trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008923830643542047,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.8500534296035767,
      "learning_rate": 4.997769042339115e-05,
      "loss": 5.7067,
      "step": 100
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.29711076617240906,
      "learning_rate": 4.995538084678229e-05,
      "loss": 4.9888,
      "step": 200
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.21760140359401703,
      "learning_rate": 4.9933071270173436e-05,
      "loss": 4.7622,
      "step": 300
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.2236577719449997,
      "learning_rate": 4.991076169356459e-05,
      "loss": 4.7175,
      "step": 400
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.18726830184459686,
      "learning_rate": 4.9888452116955725e-05,
      "loss": 4.6896,
      "step": 500
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.3301438093185425,
      "learning_rate": 4.986614254034687e-05,
      "loss": 4.6776,
      "step": 600
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.23270975053310394,
      "learning_rate": 4.984383296373802e-05,
      "loss": 4.6656,
      "step": 700
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.26907047629356384,
      "learning_rate": 4.982152338712916e-05,
      "loss": 4.6493,
      "step": 800
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.22385388612747192,
      "learning_rate": 4.979921381052031e-05,
      "loss": 4.6447,
      "step": 900
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.28366366028785706,
      "learning_rate": 4.9776904233911454e-05,
      "loss": 4.632,
      "step": 1000
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.26614850759506226,
      "learning_rate": 4.975459465730259e-05,
      "loss": 4.6319,
      "step": 1100
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.3065544068813324,
      "learning_rate": 4.973228508069374e-05,
      "loss": 4.6223,
      "step": 1200
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.23633620142936707,
      "learning_rate": 4.970997550408489e-05,
      "loss": 4.619,
      "step": 1300
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.2925296127796173,
      "learning_rate": 4.968766592747603e-05,
      "loss": 4.616,
      "step": 1400
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.3636851906776428,
      "learning_rate": 4.9665356350867176e-05,
      "loss": 4.6118,
      "step": 1500
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.3567110598087311,
      "learning_rate": 4.964304677425832e-05,
      "loss": 4.6092,
      "step": 1600
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.35951370000839233,
      "learning_rate": 4.9620737197649465e-05,
      "loss": 4.6004,
      "step": 1700
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.2747381329536438,
      "learning_rate": 4.959842762104061e-05,
      "loss": 4.5976,
      "step": 1800
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.33775028586387634,
      "learning_rate": 4.9576118044431754e-05,
      "loss": 4.594,
      "step": 1900
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.2855284810066223,
      "learning_rate": 4.95538084678229e-05,
      "loss": 4.5928,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 224119,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1.5251220029472768e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}