{
  "best_metric": 0.9891978434265983,
  "best_model_checkpoint": "MASSIVE-finetuned-LangsClassifier/checkpoint-102774",
  "epoch": 15.0,
  "global_step": 110115,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1.9909185851155614e-05,
      "loss": 1.5895,
      "step": 500
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.981837170231122e-05,
      "loss": 0.1743,
      "step": 1000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.972755755346683e-05,
      "loss": 0.1255,
      "step": 1500
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.9636743404622444e-05,
      "loss": 0.1118,
      "step": 2000
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.9545929255778053e-05,
      "loss": 0.0971,
      "step": 2500
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.945511510693366e-05,
      "loss": 0.0852,
      "step": 3000
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.9364300958089274e-05,
      "loss": 0.0802,
      "step": 3500
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.9273486809244882e-05,
      "loss": 0.077,
      "step": 4000
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.918267266040049e-05,
      "loss": 0.0767,
      "step": 4500
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.9091858511556103e-05,
      "loss": 0.07,
      "step": 5000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.9001044362711712e-05,
      "loss": 0.0668,
      "step": 5500
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.891023021386732e-05,
      "loss": 0.0637,
      "step": 6000
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.8819416065022933e-05,
      "loss": 0.0643,
      "step": 6500
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.8728601916178542e-05,
      "loss": 0.0618,
      "step": 7000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.98448154470839,
      "eval_loss": 0.052093375474214554,
      "eval_runtime": 188.0662,
      "eval_samples_per_second": 551.311,
      "eval_steps_per_second": 6.897,
      "step": 7341
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.863778776733415e-05,
      "loss": 0.0562,
      "step": 7500
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.8546973618489763e-05,
      "loss": 0.0509,
      "step": 8000
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.8456159469645372e-05,
      "loss": 0.0536,
      "step": 8500
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.836534532080098e-05,
      "loss": 0.0506,
      "step": 9000
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.8274531171956593e-05,
      "loss": 0.0511,
      "step": 9500
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.8183717023112202e-05,
      "loss": 0.0514,
      "step": 10000
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.8092902874267814e-05,
      "loss": 0.0499,
      "step": 10500
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.8002088725423423e-05,
      "loss": 0.0513,
      "step": 11000
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.7911274576579032e-05,
      "loss": 0.0494,
      "step": 11500
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.7820460427734644e-05,
      "loss": 0.0481,
      "step": 12000
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.7729646278890253e-05,
      "loss": 0.045,
      "step": 12500
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.763883213004586e-05,
      "loss": 0.0472,
      "step": 13000
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.7548017981201474e-05,
      "loss": 0.047,
      "step": 13500
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.7457203832357083e-05,
      "loss": 0.045,
      "step": 14000
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.736638968351269e-05,
      "loss": 0.0449,
      "step": 14500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9861790264556388,
