{
  "best_global_step": 2000,
  "best_metric": 0.9480290412902832,
  "best_model_checkpoint": "/kaggle/working/tts_processed/checkpoint-2000",
  "epoch": 9.900990099009901,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12376237623762376,
      "grad_norm": 363.43377685546875,
      "learning_rate": 4.8e-08,
      "loss": 10.89256103515625,
      "step": 25
    },
    {
      "epoch": 0.24752475247524752,
      "grad_norm": 336.6938171386719,
      "learning_rate": 9.8e-08,
      "loss": 10.47541259765625,
      "step": 50
    },
    {
      "epoch": 0.3712871287128713,
      "grad_norm": 255.0070343017578,
      "learning_rate": 1.4799999999999998e-07,
      "loss": 10.08507568359375,
      "step": 75
    },
    {
      "epoch": 0.49504950495049505,
      "grad_norm": 247.54541015625,
      "learning_rate": 1.98e-07,
      "loss": 9.282888793945313,
      "step": 100
    },
    {
      "epoch": 0.6188118811881188,
      "grad_norm": 124.208740234375,
      "learning_rate": 2.48e-07,
      "loss": 8.717689208984375,
      "step": 125
    },
    {
      "epoch": 0.7425742574257426,
      "grad_norm": 194.5498809814453,
      "learning_rate": 2.98e-07,
      "loss": 8.212156372070313,
      "step": 150
    },
    {
      "epoch": 0.8663366336633663,
      "grad_norm": 143.2777557373047,
      "learning_rate": 3.4799999999999994e-07,
      "loss": 7.8293896484375,
      "step": 175
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 55.50076675415039,
      "learning_rate": 3.98e-07,
      "loss": 7.3809716796875,
      "step": 200
    },
    {
      "epoch": 1.113861386138614,
      "grad_norm": 69.43047332763672,
      "learning_rate": 4.48e-07,
      "loss": 6.937587890625,
      "step": 225
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 49.69321060180664,
      "learning_rate": 4.979999999999999e-07,
      "loss": 6.8110888671875,
      "step": 250
    },
    {
      "epoch": 1.3613861386138613,
      "grad_norm": 26.72427749633789,
      "learning_rate": 5.48e-07,
      "loss": 6.522671508789062,
      "step": 275
    },
    {
      "epoch": 1.4851485148514851,
      "grad_norm": 51.36345672607422,
      "learning_rate": 5.979999999999999e-07,
      "loss": 6.398966064453125,
      "step": 300
    },
    {
      "epoch": 1.608910891089109,
      "grad_norm": 38.85439682006836,
      "learning_rate": 6.48e-07,
      "loss": 6.198662109375,
      "step": 325
    },
    {
      "epoch": 1.7326732673267327,
      "grad_norm": 27.508665084838867,
      "learning_rate": 6.979999999999999e-07,
      "loss": 6.075740356445312,
      "step": 350
    },
    {
      "epoch": 1.8564356435643563,
      "grad_norm": 36.8642463684082,
      "learning_rate": 7.48e-07,
      "loss": 6.0834722900390625,
      "step": 375
    },
    {
      "epoch": 1.9801980198019802,
      "grad_norm": 27.07192039489746,
      "learning_rate": 7.98e-07,
      "loss": 5.9166015625,
      "step": 400
    },
    {
      "epoch": 2.103960396039604,
      "grad_norm": 22.465463638305664,
      "learning_rate": 8.48e-07,
      "loss": 5.795056762695313,
      "step": 425
    },
    {
      "epoch": 2.227722772277228,
      "grad_norm": 34.86723709106445,
      "learning_rate": 8.98e-07,
      "loss": 5.741965942382812,
      "step": 450
    },
    {
      "epoch": 2.3514851485148514,
      "grad_norm": 22.37932777404785,
      "learning_rate": 9.479999999999999e-07,
      "loss": 5.716455688476563,
      "step": 475
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 29.54213523864746,
      "learning_rate": 9.98e-07,
      "loss": 5.599214477539062,
      "step": 500
    },
    {
      "epoch": 2.4752475247524752,
      "eval_loss": 1.2534884214401245,
      "eval_runtime": 82.4141,
      "eval_samples_per_second": 19.608,
      "eval_steps_per_second": 4.902,
      "step": 500
    },
    {
      "epoch": 2.599009900990099,
      "grad_norm": 21.54619026184082,
