trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2747603833865815,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06389776357827476,
      "grad_norm": 27.007149720149624,
      "learning_rate": 1.8750000000000003e-06,
      "loss": 3.0251,
      "step": 10
    },
    {
      "epoch": 0.12779552715654952,
      "grad_norm": 7.200384353707933,
      "learning_rate": 3.958333333333333e-06,
      "loss": 2.2511,
      "step": 20
    },
    {
      "epoch": 0.19169329073482427,
      "grad_norm": 3.556500087950233,
      "learning_rate": 6.041666666666667e-06,
      "loss": 1.6305,
      "step": 30
    },
    {
      "epoch": 0.25559105431309903,
      "grad_norm": 2.6746825713695674,
      "learning_rate": 8.125000000000001e-06,
      "loss": 1.2942,
      "step": 40
    },
    {
      "epoch": 0.3194888178913738,
      "grad_norm": 3.016385157178359,
      "learning_rate": 9.999862102299874e-06,
      "loss": 1.1516,
      "step": 50
    },
    {
      "epoch": 0.38338658146964855,
      "grad_norm": 2.6763627648882995,
      "learning_rate": 9.983323579940351e-06,
      "loss": 1.0652,
      "step": 60
    },
    {
      "epoch": 0.4472843450479233,
      "grad_norm": 2.4049859456438094,
      "learning_rate": 9.939310009499348e-06,
      "loss": 0.9943,
      "step": 70
    },
    {
      "epoch": 0.5111821086261981,
      "grad_norm": 2.105383899953641,
      "learning_rate": 9.868064055324204e-06,
      "loss": 0.9601,
      "step": 80
    },
    {
      "epoch": 0.5750798722044729,
      "grad_norm": 2.1151352790518603,
      "learning_rate": 9.76997852474223e-06,
      "loss": 0.9231,
      "step": 90
    },
    {
      "epoch": 0.6389776357827476,
      "grad_norm": 1.792736838810565,
      "learning_rate": 9.645594202357438e-06,
      "loss": 0.9041,
      "step": 100
    },
    {
      "epoch": 0.7028753993610224,
      "grad_norm": 1.8385962515662637,
      "learning_rate": 9.495596868489588e-06,
      "loss": 0.8842,
      "step": 110
    },
    {
      "epoch": 0.7667731629392971,
      "grad_norm": 2.05797408169935,
      "learning_rate": 9.320813518194084e-06,
      "loss": 0.8689,
      "step": 120
    },
    {
      "epoch": 0.8306709265175719,
      "grad_norm": 2.0006315711572107,
      "learning_rate": 9.122207801708802e-06,
      "loss": 0.8651,
      "step": 130
    },
    {
      "epoch": 0.8945686900958466,
      "grad_norm": 2.0622583744546685,
      "learning_rate": 8.900874711466436e-06,
      "loss": 0.8368,
      "step": 140
    },
    {
      "epoch": 0.9584664536741214,
      "grad_norm": 1.9281533048022628,
      "learning_rate": 8.658034544965003e-06,
      "loss": 0.8362,
      "step": 150
    },
    {
      "epoch": 1.0191693290734825,
      "grad_norm": 1.7856911939628375,
      "learning_rate": 8.395026176781627e-06,
      "loss": 0.8083,
      "step": 160
    },
    {
      "epoch": 1.0830670926517572,
      "grad_norm": 1.857546453101415,
      "learning_rate": 8.113299676823614e-06,
      "loss": 0.7305,
      "step": 170
    },
    {
      "epoch": 1.1469648562300319,
      "grad_norm": 1.870887786495633,
      "learning_rate": 7.814408315515419e-06,
      "loss": 0.7347,
      "step": 180
    },
    {
      "epoch": 1.2108626198083068,
      "grad_norm": 1.936193043129797,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.7142,
      "step": 190
    },
    {
      "epoch": 1.2747603833865815,
      "grad_norm": 2.083355561746048,
      "learning_rate": 7.1718081885702905e-06,
      "loss": 0.7132,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 471,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 15559929102336.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}