      "eval_loss": 0.05018872022628784,
      "eval_runtime": 187.122,
      "eval_samples_per_second": 554.093,
      "eval_steps_per_second": 6.931,
      "step": 14682
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.7275575534668304e-05,
      "loss": 0.0412,
      "step": 15000
    },
    {
      "epoch": 2.11,
      "learning_rate": 1.7184761385823913e-05,
      "loss": 0.0385,
      "step": 15500
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.709394723697952e-05,
      "loss": 0.0375,
      "step": 16000
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.7003133088135134e-05,
      "loss": 0.0367,
      "step": 16500
    },
    {
      "epoch": 2.32,
      "learning_rate": 1.6912318939290742e-05,
      "loss": 0.0395,
      "step": 17000
    },
    {
      "epoch": 2.38,
      "learning_rate": 1.682150479044635e-05,
      "loss": 0.0376,
      "step": 17500
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.6730690641601963e-05,
      "loss": 0.0402,
      "step": 18000
    },
    {
      "epoch": 2.52,
      "learning_rate": 1.6639876492757576e-05,
      "loss": 0.0391,
      "step": 18500
    },
    {
      "epoch": 2.59,
      "learning_rate": 1.654906234391318e-05,
      "loss": 0.0359,
      "step": 19000
    },
    {
      "epoch": 2.66,
      "learning_rate": 1.6458248195068793e-05,
      "loss": 0.0355,
      "step": 19500
    },
    {
      "epoch": 2.72,
      "learning_rate": 1.6367434046224406e-05,
      "loss": 0.0385,
      "step": 20000
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.6276619897380014e-05,
      "loss": 0.0375,
      "step": 20500
    },
    {
      "epoch": 2.86,
      "learning_rate": 1.6185805748535623e-05,
      "loss": 0.0392,
      "step": 21000
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.6094991599691235e-05,
      "loss": 0.035,
      "step": 21500
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.6004177450846844e-05,
      "loss": 0.0357,
      "step": 22000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.987095280807847,
      "eval_loss": 0.045726146548986435,
      "eval_runtime": 187.1686,
      "eval_samples_per_second": 553.955,
      "eval_steps_per_second": 6.93,
      "step": 22023
    },
    {
      "epoch": 3.06,
      "learning_rate": 1.5913363302002453e-05,
      "loss": 0.0306,
      "step": 22500
    },
    {
      "epoch": 3.13,
      "learning_rate": 1.5822549153158065e-05,
      "loss": 0.0289,
      "step": 23000
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.5731735004313674e-05,
      "loss": 0.0329,
      "step": 23500
    },
    {
      "epoch": 3.27,
      "learning_rate": 1.5640920855469283e-05,
      "loss": 0.0295,
      "step": 24000
    },
    {
      "epoch": 3.34,
      "learning_rate": 1.5550106706624895e-05,
      "loss": 0.0323,
      "step": 24500
    },
    {
      "epoch": 3.41,
      "learning_rate": 1.5459292557780504e-05,
      "loss": 0.0305,
      "step": 25000
    },
    {
      "epoch": 3.47,
      "learning_rate": 1.5368478408936113e-05,
      "loss": 0.0315,
      "step": 25500
    },
    {
      "epoch": 3.54,
      "learning_rate": 1.527766426009172e-05,
      "loss": 0.0302,
      "step": 26000
    },
    {
      "epoch": 3.61,
      "learning_rate": 1.5186850111247334e-05,
      "loss": 0.0314,
      "step": 26500
    },
    {
      "epoch": 3.68,
      "learning_rate": 1.5096035962402944e-05,
      "loss": 0.0266,
      "step": 27000
    },
    {
      "epoch": 3.75,
      "learning_rate": 1.5005221813558553e-05,
      "loss": 0.0309,
      "step": 27500
    },
    {
      "epoch": 3.81,
      "learning_rate": 1.4914407664714164e-05,
      "loss": 0.0331,
      "step": 28000
    },
    {
      "epoch": 3.88,
      "learning_rate": 1.4823593515869774e-05,
      "loss": 0.0293,
      "step": 28500
    },
    {
