{
  "best_global_step": 200,
  "best_metric": 0.0003925538039766252,
  "best_model_checkpoint": "tr-sentiment-model\\checkpoint-200",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 31.119638442993164,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.8165468215942383,
      "step": 5
    },
    {
      "epoch": 0.1,
      "grad_norm": 12.373876571655273,
      "learning_rate": 1.91e-05,
      "loss": 0.5896224498748779,
      "step": 10
    },
    {
      "epoch": 0.15,
      "grad_norm": 10.269111633300781,
      "learning_rate": 1.86e-05,
      "loss": 0.6049572467803955,
      "step": 15
    },
    {
      "epoch": 0.2,
      "grad_norm": 19.01222801208496,
      "learning_rate": 1.8100000000000003e-05,
      "loss": 0.6137516021728515,
      "step": 20
    },
    {
      "epoch": 0.25,
      "grad_norm": 15.121289253234863,
      "learning_rate": 1.76e-05,
      "loss": 0.47811298370361327,
      "step": 25
    },
    {
      "epoch": 0.3,
      "grad_norm": 15.115927696228027,
      "learning_rate": 1.7100000000000002e-05,
      "loss": 0.4332573890686035,
      "step": 30
    },
    {
      "epoch": 0.35,
      "grad_norm": 11.673855781555176,
      "learning_rate": 1.66e-05,
      "loss": 0.28487935066223147,
      "step": 35
    },
    {
      "epoch": 0.4,
      "grad_norm": 23.57175064086914,
      "learning_rate": 1.6100000000000002e-05,
      "loss": 0.20236294269561766,
      "step": 40
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.82466721534729,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 0.11973601579666138,
      "step": 45
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.8704144954681396,
      "learning_rate": 1.5100000000000001e-05,
      "loss": 0.04779849350452423,
      "step": 50
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5238797068595886,
      "learning_rate": 1.46e-05,
      "loss": 0.047495442628860476,
      "step": 55
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.25120118260383606,
      "learning_rate": 1.41e-05,
      "loss": 0.010647669434547424,
      "step": 60
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.1290791928768158,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 0.008740333467721939,
      "step": 65
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.07909256219863892,
      "learning_rate": 1.3100000000000002e-05,
      "loss": 0.004749870300292969,
      "step": 70
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.09023287892341614,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 0.002569456771016121,
      "step": 75
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.06576652824878693,
      "learning_rate": 1.2100000000000001e-05,
      "loss": 0.0023083891719579697,
      "step": 80
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.061244454234838486,
      "learning_rate": 1.16e-05,
      "loss": 0.0019361034035682678,
      "step": 85
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.05338131636381149,
      "learning_rate": 1.1100000000000002e-05,
      "loss": 0.001786946691572666,
      "step": 90
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.03496626392006874,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 0.0014607097022235394,
      "step": 95
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0410640686750412,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 0.0014525197446346283,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0007943756063468754,
      "eval_runtime": 26.5532,
      "eval_samples_per_second": 3.766,
      "eval_steps_per_second": 0.942,
      "step": 100
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.03476925566792488,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.001148415356874466,
      "step": 105
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.030995864421129227,
      "learning_rate": 9.100000000000001e-06,
      "loss": 0.0012477874755859376,
      "step": 110
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.022863049060106277,
      "learning_rate": 8.6e-06,
      "loss": 0.0009570728056132793,
      "step": 115
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.025992313399910927,
      "learning_rate": 8.1e-06,
      "loss": 0.0009571532718837261,
      "step": 120
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.02837001159787178,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.0009419848211109638,
      "step": 125
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.020482724532485008,
      "learning_rate": 7.100000000000001e-06,
      "loss": 0.000887809693813324,
      "step": 130
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.024091143161058426,
      "learning_rate": 6.600000000000001e-06,
      "loss": 0.0008436970412731171,
      "step": 135
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.019256388768553734,
      "learning_rate": 6.1e-06,
      "loss": 0.0007690337486565113,
      "step": 140
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.0230976864695549,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.0007221823558211327,
      "step": 145
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.01936892233788967,
      "learning_rate": 5.1e-06,
      "loss": 0.0007346693892031908,
      "step": 150
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.021034760400652885,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.0007220861036330462,
      "step": 155
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.01564309187233448,
      "learning_rate": 4.1e-06,
      "loss": 0.0006218148395419121,
      "step": 160
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.016282767057418823,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0006177808623760939,
      "step": 165
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.022097593173384666,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0006359980441629886,
      "step": 170
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.01770627871155739,
      "learning_rate": 2.6e-06,
      "loss": 0.0006778056267648935,
      "step": 175
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.020395858213305473,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0006870470941066742,
      "step": 180
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.016721302643418312,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.0006109749898314476,
      "step": 185
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.02269955538213253,
      "learning_rate": 1.1e-06,
      "loss": 0.0007013730704784393,
      "step": 190
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.018245233222842216,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.0006785429082810879,
      "step": 195
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.01847158744931221,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.0006762909702956677,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0003925538039766252,
      "eval_runtime": 25.5298,
      "eval_samples_per_second": 3.917,
      "eval_steps_per_second": 0.979,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 210488844288000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}