trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029858768027231197,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9905845351487463e-05,
      "grad_norm": 5.78125,
      "learning_rate": 5e-05,
      "loss": 3.0625,
      "step": 1
    },
    {
      "epoch": 0.0019905845351487466,
      "grad_norm": 2.5,
      "learning_rate": 4.996715568206701e-05,
      "loss": 1.3333,
      "step": 100
    },
    {
      "epoch": 0.003981169070297493,
      "grad_norm": 2.46875,
      "learning_rate": 4.99339796033468e-05,
      "loss": 1.29,
      "step": 200
    },
    {
      "epoch": 0.005971753605446239,
      "grad_norm": 2.375,
      "learning_rate": 4.99008035246266e-05,
      "loss": 1.28,
      "step": 300
    },
    {
      "epoch": 0.007962338140594986,
      "grad_norm": 2.3125,
      "learning_rate": 4.9867627445906404e-05,
      "loss": 1.3,
      "step": 400
    },
    {
      "epoch": 0.009952922675743733,
      "grad_norm": 2.3125,
      "learning_rate": 4.9834451367186206e-05,
      "loss": 1.28,
      "step": 500
    },
    {
      "epoch": 0.011943507210892478,
      "grad_norm": 2.25,
      "learning_rate": 4.980127528846601e-05,
      "loss": 1.29,
      "step": 600
    },
    {
      "epoch": 0.013934091746041224,
      "grad_norm": 2.53125,
      "learning_rate": 4.976809920974581e-05,
      "loss": 1.3,
      "step": 700
    },
    {
      "epoch": 0.015924676281189973,
      "grad_norm": 2.453125,
      "learning_rate": 4.973492313102561e-05,
      "loss": 1.29,
      "step": 800
    },
    {
      "epoch": 0.017915260816338718,
      "grad_norm": 2.4375,
      "learning_rate": 4.970174705230541e-05,
      "loss": 1.28,
      "step": 900
    },
    {
      "epoch": 0.019905845351487466,
      "grad_norm": 2.328125,
      "learning_rate": 4.966857097358521e-05,
      "loss": 1.29,
      "step": 1000
    },
    {
      "epoch": 0.02189642988663621,
      "grad_norm": 2.296875,
      "learning_rate": 4.963539489486501e-05,
      "loss": 1.28,
      "step": 1100
    },
    {
      "epoch": 0.023887014421784956,
      "grad_norm": 2.3125,
      "learning_rate": 4.960221881614481e-05,
      "loss": 1.29,
      "step": 1200
    },
    {
      "epoch": 0.025877598956933704,
      "grad_norm": 2.1875,
      "learning_rate": 4.956904273742461e-05,
      "loss": 1.29,
      "step": 1300
    },
    {
      "epoch": 0.02786818349208245,
      "grad_norm": 2.46875,
      "learning_rate": 4.953586665870441e-05,
      "loss": 1.28,
      "step": 1400
    },
    {
      "epoch": 0.029858768027231197,
      "grad_norm": 2.171875,
      "learning_rate": 4.950269057998421e-05,
      "loss": 1.29,
      "step": 1500
    }
  ],
  "logging_steps": 100,
  "max_steps": 150711,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6271008768000000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}