      "epoch": 3.95,
      "learning_rate": 1.4732779367025383e-05,
      "loss": 0.0324,
      "step": 29000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9876546782018267,
      "eval_loss": 0.04698457568883896,
      "eval_runtime": 187.1654,
      "eval_samples_per_second": 553.965,
      "eval_steps_per_second": 6.93,
      "step": 29364
    },
    {
      "epoch": 4.02,
      "learning_rate": 1.4641965218180994e-05,
      "loss": 0.0295,
      "step": 29500
    },
    {
      "epoch": 4.09,
      "learning_rate": 1.4551151069336604e-05,
      "loss": 0.0233,
      "step": 30000
    },
    {
      "epoch": 4.15,
      "learning_rate": 1.4460336920492213e-05,
      "loss": 0.0256,
      "step": 30500
    },
    {
      "epoch": 4.22,
      "learning_rate": 1.4369522771647823e-05,
      "loss": 0.0257,
      "step": 31000
    },
    {
      "epoch": 4.29,
      "learning_rate": 1.4278708622803434e-05,
      "loss": 0.0258,
      "step": 31500
    },
    {
      "epoch": 4.36,
      "learning_rate": 1.4187894473959043e-05,
      "loss": 0.0259,
      "step": 32000
    },
    {
      "epoch": 4.43,
      "learning_rate": 1.4097080325114653e-05,
      "loss": 0.029,
      "step": 32500
    },
    {
      "epoch": 4.5,
      "learning_rate": 1.4006266176270264e-05,
      "loss": 0.0252,
      "step": 33000
    },
    {
      "epoch": 4.56,
      "learning_rate": 1.3915452027425873e-05,
      "loss": 0.0262,
      "step": 33500
    },
    {
      "epoch": 4.63,
      "learning_rate": 1.3824637878581483e-05,
      "loss": 0.027,
      "step": 34000
    },
    {
      "epoch": 4.7,
      "learning_rate": 1.3733823729737095e-05,
      "loss": 0.027,
      "step": 34500
    },
    {
      "epoch": 4.77,
      "learning_rate": 1.3643009580892703e-05,
      "loss": 0.0268,
      "step": 35000
    },
    {
      "epoch": 4.84,
      "learning_rate": 1.3552195432048315e-05,
      "loss": 0.0256,
      "step": 35500
    },
    {
      "epoch": 4.9,
      "learning_rate": 1.3461381283203925e-05,
      "loss": 0.0253,
      "step": 36000
    },
    {
      "epoch": 4.97,
      "learning_rate": 1.3370567134359534e-05,
      "loss": 0.0273,
      "step": 36500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9870856360251922,
      "eval_loss": 0.05222976580262184,
      "eval_runtime": 187.2236,
      "eval_samples_per_second": 553.792,
      "eval_steps_per_second": 6.928,
      "step": 36705
    },
    {
      "epoch": 5.04,
      "learning_rate": 1.3279752985515145e-05,
      "loss": 0.0231,
      "step": 37000
    },
    {
      "epoch": 5.11,
      "learning_rate": 1.3188938836670755e-05,
      "loss": 0.0227,
      "step": 37500
    },
    {
      "epoch": 5.18,
      "learning_rate": 1.3098124687826364e-05,
      "loss": 0.0233,
      "step": 38000
    },
    {
      "epoch": 5.24,
      "learning_rate": 1.3007310538981974e-05,
      "loss": 0.0208,
      "step": 38500
    },
    {
      "epoch": 5.31,
      "learning_rate": 1.2916496390137585e-05,
      "loss": 0.0248,
      "step": 39000
    },
    {
      "epoch": 5.38,
      "learning_rate": 1.2825682241293194e-05,
      "loss": 0.0204,
      "step": 39500
    },
    {
      "epoch": 5.45,
      "learning_rate": 1.2734868092448804e-05,
      "loss": 0.0208,
      "step": 40000
    },
    {
      "epoch": 5.52,
      "learning_rate": 1.2644053943604415e-05,
      "loss": 0.0228,
      "step": 40500
    },
    {
      "epoch": 5.59,
      "learning_rate": 1.2553239794760024e-05,
      "loss": 0.0237,
      "step": 41000
    },
    {
      "epoch": 5.65,
      "learning_rate": 1.2462425645915634e-05,
      "loss": 0.024,
      "step": 41500
    },
    {
      "epoch": 5.72,
      "learning_rate": 1.2371611497071245e-05,
      "loss": 0.0231,
      "step": 42000
    },
    {
      "epoch": 5.79,
      "learning_rate": 1.2280797348226854e-05,
