{
  "best_global_step": 16020,
  "best_metric": 0.7087390761548065,
  "best_model_checkpoint": "/content/drive/MyDrive/final/banglabert_emotion_model/checkpoint-16020",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 16020,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12484394506866417,
      "grad_norm": 13.420171737670898,
      "learning_rate": 1.9501622971285894e-05,
      "loss": 2.7617490234375,
      "step": 500
    },
    {
      "epoch": 0.24968789013732834,
      "grad_norm": 15.357503890991211,
      "learning_rate": 1.900224719101124e-05,
      "loss": 2.226674072265625,
      "step": 1000
    },
    {
      "epoch": 0.37453183520599254,
      "grad_norm": 25.786678314208984,
      "learning_rate": 1.850287141073658e-05,
      "loss": 2.002759521484375,
      "step": 1500
    },
    {
      "epoch": 0.4993757802746567,
      "grad_norm": 28.906641006469727,
      "learning_rate": 1.8003495630461924e-05,
      "loss": 1.9993841552734375,
      "step": 2000
    },
    {
      "epoch": 0.6242197253433208,
      "grad_norm": 16.18419075012207,
      "learning_rate": 1.7504119850187267e-05,
      "loss": 1.92766845703125,
      "step": 2500
    },
    {
      "epoch": 0.7490636704119851,
      "grad_norm": 11.467696189880371,
      "learning_rate": 1.7004744069912612e-05,
      "loss": 1.8748406982421875,
      "step": 3000
    },
    {
      "epoch": 0.8739076154806492,
      "grad_norm": 22.702239990234375,
      "learning_rate": 1.650536828963795e-05,
      "loss": 1.84278564453125,
      "step": 3500
    },
    {
      "epoch": 0.9987515605493134,
      "grad_norm": 20.29677391052246,
      "learning_rate": 1.6005992509363297e-05,
      "loss": 1.830066162109375,
      "step": 4000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6730961298377028,
      "eval_loss": 0.853507936000824,
      "eval_runtime": 31.6983,
      "eval_samples_per_second": 505.389,
      "eval_steps_per_second": 31.611,
      "step": 4005
    },
    {
      "epoch": 1.1235955056179776,
      "grad_norm": 14.780792236328125,
      "learning_rate": 1.5506616729088643e-05,
      "loss": 1.4483494873046876,
      "step": 4500
    },
    {
      "epoch": 1.2484394506866416,
      "grad_norm": 12.895259857177734,
      "learning_rate": 1.5007240948813983e-05,
      "loss": 1.4603758544921874,
      "step": 5000
    },
    {
      "epoch": 1.373283395755306,
      "grad_norm": 14.621040344238281,
      "learning_rate": 1.4507865168539327e-05,
      "loss": 1.4498388671875,
      "step": 5500
    },
    {
      "epoch": 1.4981273408239701,
      "grad_norm": 18.11307144165039,
      "learning_rate": 1.400848938826467e-05,
      "loss": 1.4085994873046874,
      "step": 6000
    },
    {
      "epoch": 1.6229712858926342,
      "grad_norm": 14.37695598602295,
      "learning_rate": 1.3509113607990014e-05,
      "loss": 1.425572998046875,
      "step": 6500
    },
    {
      "epoch": 1.7478152309612984,
      "grad_norm": 27.768917083740234,
      "learning_rate": 1.3009737827715356e-05,
      "loss": 1.4111923828125,
      "step": 7000
    },
    {
      "epoch": 1.8726591760299627,
      "grad_norm": 22.15481185913086,
      "learning_rate": 1.25103620474407e-05,
      "loss": 1.4088411865234376,
      "step": 7500
    },
    {
      "epoch": 1.9975031210986267,
      "grad_norm": 35.64712905883789,
      "learning_rate": 1.2010986267166042e-05,
      "loss": 1.4123983154296875,
      "step": 8000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.695880149812734,
      "eval_loss": 0.8021184206008911,
      "eval_runtime": 32.1386,
      "eval_samples_per_second": 498.465,
      "eval_steps_per_second": 31.177,
