1404,
      "step": 3500
    },
    {
      "epoch": 0.41463906245500876,
      "grad_norm": 0.9883187413215637,
      "learning_rate": 9.537003502420789e-05,
      "loss": 1.1168,
      "step": 3600
    },
    {
      "epoch": 0.4261568141898701,
      "grad_norm": 1.2827179431915283,
      "learning_rate": 9.511328425173265e-05,
      "loss": 1.167,
      "step": 3700
    },
    {
      "epoch": 0.4376745659247315,
      "grad_norm": 1.667656421661377,
      "learning_rate": 9.484997026091238e-05,
      "loss": 1.073,
      "step": 3800
    },
    {
      "epoch": 0.44919231765959283,
      "grad_norm": 1.2254990339279175,
      "learning_rate": 9.458013135947051e-05,
      "loss": 1.0808,
      "step": 3900
    },
    {
      "epoch": 0.4607100693944542,
      "grad_norm": 1.6514670848846436,
      "learning_rate": 9.430380680439435e-05,
      "loss": 1.1928,
      "step": 4000
    },
    {
      "epoch": 0.47222782112931555,
      "grad_norm": 1.2024292945861816,
      "learning_rate": 9.402103679622392e-05,
      "loss": 1.0847,
      "step": 4100
    },
    {
      "epoch": 0.4837455728641769,
      "grad_norm": 1.0424613952636719,
      "learning_rate": 9.373186247320345e-05,
      "loss": 1.0647,
      "step": 4200
    },
    {
      "epoch": 0.49526332459903827,
      "grad_norm": 1.5781737565994263,
      "learning_rate": 9.343632590529642e-05,
      "loss": 1.1076,
      "step": 4300
    },
    {
      "epoch": 0.5067810763338996,
      "grad_norm": 0.9091070890426636,
      "learning_rate": 9.313447008806515e-05,
      "loss": 1.0865,
      "step": 4400
    },
    {
      "epoch": 0.5182988280687609,
      "grad_norm": 1.4019910097122192,
      "learning_rate": 9.282633893641564e-05,
      "loss": 1.074,
      "step": 4500
    },
    {
      "epoch": 0.5298165798036223,
      "grad_norm": 1.0551828145980835,
      "learning_rate": 9.251197727820871e-05,
      "loss": 1.0721,
      "step": 4600
    },
    {
      "epoch": 0.5413343315384836,
      "grad_norm": 0.7485769987106323,
      "learning_rate": 9.219143084773828e-05,
      "loss": 1.0482,
      "step": 4700
    },
    {
      "epoch": 0.552852083273345,
      "grad_norm": 1.1340844631195068,
      "learning_rate": 9.186474627907784e-05,
      "loss": 1.1191,
      "step": 4800
    },
    {
      "epoch": 0.5643698350082064,
      "grad_norm": 1.5390311479568481,
      "learning_rate": 9.153197109929595e-05,
      "loss": 1.1175,
      "step": 4900
    },
    {
      "epoch": 0.5758875867430677,
      "grad_norm": 1.3286751508712769,
      "learning_rate": 9.119315372154189e-05,
      "loss": 1.0089,
      "step": 5000
    },
    {
      "epoch": 0.5874053384779291,
      "grad_norm": 1.0134896039962769,
      "learning_rate": 9.084834343800234e-05,
      "loss": 1.0604,
      "step": 5100
    },
    {
      "epoch": 0.5989230902127904,
      "grad_norm": 1.1101710796356201,
      "learning_rate": 9.049759041273023e-05,
      "loss": 1.0266,
      "step": 5200
    },
    {
      "epoch": 0.6104408419476518,
      "grad_norm": 0.9307985901832581,
      "learning_rate": 9.014094567434668e-05,
      "loss": 1.042,
      "step": 5300
    },
    {
      "epoch": 0.6219585936825132,
      "grad_norm": 1.295506238937378,
      "learning_rate": 8.977846110861722e-05,
      "loss": 1.102,
      "step": 5400
    },
    {
      "epoch": 0.6334763454173745,
      "grad_norm": 1.0131995677947998,
      "learning_rate": 8.941018945090334e-05,
      "loss": 1.0017,
      "step": 5500
    },
    {
      "epoch": 0.6449940971522359,
      "grad_norm": 0.9528135061264038,
      "learning_rate": 8.90361842784903e-05,
      "loss": 1.0597,
      "step": 5600
    },
    {
      "epoch": 0.6565118488870972,
      "grad_norm": 0.8767136335372925,
      "learning_rate": 8.86565000027926e-05,
      "loss": 1.0354,
      "step": 5700
    },
    {
      "epoch": 0.6680296006219586,
      "grad_norm": 0.7215752601623535,