      "loss": 0.0244,
      "step": 42500
    },
    {
      "epoch": 5.86,
      "learning_rate": 1.2189983199382464e-05,
      "loss": 0.0252,
      "step": 43000
    },
    {
      "epoch": 5.93,
      "learning_rate": 1.2099169050538075e-05,
      "loss": 0.0234,
      "step": 43500
    },
    {
      "epoch": 5.99,
      "learning_rate": 1.2008354901693683e-05,
      "loss": 0.0218,
      "step": 44000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9878957977681972,
      "eval_loss": 0.04787103086709976,
      "eval_runtime": 187.2388,
      "eval_samples_per_second": 553.747,
      "eval_steps_per_second": 6.927,
      "step": 44046
    },
    {
      "epoch": 6.06,
      "learning_rate": 1.1917540752849294e-05,
      "loss": 0.018,
      "step": 44500
    },
    {
      "epoch": 6.13,
      "learning_rate": 1.1826726604004906e-05,
      "loss": 0.0204,
      "step": 45000
    },
    {
      "epoch": 6.2,
      "learning_rate": 1.1735912455160513e-05,
      "loss": 0.0189,
      "step": 45500
    },
    {
      "epoch": 6.27,
      "learning_rate": 1.1645098306316126e-05,
      "loss": 0.0181,
      "step": 46000
    },
    {
      "epoch": 6.33,
      "learning_rate": 1.1554284157471736e-05,
      "loss": 0.0217,
      "step": 46500
    },
    {
      "epoch": 6.4,
      "learning_rate": 1.1463470008627345e-05,
      "loss": 0.0216,
      "step": 47000
    },
    {
      "epoch": 6.47,
      "learning_rate": 1.1372655859782955e-05,
      "loss": 0.0192,
      "step": 47500
    },
    {
      "epoch": 6.54,
      "learning_rate": 1.1281841710938566e-05,
      "loss": 0.0203,
      "step": 48000
    },
    {
      "epoch": 6.61,
      "learning_rate": 1.1191027562094175e-05,
      "loss": 0.0185,
      "step": 48500
    },
    {
      "epoch": 6.67,
      "learning_rate": 1.1100213413249785e-05,
      "loss": 0.0213,
      "step": 49000
    },
    {
      "epoch": 6.74,
      "learning_rate": 1.1009399264405396e-05,
      "loss": 0.0198,
      "step": 49500
    },
    {
      "epoch": 6.81,
      "learning_rate": 1.0918585115561005e-05,
      "loss": 0.0213,
      "step": 50000
    },
    {
      "epoch": 6.88,
      "learning_rate": 1.0827770966716615e-05,
      "loss": 0.0209,
      "step": 50500
    },
    {
      "epoch": 6.95,
      "learning_rate": 1.0736956817872226e-05,
      "loss": 0.0205,
      "step": 51000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9882140755958064,
      "eval_loss": 0.05050428584218025,
      "eval_runtime": 187.0914,
      "eval_samples_per_second": 554.184,
      "eval_steps_per_second": 6.932,
      "step": 51387
    },
    {
      "epoch": 7.02,
      "learning_rate": 1.0646142669027834e-05,
      "loss": 0.0191,
      "step": 51500
    },
    {
      "epoch": 7.08,
      "learning_rate": 1.0555328520183445e-05,
      "loss": 0.0165,
      "step": 52000
    },
    {
      "epoch": 7.15,
      "learning_rate": 1.0464514371339056e-05,
      "loss": 0.0172,
      "step": 52500
    },
    {
      "epoch": 7.22,
      "learning_rate": 1.0373700222494664e-05,
      "loss": 0.0173,
      "step": 53000
    },
    {
      "epoch": 7.29,
      "learning_rate": 1.0282886073650275e-05,
      "loss": 0.0174,
      "step": 53500
    },
    {
      "epoch": 7.36,
      "learning_rate": 1.0192071924805887e-05,
      "loss": 0.0188,
      "step": 54000
    },
    {
      "epoch": 7.42,
      "learning_rate": 1.0101257775961494e-05,
      "loss": 0.0192,
      "step": 54500
    },
    {
      "epoch": 7.49,
      "learning_rate": 1.0010443627117106e-05,
      "loss": 0.0167,
      "step": 55000
    },
    {
      "epoch": 7.56,
      "learning_rate": 9.919629478272715e-06,
      "loss": 0.0183,
      "step": 55500
    },
    {
      "epoch": 7.63,
      "learning_rate": 9.828815329428326e-06,
      "loss": 0.0184,