      "learning_rate": 9.999953592789052e-07,
      "loss": 5.526549072265625,
      "step": 525
    },
    {
      "epoch": 2.7227722772277225,
      "grad_norm": 31.9982967376709,
      "learning_rate": 9.999806557001091e-07,
      "loss": 5.38673828125,
      "step": 550
    },
    {
      "epoch": 2.8465346534653464,
      "grad_norm": 19.33993148803711,
      "learning_rate": 9.999558815029513e-07,
      "loss": 5.291504516601562,
      "step": 575
    },
    {
      "epoch": 2.9702970297029703,
      "grad_norm": 18.838518142700195,
      "learning_rate": 9.999210371864342e-07,
      "loss": 5.345247192382812,
      "step": 600
    },
    {
      "epoch": 3.094059405940594,
      "grad_norm": 19.941740036010742,
      "learning_rate": 9.998761234523925e-07,
      "loss": 5.081980285644531,
      "step": 625
    },
    {
      "epoch": 3.217821782178218,
      "grad_norm": 24.84575080871582,
      "learning_rate": 9.998211412054793e-07,
      "loss": 5.025005493164063,
      "step": 650
    },
    {
      "epoch": 3.3415841584158414,
      "grad_norm": 24.532045364379883,
      "learning_rate": 9.99756091553148e-07,
      "loss": 5.004798889160156,
      "step": 675
    },
    {
      "epoch": 3.4653465346534653,
      "grad_norm": 21.20513916015625,
      "learning_rate": 9.996809758056298e-07,
      "loss": 4.870877685546875,
      "step": 700
    },
    {
      "epoch": 3.589108910891089,
      "grad_norm": 16.589248657226562,
      "learning_rate": 9.995957954759072e-07,
      "loss": 4.95923095703125,
      "step": 725
    },
    {
      "epoch": 3.7128712871287126,
      "grad_norm": 26.863059997558594,
      "learning_rate": 9.995005522796837e-07,
      "loss": 4.81072265625,
      "step": 750
    },
    {
      "epoch": 3.8366336633663365,
      "grad_norm": 14.973981857299805,
      "learning_rate": 9.993952481353493e-07,
      "loss": 4.8048876953125,
      "step": 775
    },
    {
      "epoch": 3.9603960396039604,
      "grad_norm": 18.018110275268555,
      "learning_rate": 9.992798851639418e-07,
      "loss": 4.770014343261718,
      "step": 800
    },
    {
      "epoch": 4.084158415841584,
      "grad_norm": 15.32919979095459,
      "learning_rate": 9.991544656891043e-07,
      "loss": 4.663901672363282,
      "step": 825
    },
    {
      "epoch": 4.207920792079208,
      "grad_norm": 14.925799369812012,
      "learning_rate": 9.990189922370373e-07,
      "loss": 4.614352111816406,
      "step": 850
    },
    {
      "epoch": 4.3316831683168315,
      "grad_norm": 14.5320405960083,
      "learning_rate": 9.988734675364496e-07,
      "loss": 4.607881774902344,
      "step": 875
    },
    {
      "epoch": 4.455445544554456,
      "grad_norm": 17.06329345703125,
      "learning_rate": 9.987178945185019e-07,
      "loss": 4.582254028320312,
      "step": 900
    },
    {
      "epoch": 4.579207920792079,
      "grad_norm": 16.860803604125977,
      "learning_rate": 9.985522763167486e-07,
      "loss": 4.6025848388671875,
      "step": 925
    },
    {
      "epoch": 4.702970297029703,
      "grad_norm": 12.743483543395996,
      "learning_rate": 9.983766162670739e-07,
      "loss": 4.603981628417968,
      "step": 950
    },
    {
      "epoch": 4.826732673267327,
      "grad_norm": 11.648216247558594,
      "learning_rate": 9.981909179076255e-07,
      "loss": 4.5333544921875,
      "step": 975
    },
    {
      "epoch": 4.9504950495049505,
      "grad_norm": 12.38879108428955,
      "learning_rate": 9.979951849787429e-07,
      "loss": 4.538429565429688,
      "step": 1000
    },
    {
      "epoch": 4.9504950495049505,
      "eval_loss": 1.0112695693969727,
      "eval_runtime": 82.132,
      "eval_samples_per_second": 19.676,
      "eval_steps_per_second": 4.919,
      "step": 1000
    },
    {
      "epoch": 5.074257425742574,
      "grad_norm": 39.850196838378906,
      "learning_rate": 9.977894214228815e-07,
      "loss": 4.55607666015625,
