last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007064641469445425,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028258565877781704,
      "grad_norm": NaN,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00028258565877781704,
      "eval_loss": NaN,
      "eval_runtime": 91.2489,
      "eval_samples_per_second": 16.329,
      "eval_steps_per_second": 8.164,
      "step": 1
    },
    {
      "epoch": 0.0005651713175556341,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0008477569763334511,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0011303426351112682,
      "grad_norm": NaN,
      "learning_rate": 4.997620553954645e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.001412928293889085,
      "grad_norm": NaN,
      "learning_rate": 4.990486745229364e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0016955139526669022,
      "grad_norm": NaN,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.001978099611444719,
      "grad_norm": NaN,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0022606852702225363,
      "grad_norm": NaN,
      "learning_rate": 4.940740017799833e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.002543270929000353,
      "grad_norm": NaN,
      "learning_rate": 4.914814565722671e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00282585658777817,
      "grad_norm": NaN,
      "learning_rate": 4.884292376870567e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0031084422465559873,
      "grad_norm": NaN,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0033910279053338045,
      "grad_norm": NaN,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.003673613564111621,
      "grad_norm": NaN,
      "learning_rate": 4.765769467591625e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.003956199222889438,
      "grad_norm": NaN,
      "learning_rate": 4.717527082945554e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0042387848816672555,
      "grad_norm": NaN,
      "learning_rate": 4.665063509461097e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.004521370540445073,
      "grad_norm": NaN,
      "learning_rate": 4.608478614532215e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.00480395619922289,
      "grad_norm": NaN,
      "learning_rate": 4.54788011072248e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.005086541858000706,
      "grad_norm": NaN,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.005369127516778523,
      "grad_norm": NaN,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.00565171317555634,
      "grad_norm": NaN,
      "learning_rate": 4.34319334202531e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0059342988343341575,
      "grad_norm": NaN,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.006216884493111975,
      "grad_norm": NaN,
      "learning_rate": 4.188975519039151e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.006499470151889792,
      "grad_norm": NaN,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.006782055810667609,
      "grad_norm": NaN,
      "learning_rate": 4.021903572521802e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.007064641469445425,
      "grad_norm": NaN,
      "learning_rate": 3.933941090877615e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.007064641469445425,
      "eval_loss": NaN,
      "eval_runtime": 90.8959,
      "eval_samples_per_second": 16.392,
      "eval_steps_per_second": 8.196,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5761228924256256.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}