      "step": 56000
    },
    {
      "epoch": 7.7,
      "learning_rate": 9.738001180583936e-06,
      "loss": 0.0174,
      "step": 56500
    },
    {
      "epoch": 7.76,
      "learning_rate": 9.647187031739545e-06,
      "loss": 0.0187,
      "step": 57000
    },
    {
      "epoch": 7.83,
      "learning_rate": 9.556372882895156e-06,
      "loss": 0.0181,
      "step": 57500
    },
    {
      "epoch": 7.9,
      "learning_rate": 9.465558734050766e-06,
      "loss": 0.0172,
      "step": 58000
    },
    {
      "epoch": 7.97,
      "learning_rate": 9.374744585206375e-06,
      "loss": 0.017,
      "step": 58500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9881754964651872,
      "eval_loss": 0.05063909664750099,
      "eval_runtime": 187.0892,
      "eval_samples_per_second": 554.19,
      "eval_steps_per_second": 6.933,
      "step": 58728
    },
    {
      "epoch": 8.04,
      "learning_rate": 9.283930436361987e-06,
      "loss": 0.0161,
      "step": 59000
    },
    {
      "epoch": 8.11,
      "learning_rate": 9.193116287517596e-06,
      "loss": 0.0142,
      "step": 59500
    },
    {
      "epoch": 8.17,
      "learning_rate": 9.102302138673207e-06,
      "loss": 0.0158,
      "step": 60000
    },
    {
      "epoch": 8.24,
      "learning_rate": 9.011487989828817e-06,
      "loss": 0.0175,
      "step": 60500
    },
    {
      "epoch": 8.31,
      "learning_rate": 8.920673840984426e-06,
      "loss": 0.0154,
      "step": 61000
    },
    {
      "epoch": 8.38,
      "learning_rate": 8.829859692140036e-06,
      "loss": 0.0156,
      "step": 61500
    },
    {
      "epoch": 8.45,
      "learning_rate": 8.739045543295647e-06,
      "loss": 0.0164,
      "step": 62000
    },
    {
      "epoch": 8.51,
      "learning_rate": 8.648231394451256e-06,
      "loss": 0.017,
      "step": 62500
    },
    {
      "epoch": 8.58,
      "learning_rate": 8.557417245606866e-06,
      "loss": 0.0168,
      "step": 63000
    },
    {
      "epoch": 8.65,
      "learning_rate": 8.466603096762477e-06,
      "loss": 0.0156,
      "step": 63500
    },
    {
      "epoch": 8.72,
      "learning_rate": 8.375788947918087e-06,
      "loss": 0.0173,
      "step": 64000
    },
    {
      "epoch": 8.79,
      "learning_rate": 8.284974799073696e-06,
      "loss": 0.0159,
      "step": 64500
    },
    {
      "epoch": 8.85,
      "learning_rate": 8.194160650229307e-06,
      "loss": 0.0153,
      "step": 65000
    },
    {
      "epoch": 8.92,
      "learning_rate": 8.103346501384917e-06,
      "loss": 0.0169,
      "step": 65500
    },
    {
      "epoch": 8.99,
      "learning_rate": 8.012532352540526e-06,
      "loss": 0.0152,
      "step": 66000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.988291233857045,
      "eval_loss": 0.05800553783774376,
      "eval_runtime": 187.1909,
      "eval_samples_per_second": 553.889,
      "eval_steps_per_second": 6.929,
      "step": 66069
    },
    {
      "epoch": 9.06,
      "learning_rate": 7.921718203696137e-06,
      "loss": 0.0125,
      "step": 66500
    },
    {
      "epoch": 9.13,
      "learning_rate": 7.830904054851747e-06,
      "loss": 0.0128,
      "step": 67000
    },
    {
      "epoch": 9.19,
      "learning_rate": 7.740089906007356e-06,
      "loss": 0.0144,
      "step": 67500
    },
    {
      "epoch": 9.26,
      "learning_rate": 7.649275757162966e-06,
      "loss": 0.0155,
      "step": 68000
    },
    {
      "epoch": 9.33,
      "learning_rate": 7.558461608318577e-06,
      "loss": 0.0161,
      "step": 68500
    },
    {
      "epoch": 9.4,
      "learning_rate": 7.467647459474187e-06,
      "loss": 0.0141,
      "step": 69000
    },
    {
      "epoch": 9.47,
      "learning_rate": 7.376833310629796e-06,
      "loss": 0.0149,
      "step": 69500
    },
    {
      "epoch": 9.54,
