{
  "best_global_step": 26970,
  "best_metric": 0.7815828323364258,
  "best_model_checkpoint": "emotion_stress_model_balanced/checkpoint-26970",
  "epoch": 15.0,
  "eval_steps": 500,
  "global_step": 26970,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27808676307007785,
      "grad_norm": 1.7513720989227295,
      "learning_rate": 2.949962852897474e-06,
      "loss": 2.0324,
      "step": 500
    },
    {
      "epoch": 0.5561735261401557,
      "grad_norm": 1.5362915992736816,
      "learning_rate": 2.89424219910847e-06,
      "loss": 1.9445,
      "step": 1000
    },
    {
      "epoch": 0.8342602892102335,
      "grad_norm": 1.602758526802063,
      "learning_rate": 2.838521545319465e-06,
      "loss": 1.864,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.7139734029769897,
      "eval_runtime": 46.8601,
      "eval_samples_per_second": 801.705,
      "eval_steps_per_second": 100.213,
      "step": 1798
    },
    {
      "epoch": 1.1123470522803114,
      "grad_norm": 1.359454870223999,
      "learning_rate": 2.782800891530461e-06,
      "loss": 1.7878,
      "step": 2000
    },
    {
      "epoch": 1.3904338153503892,
      "grad_norm": 1.6392908096313477,
      "learning_rate": 2.727080237741456e-06,
      "loss": 1.7208,
      "step": 2500
    },
    {
      "epoch": 1.668520578420467,
      "grad_norm": 1.5447863340377808,
      "learning_rate": 2.6713595839524517e-06,
      "loss": 1.6523,
      "step": 3000
    },
    {
      "epoch": 1.946607341490545,
      "grad_norm": 1.3621774911880493,
      "learning_rate": 2.6156389301634473e-06,
      "loss": 1.5958,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.4455991983413696,
      "eval_runtime": 21.1788,
      "eval_samples_per_second": 1773.853,
      "eval_steps_per_second": 221.732,
      "step": 3596
    },
    {
      "epoch": 2.2246941045606228,
      "grad_norm": 1.2821935415267944,
      "learning_rate": 2.559918276374443e-06,
      "loss": 1.5441,
      "step": 4000
    },
    {
      "epoch": 2.5027808676307006,
      "grad_norm": 1.2539781332015991,
      "learning_rate": 2.5041976225854384e-06,
      "loss": 1.4902,
      "step": 4500
    },
    {
      "epoch": 2.7808676307007785,
      "grad_norm": 1.247044324874878,
      "learning_rate": 2.448476968796434e-06,
      "loss": 1.4496,
      "step": 5000
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.2488250732421875,
      "eval_runtime": 21.3725,
      "eval_samples_per_second": 1757.774,
      "eval_steps_per_second": 219.722,
      "step": 5394
    },
    {
      "epoch": 3.0589543937708563,
      "grad_norm": 1.122979998588562,
      "learning_rate": 2.3927563150074296e-06,
      "loss": 1.4087,
      "step": 5500
    },
    {
      "epoch": 3.337041156840934,
      "grad_norm": 1.197558045387268,
      "learning_rate": 2.337035661218425e-06,
      "loss": 1.3679,
      "step": 6000
    },
    {
      "epoch": 3.6151279199110125,
      "grad_norm": 1.2191081047058105,
      "learning_rate": 2.2813150074294203e-06,
      "loss": 1.3373,
      "step": 6500
    },
    {
      "epoch": 3.89321468298109,
      "grad_norm": 1.0837751626968384,
      "learning_rate": 2.2255943536404163e-06,
      "loss": 1.3151,
      "step": 7000
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.1083296537399292,
      "eval_runtime": 21.3785,
      "eval_samples_per_second": 1757.28,
      "eval_steps_per_second": 219.66,
      "step": 7192
    },
    {
      "epoch": 4.171301446051168,
      "grad_norm": 1.2327854633331299,
      "learning_rate": 2.1698736998514114e-06,
      "loss": 1.2756,
      "step": 7500
    },
    {
      "epoch": 4.4493882091212456,
      "grad_norm": 1.0573621988296509,
      "learning_rate": 2.1141530460624074e-06,
      "loss": 1.2522,
      "step": 8000
    },
    {
      "epoch": 4.727474972191324,
      "grad_norm": 1.0322808027267456,
      "learning_rate": 2.0584323922734026e-06,
      "loss": 1.2318,
      "step": 8500
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.0092095136642456,
      "eval_runtime": 21.2558,
      "eval_samples_per_second": 1767.427,
      "eval_steps_per_second": 220.928,
      "step": 8990
    },
    {
      "epoch": 5.005561735261401,