      "learning_rate": 8.8271191861438e-05,
      "loss": 1.0266,
      "step": 5800
    },
    {
      "epoch": 0.67954735235682,
      "grad_norm": 0.9168160557746887,
      "learning_rate": 8.788031591023145e-05,
      "loss": 0.9974,
      "step": 5900
    },
    {
      "epoch": 0.6910651040916813,
      "grad_norm": 0.9805298447608948,
      "learning_rate": 8.748392901499985e-05,
      "loss": 1.0205,
      "step": 6000
    },
    {
      "epoch": 0.7025828558265427,
      "grad_norm": 0.9025911092758179,
      "learning_rate": 8.708208884331907e-05,
      "loss": 1.0282,
      "step": 6100
    },
    {
      "epoch": 0.714100607561404,
      "grad_norm": 0.7643795609474182,
      "learning_rate": 8.667485385612433e-05,
      "loss": 1.0281,
      "step": 6200
    },
    {
      "epoch": 0.7256183592962654,
      "grad_norm": 1.015793800354004,
      "learning_rate": 8.6262283299205e-05,
      "loss": 1.0153,
      "step": 6300
    },
    {
      "epoch": 0.7371361110311268,
      "grad_norm": 0.9706717133522034,
      "learning_rate": 8.58444371945855e-05,
      "loss": 0.9879,
      "step": 6400
    },
    {
      "epoch": 0.7486538627659881,
      "grad_norm": 0.8967713117599487,
      "learning_rate": 8.5421376331793e-05,
      "loss": 1.044,
      "step": 6500
    },
    {
      "epoch": 0.7601716145008495,
      "grad_norm": 1.0314196348190308,
      "learning_rate": 8.499316225901364e-05,
      "loss": 1.0163,
      "step": 6600
    },
    {
      "epoch": 0.7716893662357108,
      "grad_norm": 0.9607068300247192,
      "learning_rate": 8.455985727413825e-05,
      "loss": 1.0047,
      "step": 6700
    },
    {
      "epoch": 0.7832071179705722,
      "grad_norm": 0.8781064748764038,
      "learning_rate": 8.41215244156991e-05,
      "loss": 0.9683,
      "step": 6800
    },
    {
      "epoch": 0.7947248697054335,
      "grad_norm": 0.7523179054260254,
      "learning_rate": 8.367822745369891e-05,
      "loss": 0.9814,
      "step": 6900
    },
    {
      "epoch": 0.8062426214402949,
      "grad_norm": 0.7084505558013916,
      "learning_rate": 8.323003088033327e-05,
      "loss": 1.0103,
      "step": 7000
    },
    {
      "epoch": 0.8177603731751563,
      "grad_norm": 0.8509836792945862,
      "learning_rate": 8.277699990060826e-05,
      "loss": 0.947,
      "step": 7100
    },
    {
      "epoch": 0.8292781249100175,
      "grad_norm": 0.9924744963645935,
      "learning_rate": 8.231920042285408e-05,
      "loss": 0.9985,
      "step": 7200
    },
    {
      "epoch": 0.8407958766448789,
      "grad_norm": 0.9982401132583618,
      "learning_rate": 8.185669904913669e-05,
      "loss": 1.004,
      "step": 7300
    },
    {
      "epoch": 0.8523136283797402,
      "grad_norm": 0.9341840744018555,
      "learning_rate": 8.138956306556813e-05,
      "loss": 1.005,
      "step": 7400
    },
    {
      "epoch": 0.8638313801146016,
      "grad_norm": 1.4367643594741821,
      "learning_rate": 8.09178604325177e-05,
      "loss": 0.9949,
      "step": 7500
    },
    {
      "epoch": 0.875349131849463,
      "grad_norm": 0.7783756256103516,
      "learning_rate": 8.044165977472476e-05,
      "loss": 0.9786,
      "step": 7600
    },
    {
      "epoch": 0.8868668835843243,
      "grad_norm": 1.033542513847351,
      "learning_rate": 7.99610303713151e-05,
      "loss": 0.9979,
      "step": 7700
    },
    {
      "epoch": 0.8983846353191857,
      "grad_norm": 0.7946944832801819,
      "learning_rate": 7.947604214572189e-05,
      "loss": 0.9736,
      "step": 7800
    },
    {
      "epoch": 0.909902387054047,
      "grad_norm": 0.8648232221603394,
      "learning_rate": 7.89867656555131e-05,
      "loss": 0.9916,
      "step": 7900
    },
    {
      "epoch": 0.9214201387889084,
      "grad_norm": 1.1316163539886475,
      "learning_rate": 7.849327208212653e-05,
      "loss": 1.0083,
      "step": 8000
    },
    {
      "epoch": 0.9329378905237697,