      "learning_rate": 7.286019161785407e-06,
      "loss": 0.0145,
      "step": 70000
    },
    {
      "epoch": 9.6,
      "learning_rate": 7.1952050129410165e-06,
      "loss": 0.0161,
      "step": 70500
    },
    {
      "epoch": 9.67,
      "learning_rate": 7.104390864096626e-06,
      "loss": 0.0148,
      "step": 71000
    },
    {
      "epoch": 9.74,
      "learning_rate": 7.0135767152522375e-06,
      "loss": 0.0157,
      "step": 71500
    },
    {
      "epoch": 9.81,
      "learning_rate": 6.922762566407847e-06,
      "loss": 0.0135,
      "step": 72000
    },
    {
      "epoch": 9.88,
      "learning_rate": 6.831948417563457e-06,
      "loss": 0.0149,
      "step": 72500
    },
    {
      "epoch": 9.94,
      "learning_rate": 6.741134268719067e-06,
      "loss": 0.0133,
      "step": 73000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9885805773366897,
      "eval_loss": 0.05762995034456253,
      "eval_runtime": 187.1376,
      "eval_samples_per_second": 554.047,
      "eval_steps_per_second": 6.931,
      "step": 73410
    },
    {
      "epoch": 10.01,
      "learning_rate": 6.650320119874677e-06,
      "loss": 0.0144,
      "step": 73500
    },
    {
      "epoch": 10.08,
      "learning_rate": 6.559505971030287e-06,
      "loss": 0.011,
      "step": 74000
    },
    {
      "epoch": 10.15,
      "learning_rate": 6.468691822185897e-06,
      "loss": 0.0129,
      "step": 74500
    },
    {
      "epoch": 10.22,
      "learning_rate": 6.377877673341507e-06,
      "loss": 0.0116,
      "step": 75000
    },
    {
      "epoch": 10.28,
      "learning_rate": 6.287063524497117e-06,
      "loss": 0.0125,
      "step": 75500
    },
    {
      "epoch": 10.35,
      "learning_rate": 6.196249375652728e-06,
      "loss": 0.0133,
      "step": 76000
    },
    {
      "epoch": 10.42,
      "learning_rate": 6.105435226808338e-06,
      "loss": 0.0142,
      "step": 76500
    },
    {
      "epoch": 10.49,
      "learning_rate": 6.014621077963947e-06,
      "loss": 0.0123,
      "step": 77000
    },
    {
      "epoch": 10.56,
      "learning_rate": 5.923806929119558e-06,
      "loss": 0.0133,
      "step": 77500
    },
    {
      "epoch": 10.63,
      "learning_rate": 5.8329927802751675e-06,
      "loss": 0.0142,
      "step": 78000
    },
    {
      "epoch": 10.69,
      "learning_rate": 5.742178631430777e-06,
      "loss": 0.0124,
      "step": 78500
    },
    {
      "epoch": 10.76,
      "learning_rate": 5.651364482586388e-06,
      "loss": 0.015,
      "step": 79000
    },
    {
      "epoch": 10.83,
      "learning_rate": 5.560550333741997e-06,
      "loss": 0.013,
      "step": 79500
    },
    {
      "epoch": 10.9,
      "learning_rate": 5.469736184897607e-06,
      "loss": 0.0123,
      "step": 80000
    },
    {
      "epoch": 10.97,
      "learning_rate": 5.3789220360532176e-06,
      "loss": 0.0135,
      "step": 80500
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9884551951621771,
      "eval_loss": 0.05924547091126442,
      "eval_runtime": 187.3771,
      "eval_samples_per_second": 553.339,
      "eval_steps_per_second": 6.922,
      "step": 80751
    },
    {
      "epoch": 11.03,
      "learning_rate": 5.288107887208827e-06,
      "loss": 0.0145,
      "step": 81000
    },
    {
      "epoch": 11.1,
      "learning_rate": 5.197293738364437e-06,
      "loss": 0.0115,
      "step": 81500
    },
    {
      "epoch": 11.17,
      "learning_rate": 5.106479589520048e-06,
      "loss": 0.0107,
      "step": 82000
    },
    {
      "epoch": 11.24,
      "learning_rate": 5.015665440675658e-06,
      "loss": 0.0108,
      "step": 82500
    },
    {
      "epoch": 11.31,
      "learning_rate": 4.924851291831268e-06,
      "loss": 0.012,
      "step": 83000
    },
    {
      "epoch": 11.37,
      "learning_rate": 4.834037142986877e-06,
      "loss": 0.0111,