      "grad_norm": 0.9742701649665833,
      "learning_rate": 2.002711738484398e-06,
      "loss": 1.2109,
      "step": 9000
    },
    {
      "epoch": 5.2836484983314795,
      "grad_norm": 0.923886239528656,
      "learning_rate": 1.9469910846953937e-06,
      "loss": 1.1863,
      "step": 9500
    },
    {
      "epoch": 5.561735261401557,
      "grad_norm": 0.8879143595695496,
      "learning_rate": 1.8912704309063893e-06,
      "loss": 1.1806,
      "step": 10000
    },
    {
      "epoch": 5.839822024471635,
      "grad_norm": 1.0213676691055298,
      "learning_rate": 1.835549777117385e-06,
      "loss": 1.1754,
      "step": 10500
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.9406551122665405,
      "eval_runtime": 21.4277,
      "eval_samples_per_second": 1753.245,
      "eval_steps_per_second": 219.156,
      "step": 10788
    },
    {
      "epoch": 6.117908787541713,
      "grad_norm": 1.061405897140503,
      "learning_rate": 1.7798291233283805e-06,
      "loss": 1.1517,
      "step": 11000
    },
    {
      "epoch": 6.395995550611791,
      "grad_norm": 0.8349337577819824,
      "learning_rate": 1.7241084695393758e-06,
      "loss": 1.1448,
      "step": 11500
    },
    {
      "epoch": 6.674082313681868,
      "grad_norm": 1.023738980293274,
      "learning_rate": 1.6683878157503716e-06,
      "loss": 1.1415,
      "step": 12000
    },
    {
      "epoch": 6.952169076751947,
      "grad_norm": 0.9870001673698425,
      "learning_rate": 1.612667161961367e-06,
      "loss": 1.1213,
      "step": 12500
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.8925299048423767,
      "eval_runtime": 21.5166,
      "eval_samples_per_second": 1745.999,
      "eval_steps_per_second": 218.25,
      "step": 12586
    },
    {
      "epoch": 7.230255839822025,
      "grad_norm": 1.0453287363052368,
      "learning_rate": 1.5569465081723627e-06,
      "loss": 1.1173,
      "step": 13000
    },
    {
      "epoch": 7.508342602892102,
      "grad_norm": 0.8402040004730225,
      "learning_rate": 1.5012258543833581e-06,
      "loss": 1.1053,
      "step": 13500
    },
    {
      "epoch": 7.78642936596218,
      "grad_norm": 0.9418850541114807,
      "learning_rate": 1.4455052005943537e-06,
      "loss": 1.1068,
      "step": 14000
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.8576251268386841,
      "eval_runtime": 21.4862,
      "eval_samples_per_second": 1748.467,
      "eval_steps_per_second": 218.558,
      "step": 14384
    },
    {
      "epoch": 8.064516129032258,
      "grad_norm": 0.9174266457557678,
      "learning_rate": 1.3897845468053493e-06,
      "loss": 1.0912,
      "step": 14500
    },
    {
      "epoch": 8.342602892102336,
      "grad_norm": 0.8031694889068604,
      "learning_rate": 1.3340638930163446e-06,
      "loss": 1.0819,
      "step": 15000
    },
    {
      "epoch": 8.620689655172415,
      "grad_norm": 0.8880692720413208,
      "learning_rate": 1.2783432392273402e-06,
      "loss": 1.0889,
      "step": 15500
    },
    {
      "epoch": 8.898776418242491,
      "grad_norm": 0.8549273014068604,
      "learning_rate": 1.2226225854383358e-06,
      "loss": 1.0765,
      "step": 16000
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.8325429558753967,
      "eval_runtime": 21.4809,
      "eval_samples_per_second": 1748.903,
      "eval_steps_per_second": 218.613,
      "step": 16182
    },
    {
      "epoch": 9.17686318131257,
      "grad_norm": 0.7732747197151184,
      "learning_rate": 1.1669019316493313e-06,
      "loss": 1.0792,
      "step": 16500
    },
    {
      "epoch": 9.454949944382648,
      "grad_norm": 0.8062688112258911,
      "learning_rate": 1.111181277860327e-06,
      "loss": 1.0736,
      "step": 17000
    },
    {
      "epoch": 9.733036707452726,
      "grad_norm": 0.873096227645874,
      "learning_rate": 1.0554606240713225e-06,
      "loss": 1.0707,
      "step": 17500
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.8145096302032471,
      "eval_runtime": 21.1956,
      "eval_samples_per_second": 1772.441,
      "eval_steps_per_second": 221.555,
      "step": 17980
    },
    {
      "epoch": 10.011123470522802,
      "grad_norm": 0.7561053037643433,
      "learning_rate": 9.997399702823179e-07,