      "step": 1025
    },
    {
      "epoch": 5.198019801980198,
      "grad_norm": 13.423649787902832,
      "learning_rate": 9.975736313845345e-07,
      "loss": 4.43293212890625,
      "step": 1050
    },
    {
      "epoch": 5.321782178217822,
      "grad_norm": 15.34720516204834,
      "learning_rate": 9.97347819210148e-07,
      "loss": 4.4848849487304685,
      "step": 1075
    },
    {
      "epoch": 5.445544554455446,
      "grad_norm": 10.895915031433105,
      "learning_rate": 9.971119894480344e-07,
      "loss": 4.418946228027344,
      "step": 1100
    },
    {
      "epoch": 5.569306930693069,
      "grad_norm": 13.77745532989502,
      "learning_rate": 9.96866146848281e-07,
      "loss": 4.675699768066406,
      "step": 1125
    },
    {
      "epoch": 5.693069306930693,
      "grad_norm": 21.53974723815918,
      "learning_rate": 9.96610296362653e-07,
      "loss": 4.483356628417969,
      "step": 1150
    },
    {
      "epoch": 5.816831683168317,
      "grad_norm": 14.47573184967041,
      "learning_rate": 9.963444431444948e-07,
      "loss": 4.555756530761719,
      "step": 1175
    },
    {
      "epoch": 5.9405940594059405,
      "grad_norm": 11.701032638549805,
      "learning_rate": 9.960685925486265e-07,
      "loss": 4.419072265625,
      "step": 1200
    },
    {
      "epoch": 6.064356435643564,
      "grad_norm": 17.197729110717773,
      "learning_rate": 9.957827501312352e-07,
      "loss": 4.375239562988281,
      "step": 1225
    },
    {
      "epoch": 6.188118811881188,
      "grad_norm": 12.936083793640137,
      "learning_rate": 9.954869216497633e-07,
      "loss": 4.3699853515625,
      "step": 1250
    },
    {
      "epoch": 6.311881188118812,
      "grad_norm": 15.114112854003906,
      "learning_rate": 9.95181113062793e-07,
      "loss": 4.41375732421875,
      "step": 1275
    },
    {
      "epoch": 6.435643564356436,
      "grad_norm": 17.72418785095215,
      "learning_rate": 9.948653305299256e-07,
      "loss": 4.430754089355469,
      "step": 1300
    },
    {
      "epoch": 6.5594059405940595,
      "grad_norm": 18.342178344726562,
      "learning_rate": 9.945395804116578e-07,
      "loss": 4.4040380859375,
      "step": 1325
    },
    {
      "epoch": 6.683168316831683,
      "grad_norm": 12.649271965026855,
      "learning_rate": 9.94203869269254e-07,
      "loss": 4.3536474609375,
      "step": 1350
    },
    {
      "epoch": 6.806930693069307,
      "grad_norm": 32.92485809326172,
      "learning_rate": 9.938582038646131e-07,
      "loss": 4.349139709472656,
      "step": 1375
    },
    {
      "epoch": 6.930693069306931,
      "grad_norm": 11.99206829071045,
      "learning_rate": 9.935025911601334e-07,
      "loss": 4.317200317382812,
      "step": 1400
    },
    {
      "epoch": 7.054455445544554,
      "grad_norm": 15.798395156860352,
      "learning_rate": 9.931370383185716e-07,
      "loss": 4.390576782226563,
      "step": 1425
    },
    {
      "epoch": 7.178217821782178,
      "grad_norm": 12.485000610351562,
      "learning_rate": 9.92761552702899e-07,
      "loss": 4.415244750976562,
      "step": 1450
    },
    {
      "epoch": 7.301980198019802,
      "grad_norm": 14.873079299926758,
      "learning_rate": 9.923761418761526e-07,
      "loss": 4.3524868774414065,
      "step": 1475
    },
    {
      "epoch": 7.425742574257426,
      "grad_norm": 13.601946830749512,
      "learning_rate": 9.919808136012837e-07,
      "loss": 4.294336547851563,
      "step": 1500
    },
    {
      "epoch": 7.425742574257426,
      "eval_loss": 0.9704130291938782,
      "eval_runtime": 86.4979,
      "eval_samples_per_second": 18.683,
      "eval_steps_per_second": 4.671,
      "step": 1500
    },
    {
      "epoch": 7.5495049504950495,
      "grad_norm": 15.53011417388916,
      "learning_rate": 9.915755758410008e-07,
      "loss": 4.254639587402344,
      "step": 1525
    },