      "step": 83500
    },
    {
      "epoch": 11.44,
      "learning_rate": 4.743222994142488e-06,
      "loss": 0.0111,
      "step": 84000
    },
    {
      "epoch": 11.51,
      "learning_rate": 4.6524088452980975e-06,
      "loss": 0.0126,
      "step": 84500
    },
    {
      "epoch": 11.58,
      "learning_rate": 4.561594696453708e-06,
      "loss": 0.0127,
      "step": 85000
    },
    {
      "epoch": 11.65,
      "learning_rate": 4.470780547609318e-06,
      "loss": 0.0125,
      "step": 85500
    },
    {
      "epoch": 11.72,
      "learning_rate": 4.379966398764927e-06,
      "loss": 0.0129,
      "step": 86000
    },
    {
      "epoch": 11.78,
      "learning_rate": 4.289152249920538e-06,
      "loss": 0.0118,
      "step": 86500
    },
    {
      "epoch": 11.85,
      "learning_rate": 4.198338101076148e-06,
      "loss": 0.0117,
      "step": 87000
    },
    {
      "epoch": 11.92,
      "learning_rate": 4.107523952231758e-06,
      "loss": 0.0133,
      "step": 87500
    },
    {
      "epoch": 11.99,
      "learning_rate": 4.016709803387368e-06,
      "loss": 0.0124,
      "step": 88000
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9888699208163344,
      "eval_loss": 0.06216460466384888,
      "eval_runtime": 187.1872,
      "eval_samples_per_second": 553.9,
      "eval_steps_per_second": 6.929,
      "step": 88092
    },
    {
      "epoch": 12.06,
      "learning_rate": 3.925895654542978e-06,
      "loss": 0.0109,
      "step": 88500
    },
    {
      "epoch": 12.12,
      "learning_rate": 3.835081505698588e-06,
      "loss": 0.0108,
      "step": 89000
    },
    {
      "epoch": 12.19,
      "learning_rate": 3.744267356854198e-06,
      "loss": 0.0109,
      "step": 89500
    },
    {
      "epoch": 12.26,
      "learning_rate": 3.6534532080098086e-06,
      "loss": 0.0122,
      "step": 90000
    },
    {
      "epoch": 12.33,
      "learning_rate": 3.5626390591654182e-06,
      "loss": 0.0117,
      "step": 90500
    },
    {
      "epoch": 12.4,
      "learning_rate": 3.4718249103210283e-06,
      "loss": 0.0106,
      "step": 91000
    },
    {
      "epoch": 12.46,
      "learning_rate": 3.3810107614766384e-06,
      "loss": 0.0114,
      "step": 91500
    },
    {
      "epoch": 12.53,
      "learning_rate": 3.290196612632248e-06,
      "loss": 0.0116,
      "step": 92000
    },
    {
      "epoch": 12.6,
      "learning_rate": 3.1993824637878586e-06,
      "loss": 0.0103,
      "step": 92500
    },
    {
      "epoch": 12.67,
      "learning_rate": 3.1085683149434687e-06,
      "loss": 0.0104,
      "step": 93000
    },
    {
      "epoch": 12.74,
      "learning_rate": 3.0177541660990784e-06,
      "loss": 0.0123,
      "step": 93500
    },
    {
      "epoch": 12.8,
      "learning_rate": 2.9269400172546885e-06,
      "loss": 0.0116,
      "step": 94000
    },
    {
      "epoch": 12.87,
      "learning_rate": 2.8361258684102986e-06,
      "loss": 0.0114,
      "step": 94500
    },
    {
      "epoch": 12.94,
      "learning_rate": 2.7453117195659083e-06,
      "loss": 0.0101,
      "step": 95000
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.988889210381644,
      "eval_loss": 0.06189201399683952,
      "eval_runtime": 187.272,
      "eval_samples_per_second": 553.649,
      "eval_steps_per_second": 6.926,
      "step": 95433
    },
    {
      "epoch": 13.01,
      "learning_rate": 2.654497570721519e-06,
      "loss": 0.0123,
      "step": 95500
    },
    {
      "epoch": 13.08,
      "learning_rate": 2.563683421877129e-06,
      "loss": 0.0085,
      "step": 96000
    },
    {
      "epoch": 13.15,
      "learning_rate": 2.4728692730327386e-06,
      "loss": 0.0097,
      "step": 96500
    },
    {
      "epoch": 13.21,
      "learning_rate": 2.3820551241883487e-06,
      "loss": 0.0093,
      "step": 97000
    },
    {