      "loss": 1.0761,
      "step": 18000
    },
    {
      "epoch": 10.28921023359288,
      "grad_norm": 0.770944356918335,
      "learning_rate": 9.440193164933135e-07,
      "loss": 1.0601,
      "step": 18500
    },
    {
      "epoch": 10.567296996662959,
      "grad_norm": 0.8369573354721069,
      "learning_rate": 8.882986627043091e-07,
      "loss": 1.0777,
      "step": 19000
    },
    {
      "epoch": 10.845383759733037,
      "grad_norm": 0.9367430210113525,
      "learning_rate": 8.325780089153047e-07,
      "loss": 1.0635,
      "step": 19500
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.8015358448028564,
      "eval_runtime": 21.488,
      "eval_samples_per_second": 1748.322,
      "eval_steps_per_second": 218.54,
      "step": 19778
    },
    {
      "epoch": 11.123470522803114,
      "grad_norm": 0.765078604221344,
      "learning_rate": 7.768573551263003e-07,
      "loss": 1.0579,
      "step": 20000
    },
    {
      "epoch": 11.401557285873192,
      "grad_norm": 0.7660267949104309,
      "learning_rate": 7.211367013372957e-07,
      "loss": 1.0598,
      "step": 20500
    },
    {
      "epoch": 11.67964404894327,
      "grad_norm": 0.8136441111564636,
      "learning_rate": 6.654160475482912e-07,
      "loss": 1.0427,
      "step": 21000
    },
    {
      "epoch": 11.957730812013349,
      "grad_norm": 0.7501266598701477,
      "learning_rate": 6.096953937592868e-07,
      "loss": 1.0626,
      "step": 21500
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.7923984527587891,
      "eval_runtime": 21.5573,
      "eval_samples_per_second": 1742.708,
      "eval_steps_per_second": 217.839,
      "step": 21576
    },
    {
      "epoch": 12.235817575083425,
      "grad_norm": 0.895750105381012,
      "learning_rate": 5.539747399702823e-07,
      "loss": 1.054,
      "step": 22000
    },
    {
      "epoch": 12.513904338153504,
      "grad_norm": 0.9563328623771667,
      "learning_rate": 4.982540861812778e-07,
      "loss": 1.0396,
      "step": 22500
    },
    {
      "epoch": 12.791991101223582,
      "grad_norm": 0.8842599391937256,
      "learning_rate": 4.4253343239227344e-07,
      "loss": 1.0475,
      "step": 23000
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.786158561706543,
      "eval_runtime": 21.3873,
      "eval_samples_per_second": 1756.555,
      "eval_steps_per_second": 219.569,
      "step": 23374
    },
    {
      "epoch": 13.07007786429366,
      "grad_norm": 0.6965476870536804,
      "learning_rate": 3.86812778603269e-07,
      "loss": 1.0429,
      "step": 23500
    },
    {
      "epoch": 13.348164627363737,
      "grad_norm": 0.9398712515830994,
      "learning_rate": 3.310921248142645e-07,
      "loss": 1.0404,
      "step": 24000
    },
    {
      "epoch": 13.626251390433815,
      "grad_norm": 0.9795758128166199,
      "learning_rate": 2.7537147102526e-07,
      "loss": 1.0469,
      "step": 24500
    },
    {
      "epoch": 13.904338153503893,
      "grad_norm": 0.8730781674385071,
      "learning_rate": 2.1965081723625558e-07,
      "loss": 1.0361,
      "step": 25000
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.7827068567276001,
      "eval_runtime": 21.4998,
      "eval_samples_per_second": 1747.363,
      "eval_steps_per_second": 218.42,
      "step": 25172
    },
    {
      "epoch": 14.182424916573972,
      "grad_norm": 0.9993116855621338,
      "learning_rate": 1.6393016344725113e-07,
      "loss": 1.0525,
      "step": 25500
    },
    {
      "epoch": 14.46051167964405,
      "grad_norm": 0.9638302326202393,
      "learning_rate": 1.0820950965824665e-07,
      "loss": 1.05,
      "step": 26000
    },
    {
      "epoch": 14.738598442714126,
      "grad_norm": 0.8064911961555481,
      "learning_rate": 5.24888558692422e-08,
      "loss": 1.0457,
      "step": 26500
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.7815828323364258,
      "eval_runtime": 21.1724,
      "eval_samples_per_second": 1774.387,
      "eval_steps_per_second": 221.798,
      "step": 26970
    }
  ],
  "logging_steps": 500,
  "max_steps": 26970,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.687298365324853e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}