    {
      "epoch": 7.673267326732673,
      "grad_norm": 11.795248985290527,
      "learning_rate": 9.91160436757609e-07,
      "loss": 4.307816467285156,
      "step": 1550
    },
    {
      "epoch": 7.797029702970297,
      "grad_norm": 15.00704574584961,
      "learning_rate": 9.907354047128464e-07,
      "loss": 4.349948120117188,
      "step": 1575
    },
    {
      "epoch": 7.920792079207921,
      "grad_norm": 13.17168140411377,
      "learning_rate": 9.903004882677155e-07,
      "loss": 4.2257516479492185,
      "step": 1600
    },
    {
      "epoch": 8.044554455445544,
      "grad_norm": 13.770243644714355,
      "learning_rate": 9.898556961823103e-07,
      "loss": 4.310787048339844,
      "step": 1625
    },
    {
      "epoch": 8.168316831683168,
      "grad_norm": 13.734089851379395,
      "learning_rate": 9.894010374156398e-07,
      "loss": 4.148223266601563,
      "step": 1650
    },
    {
      "epoch": 8.292079207920793,
      "grad_norm": 15.90095329284668,
      "learning_rate": 9.889365211254485e-07,
      "loss": 4.3510107421875,
      "step": 1675
    },
    {
      "epoch": 8.415841584158416,
      "grad_norm": 12.133323669433594,
      "learning_rate": 9.884621566680306e-07,
      "loss": 4.337423400878906,
      "step": 1700
    },
    {
      "epoch": 8.53960396039604,
      "grad_norm": 50.35639190673828,
      "learning_rate": 9.87977953598043e-07,
      "loss": 4.3044869995117185,
      "step": 1725
    },
    {
      "epoch": 8.663366336633663,
      "grad_norm": 12.457736015319824,
      "learning_rate": 9.874839216683112e-07,
      "loss": 4.3085205078125,
      "step": 1750
    },
    {
      "epoch": 8.787128712871286,
      "grad_norm": 14.483731269836426,
      "learning_rate": 9.869800708296346e-07,
      "loss": 4.1831143188476565,
      "step": 1775
    },
    {
      "epoch": 8.910891089108912,
      "grad_norm": 11.174741744995117,
      "learning_rate": 9.864664112305846e-07,
      "loss": 4.162017822265625,
      "step": 1800
    },
    {
      "epoch": 9.034653465346535,
      "grad_norm": 10.312405586242676,
      "learning_rate": 9.859429532173012e-07,
      "loss": 4.320256958007812,
      "step": 1825
    },
    {
      "epoch": 9.158415841584159,
      "grad_norm": 13.814125061035156,
      "learning_rate": 9.85409707333284e-07,
      "loss": 4.314511413574219,
      "step": 1850
    },
    {
      "epoch": 9.282178217821782,
      "grad_norm": 11.276887893676758,
      "learning_rate": 9.848666843191804e-07,
      "loss": 4.327219543457031,
      "step": 1875
    },
    {
      "epoch": 9.405940594059405,
      "grad_norm": 13.48475170135498,
      "learning_rate": 9.84313895112568e-07,
      "loss": 4.2580517578125,
      "step": 1900
    },
    {
      "epoch": 9.52970297029703,
      "grad_norm": 13.70500659942627,
      "learning_rate": 9.837513508477365e-07,
      "loss": 4.269812316894531,
      "step": 1925
    },
    {
      "epoch": 9.653465346534654,
      "grad_norm": 12.701525688171387,
      "learning_rate": 9.831790628554612e-07,
      "loss": 4.257364196777344,
      "step": 1950
    },
    {
      "epoch": 9.777227722772277,
      "grad_norm": 11.086860656738281,
      "learning_rate": 9.82597042662776e-07,
      "loss": 4.120067443847656,
      "step": 1975
    },
    {
      "epoch": 9.900990099009901,
      "grad_norm": 14.811179161071777,
      "learning_rate": 9.820053019927408e-07,
      "loss": 4.13207275390625,
      "step": 2000
    },
    {
      "epoch": 9.900990099009901,
      "eval_loss": 0.9480290412902832,
      "eval_runtime": 81.9519,
      "eval_samples_per_second": 19.719,
      "eval_steps_per_second": 4.93,
      "step": 2000
    }
  ],
  "logging_steps": 25,
  "max_steps": 18000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 90,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 8580226730188608.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}