      "epoch": 13.28,
      "learning_rate": 2.2912409753439588e-06,
      "loss": 0.0106,
      "step": 97500
    },
    {
      "epoch": 13.35,
      "learning_rate": 2.200426826499569e-06,
      "loss": 0.0105,
      "step": 98000
    },
    {
      "epoch": 13.42,
      "learning_rate": 2.109612677655179e-06,
      "loss": 0.0104,
      "step": 98500
    },
    {
      "epoch": 13.49,
      "learning_rate": 2.018798528810789e-06,
      "loss": 0.0111,
      "step": 99000
    },
    {
      "epoch": 13.55,
      "learning_rate": 1.9279843799663987e-06,
      "loss": 0.0095,
      "step": 99500
    },
    {
      "epoch": 13.62,
      "learning_rate": 1.837170231122009e-06,
      "loss": 0.0105,
      "step": 100000
    },
    {
      "epoch": 13.69,
      "learning_rate": 1.7463560822776191e-06,
      "loss": 0.011,
      "step": 100500
    },
    {
      "epoch": 13.76,
      "learning_rate": 1.655541933433229e-06,
      "loss": 0.0115,
      "step": 101000
    },
    {
      "epoch": 13.83,
      "learning_rate": 1.564727784588839e-06,
      "loss": 0.0107,
      "step": 101500
    },
    {
      "epoch": 13.89,
      "learning_rate": 1.4739136357444492e-06,
      "loss": 0.0095,
      "step": 102000
    },
    {
      "epoch": 13.96,
      "learning_rate": 1.383099486900059e-06,
      "loss": 0.0116,
      "step": 102500
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9891978434265983,
      "eval_loss": 0.06299556791782379,
      "eval_runtime": 187.242,
      "eval_samples_per_second": 553.738,
      "eval_steps_per_second": 6.927,
      "step": 102774
    },
    {
      "epoch": 14.03,
      "learning_rate": 1.292285338055669e-06,
      "loss": 0.011,
      "step": 103000
    },
    {
      "epoch": 14.1,
      "learning_rate": 1.201471189211279e-06,
      "loss": 0.0104,
      "step": 103500
    },
    {
      "epoch": 14.17,
      "learning_rate": 1.1106570403668892e-06,
      "loss": 0.0086,
      "step": 104000
    },
    {
      "epoch": 14.24,
      "learning_rate": 1.0198428915224993e-06,
      "loss": 0.0091,
      "step": 104500
    },
    {
      "epoch": 14.3,
      "learning_rate": 9.290287426781093e-07,
      "loss": 0.0101,
      "step": 105000
    },
    {
      "epoch": 14.37,
      "learning_rate": 8.382145938337194e-07,
      "loss": 0.0103,
      "step": 105500
    },
    {
      "epoch": 14.44,
      "learning_rate": 7.474004449893294e-07,
      "loss": 0.0082,
      "step": 106000
    },
    {
      "epoch": 14.51,
      "learning_rate": 6.565862961449394e-07,
      "loss": 0.0114,
      "step": 106500
    },
    {
      "epoch": 14.58,
      "learning_rate": 5.657721473005494e-07,
      "loss": 0.0085,
      "step": 107000
    },
    {
      "epoch": 14.64,
      "learning_rate": 4.749579984561595e-07,
      "loss": 0.0109,
      "step": 107500
    },
    {
      "epoch": 14.71,
      "learning_rate": 3.841438496117696e-07,
      "loss": 0.0095,
      "step": 108000
    },
    {
      "epoch": 14.78,
      "learning_rate": 2.933297007673796e-07,
      "loss": 0.0094,
      "step": 108500
    },
    {
      "epoch": 14.85,
      "learning_rate": 2.0251555192298962e-07,
      "loss": 0.0087,
      "step": 109000
    },
    {
      "epoch": 14.92,
      "learning_rate": 1.1170140307859966e-07,
      "loss": 0.0104,
      "step": 109500
    },
    {
      "epoch": 14.98,
      "learning_rate": 2.088725423420969e-08,
      "loss": 0.009,
      "step": 110000
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9890242373388116,
      "eval_loss": 0.06419195979833603,
      "eval_runtime": 187.2506,
      "eval_samples_per_second": 553.712,
      "eval_steps_per_second": 6.927,
      "step": 110115
    }
  ],
  "max_steps": 110115,
  "num_train_epochs": 15,
  "total_flos": 1.3235641889555946e+17,
  "trial_name": null,
  "trial_params": null
}