      "grad_norm": 0.731547474861145,
      "learning_rate": 7.799563322051407e-05,
      "loss": 0.9868,
      "step": 8100
    },
    {
      "epoch": 0.9444556422586311,
      "grad_norm": 0.7558659315109253,
      "learning_rate": 7.749392146869688e-05,
      "loss": 0.9378,
      "step": 8200
    },
    {
      "epoch": 0.9559733939934925,
      "grad_norm": 1.1830765008926392,
      "learning_rate": 7.698820981723252e-05,
      "loss": 0.947,
      "step": 8300
    },
    {
      "epoch": 0.9674911457283538,
      "grad_norm": 1.1989309787750244,
      "learning_rate": 7.647857183859626e-05,
      "loss": 0.9973,
      "step": 8400
    },
    {
      "epoch": 0.9790088974632152,
      "grad_norm": 0.7769212126731873,
      "learning_rate": 7.596508167647738e-05,
      "loss": 0.983,
      "step": 8500
    },
    {
      "epoch": 0.9905266491980765,
      "grad_norm": 0.8555830121040344,
      "learning_rate": 7.544781403499261e-05,
      "loss": 0.9472,
      "step": 8600
    },
    {
      "epoch": 1.0019580177949263,
      "grad_norm": 0.9663079380989075,
      "learning_rate": 7.492684416781785e-05,
      "loss": 0.9254,
      "step": 8700
    },
    {
      "epoch": 1.0134757695297878,
      "grad_norm": 1.0730838775634766,
      "learning_rate": 7.44022478672402e-05,
      "loss": 0.7473,
      "step": 8800
    },
    {
      "epoch": 1.024993521264649,
      "grad_norm": 1.2075188159942627,
      "learning_rate": 7.38741014531313e-05,
      "loss": 0.7745,
      "step": 8900
    },
    {
      "epoch": 1.0365112729995105,
      "grad_norm": 0.724323034286499,
      "learning_rate": 7.334248176184411e-05,
      "loss": 0.7592,
      "step": 9000
    },
    {
      "epoch": 1.0480290247343718,
      "grad_norm": 0.9635033011436462,
      "learning_rate": 7.280746613503463e-05,
      "loss": 0.7708,
      "step": 9100
    },
    {
      "epoch": 1.0595467764692332,
      "grad_norm": 1.1375808715820312,
      "learning_rate": 7.226913240840992e-05,
      "loss": 0.7739,
      "step": 9200
    },
    {
      "epoch": 1.0710645282040945,
      "grad_norm": 1.0138040781021118,
      "learning_rate": 7.172755890040428e-05,
      "loss": 0.7582,
      "step": 9300
    },
    {
      "epoch": 1.082582279938956,
      "grad_norm": 0.9169549345970154,
      "learning_rate": 7.118282440078535e-05,
      "loss": 0.7488,
      "step": 9400
    },
    {
      "epoch": 1.0941000316738172,
      "grad_norm": 0.8004472851753235,
      "learning_rate": 7.063500815919148e-05,
      "loss": 0.7401,
      "step": 9500
    },
    {
      "epoch": 1.1056177834086787,
      "grad_norm": 1.0395482778549194,
      "learning_rate": 7.008418987360222e-05,
      "loss": 0.7769,
      "step": 9600
    },
    {
      "epoch": 1.11713553514354,
      "grad_norm": 1.0113108158111572,
      "learning_rate": 6.953044967874367e-05,
      "loss": 0.8,
      "step": 9700
    },
    {
      "epoch": 1.1286532868784014,
      "grad_norm": 0.8164701461791992,
      "learning_rate": 6.897386813443019e-05,
      "loss": 0.7473,
      "step": 9800
    },
    {
      "epoch": 1.1401710386132626,
      "grad_norm": 0.7086979150772095,
      "learning_rate": 6.84145262138444e-05,
      "loss": 0.7732,
      "step": 9900
    },
    {
      "epoch": 1.151688790348124,
      "grad_norm": 1.1815799474716187,
      "learning_rate": 6.785250529175679e-05,
      "loss": 0.7656,
      "step": 10000
    },
    {
      "epoch": 1.151688790348124,
      "eval_gen_len": 0.0,
      "eval_loss": 0.12472382932901382,
      "eval_rouge1": 0.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.0,
      "eval_rougeLsum": 0.0,
      "eval_runtime": 474.3304,
      "eval_samples_per_second": 4.025,
      "eval_steps_per_second": 0.673,
      "step": 10000
    }
  ],
  "logging_steps": 100,
  "max_steps": 26046,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.24479560268356e+18,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}