      "step": 8010
    },
    {
      "epoch": 2.1223470661672907,
      "grad_norm": 10.319637298583984,
      "learning_rate": 1.1511610486891386e-05,
      "loss": 1.0521787109375,
      "step": 8500
    },
    {
      "epoch": 2.247191011235955,
      "grad_norm": 38.24408721923828,
      "learning_rate": 1.1012234706616729e-05,
      "loss": 1.0608070068359374,
      "step": 9000
    },
    {
      "epoch": 2.3720349563046192,
      "grad_norm": 20.784549713134766,
      "learning_rate": 1.0512858926342073e-05,
      "loss": 1.009867919921875,
      "step": 9500
    },
    {
      "epoch": 2.4968789013732833,
      "grad_norm": 22.94487762451172,
      "learning_rate": 1.0013483146067418e-05,
      "loss": 0.9883866577148438,
      "step": 10000
    },
    {
      "epoch": 2.6217228464419478,
      "grad_norm": 11.88857650756836,
      "learning_rate": 9.514107365792759e-06,
      "loss": 1.0441209716796875,
      "step": 10500
    },
    {
      "epoch": 2.746566791510612,
      "grad_norm": 13.06592845916748,
      "learning_rate": 9.014731585518103e-06,
      "loss": 1.0044090576171876,
      "step": 11000
    },
    {
      "epoch": 2.871410736579276,
      "grad_norm": 25.207258224487305,
      "learning_rate": 8.515355805243445e-06,
      "loss": 1.0176537475585938,
      "step": 11500
    },
    {
      "epoch": 2.9962546816479403,
      "grad_norm": 23.95787239074707,
      "learning_rate": 8.01598002496879e-06,
      "loss": 0.9907133178710937,
      "step": 12000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6981897627965044,
      "eval_loss": 0.9493064880371094,
      "eval_runtime": 31.8051,
      "eval_samples_per_second": 503.692,
      "eval_steps_per_second": 31.504,
      "step": 12015
    },
    {
      "epoch": 3.1210986267166043,
      "grad_norm": 46.73135757446289,
      "learning_rate": 7.516604244694133e-06,
      "loss": 0.7290467529296875,
      "step": 12500
    },
    {
      "epoch": 3.2459425717852683,
      "grad_norm": 33.79011535644531,
      "learning_rate": 7.017228464419476e-06,
      "loss": 0.7134989624023438,
      "step": 13000
    },
    {
      "epoch": 3.370786516853933,
      "grad_norm": 16.588682174682617,
      "learning_rate": 6.5178526841448195e-06,
      "loss": 0.7361919555664063,
      "step": 13500
    },
    {
      "epoch": 3.495630461922597,
      "grad_norm": 39.797035217285156,
      "learning_rate": 6.018476903870163e-06,
      "loss": 0.7094050903320313,
      "step": 14000
    },
    {
      "epoch": 3.620474406991261,
      "grad_norm": 52.334957122802734,
      "learning_rate": 5.519101123595506e-06,
      "loss": 0.704403564453125,
      "step": 14500
    },
    {
      "epoch": 3.7453183520599254,
      "grad_norm": 38.2628288269043,
      "learning_rate": 5.019725343320849e-06,
      "loss": 0.71558984375,
      "step": 15000
    },
    {
      "epoch": 3.8701622971285894,
      "grad_norm": 22.619749069213867,
      "learning_rate": 4.520349563046192e-06,
      "loss": 0.7283433227539062,
      "step": 15500
    },
    {
      "epoch": 3.9950062421972534,
      "grad_norm": 35.713077545166016,
      "learning_rate": 4.020973782771536e-06,
      "loss": 0.7376478881835937,
      "step": 16000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7087390761548065,
      "eval_loss": 1.003607988357544,
      "eval_runtime": 31.9071,
      "eval_samples_per_second": 502.083,
      "eval_steps_per_second": 31.404,
      "step": 16020
    }
  ],
  "logging_steps": 500,
  "max_steps": 20025,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 1.6860235708624896e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}